modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC] | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
timestamp[us, tz=UTC] | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
LoneStriker/SeaLLM-7B-v2-GGUF | LoneStriker | 2024-02-08T12:19:59Z | 492 | 5 | null | [
"gguf",
"multilingual",
"sea",
"en",
"zh",
"vi",
"id",
"th",
"ms",
"km",
"lo",
"my",
"tl",
"arxiv:2312.00738",
"arxiv:2205.11916",
"arxiv:2306.05179",
"arxiv:2306.05685",
"license:other",
"region:us"
]
| null | 2024-02-03T15:27:58Z | ---
license: other
license_name: seallms
license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
language:
- en
- zh
- vi
- id
- th
- ms
- km
- lo
- my
- tl
tags:
- multilingual
- sea
---
<p align="center">
<img src="seal_logo.png" width="200" />
</p>
# *SeaLLM-7B-v2* - Large Language Models for Southeast Asia
<p align="center">
<a href="https://huggingface.co/SeaLLMs/SeaLLM-7B-v2" target="_blank" rel="noopener"> 🤗 Tech Memo</a>
<a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B" target="_blank" rel="noopener"> 🤗 DEMO</a>
<a href="https://github.com/DAMO-NLP-SG/SeaLLMs" target="_blank" rel="noopener">Github</a>
<a href="https://arxiv.org/pdf/2312.00738.pdf" target="_blank" rel="noopener">Technical Report</a>
</p>
We introduce [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2), the state-of-the-art multilingual LLM for Southeast Asian (SEA) languages 🇬🇧 🇨🇳 🇻🇳 🇮🇩 🇹🇭 🇲🇾 🇰🇭 🇱🇦 🇲🇲 🇵🇭. It is the most significant upgrade since [SeaLLM-13B](https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat), with half the size, outperforming performance across diverse multilingual tasks, from world knowledge, math reasoning, instruction following, etc.
### Highlights
* [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) achieves the **7B-SOTA** on the **GSM8K** task with **78.2** score and outperforms GPT-3.5 in many GSM8K-translated tasks in SEA languages (🇨🇳 🇻🇳 🇮🇩 🇹🇭) as well as MGSM (🇨🇳 🇹🇭). It also surpasses GPT-3.5 in MATH for Thai 🇹🇭.
* It scores competitively against GPT-3.5 in many zero-shot commonsense benchmark, with **82.5, 68.3, 80.9** scores on Arc-C, Winogrande, and Hellaswag.
* It achieves **7.54** score on the 🇬🇧 **MT-bench**, it ranks 3rd place on the leaderboard for 7B category and is the most outperforming multilingual model.
* It scores **45.46** on the VMLU benchmark for Vietnamese 🇻🇳, and is the only open-source multilingual model that can be competitive to monolingual models ([Vistral-7B](https://huggingface.co/Viet-Mistral/Vistral-7B-Chat)) of similar sizes.
### Release and DEMO
- DEMO: [SeaLLMs/SeaLLM-7B](https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B).
- Technical report: [Arxiv: SeaLLMs - Large Language Models for Southeast Asia](https://arxiv.org/pdf/2312.00738.pdf).
- Model weights: [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2).
<blockquote style="color:red">
<p><strong style="color: red">Terms of Use and License</strong>:
By using our released weights, codes, and demos, you agree to and comply with the terms and conditions specified in our <a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b/edit/main/LICENSE" target="_blank" rel="noopener">SeaLLMs Terms Of Use</a>.
</blockquote>
> **Disclaimer**:
> We must note that even though the weights, codes, and demos are released in an open manner, similar to other pre-trained language models, and despite our best efforts in red teaming and safety fine-tuning and enforcement, our models come with potential risks, including but not limited to inaccurate, misleading or potentially harmful generation.
> Developers and stakeholders should perform their own red teaming and provide related security measures before deployment, and they must abide by and comply with local governance and regulations.
> In no event shall the authors be held liable for any claim, damages, or other liability arising from the use of the released weights, codes, or demos.
> The logo was generated by DALL-E 3.
### What's new since SeaLLM-13B-v1 and SeaLLM-7B-v1?
* SeaLLM-7B-v2 is continue-pretrained from [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) and underwent carefully designed tuning with focus in reasoning.
## Evaluation
### Zero-shot Multilingual Math Reasoning
[SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) achieves with **78.2** score on the GSM8K, making it the **state of the art** in the realm of 7B models. It also outperforms GPT-3.5 in the same GSM8K benchmark as translated into SEA languages (🇨🇳 🇻🇳 🇮🇩 🇹🇭). [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) also surpasses GPT-3.5 on the Thai-translated MATH benchmark, with **22.4** vs 18.1 scores.
<details>
<summary>See details on English and translated GSM8K and MATH</summary>
<br>
| Model | GSM8K<br>en | MATH<br>en | GSM8K<br>zh | MATH<br>zh | GSM8K<br>vi | MATH<br>vi | GSM8K<br>id | MATH<br>id | GSM8K<br>th | MATH<br>th
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| GPT-3.5 | 80.8 | 34.1 | 48.2 | 21.5 | 55 | 26.5 | 64.3 | 26.4 | 35.8 | 18.1
| Qwen-14B-chat | 61.4 | 18.4 | 41.6 | 11.8 | 33.6 | 3.6 | 44.7 | 8.6 | 22 | 6
| Vistral-7b-chat | 48.2 | 12.5 | | | 48.7 | 3.1 | | | |
| SeaLLM-7B-v2 | 78.2 | 27.5 | 53.7 | 17.6 | 69.9 | 23.8 | 71.5 | 24.4 | 59.6 | 22.4
</details>
#### Zero-shot MGSM
[SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) also outperforms GPT-3.5 and Qwen-14B on the multilingual MGSM for Zh and Th.
| Model | MGSM-Zh | MGSM-Th
|-----| ----- | ---
| ChatGPT (reported) | 61.2* | 47.2*
| Qwen-14B-chat | 59.6 | 28
| SeaLLM-7B-v2 | **64.8** | **62.4**
### Zero-shot Commonsense Reasoning
We compare [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) with ChatGPT and Mistral-7B-instruct on various zero-shot commonsense benchmarks (Arc-Challenge, Winogrande and Hellaswag). We use the 2-stage technique in [(Kojima et al., 2023)](https://arxiv.org/pdf/2205.11916.pdf) to grab the answer. Note that we **DID NOT** use "Let's think step-by-step" to invoke explicit CoT.
| Model | Arc-Challenge | Winogrande | Hellaswag
|-----| ----- | --- | -- |
| ChatGPT (reported) | 84.6* | 66.8* | 72.0*
| ChatGPT (reproduced) | 84.1 | 63.1 | 79.5
| Mistral-7B-Instruct | 68.1 | 56.4 | 45.6
| SeaLLM-7B-v2 | 82.5 | 68.3 | 80.9
### Multilingual World Knowledge
We evaluate models on 3 benchmarks following the recommended default setups: 5-shot MMLU for En, 3-shot [M3Exam](https://arxiv.org/pdf/2306.05179.pdf) (M3e) for En, Zh, Vi, Id, Th, and zero-shot [VMLU](https://vmlu.ai/) for Vi.
| Model | Langs | En<br>MMLU | En<br>M3e | Zh<br>M3e | Vi<br>M3e | Vi<br>VMLU | Id<br>M3e | Th<br>M3e
|-----| ----- | --- | -- | ----- | ---- | --- | --- | --- |
| ChatGPT | Multi | 68.90 | 75.46 | 60.20 | 58.64 | 46.32 | 49.27 | 37.41
|-----| ----- | --- | -- | ----- | ---- | --- | --- | --- |
| SeaLLM-13B | Multi | 52.78 | 62.69 | 44.50 | 46.45 | | 39.28 | 36.39
| Vistral-7B | Mono | 56.86 | 67.00 | 44.56 | 54.33 | 50.03 | 36.49 | 25.27
| SeaLLM-7B-v2 | Multi | 60.72 | 70.91 | 55.43 | 51.15 | 45.46 | 42.25 | 35.52
### MT-Bench
On the English [MT-bench](https://arxiv.org/abs/2306.05685) metric, SeaLLM-7B-v2 achieves **7.54** score on the MT-bench (3rd place on the leaderboard for 7B category), outperforms many 70B models and is arguably the only one that handles 10 SEA languages.
Refer to [mt_bench/seallm_7b_v2.jsonl](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2/blob/main/evaluation/mt_bench/seallm_7b_v2.jsonl) for the MT-bench predictions of SeaLLM-7B-v2.
| Model | Access | Langs | MT-Bench
| --- | --- | --- | --- |
| GPT-4-turbo | closed | multi | 9.32
| GPT-4-0613 | closed | multi | 9.18
| Mixtral-8x7b (46B) | open | multi | 8.3
| Starling-LM-7B-alpha | open | mono (en) | 8.0
| OpenChat-3.5-7B | open | mono (en) | 7.81
| **SeaLLM-7B-v2** | **open** | **multi (10+)** | **7.54**
| [Qwen-14B](https://huggingface.co/Qwen/Qwen-14B-Chat) | open | multi | 6.96
| [Llama-2-70B](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) | open | mono (en) | 6.86
| Mistral-7B-instuct | open | mono (en) | 6.84
### Sea-Bench
Similar to MT-Bench, [Sea-bench](https://huggingface.co/datasets/SeaLLMs/Sea-bench) is a set of categorized instruction test sets to measure models' ability as an assistant that is specifically focused on 9 SEA languages, including non-Latin low-resource languages.
As shown, the huge improvements come from math-reasoning, reaching GPT-3.5 level of performance.
Refer to [sea_bench/seallm_7b_v2.jsonl](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2/blob/main/evaluation/sea_bench/seallm_7b_v2.jsonl) for the Sea-bench predictions of SeaLLM-7B-v2.
### Usage
#### Instruction format
```python
prompt = """<|im_start|>system
You are a helpful assistant.</s>
<|im_start|>user
Hello world</s>
<|im_start|>assistant
Hi there, how can I help?</s>
# ! ENSURE 1 and only 1 bos `<s>` at the beginning of sequence
print(tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt)))
['<s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'system', '<0x0A>', 'You', '▁are', '▁a', '▁helpful', '▁assistant', '.', '</s>', '▁', '<0x0A>', '<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '</s>', '▁', '<0x0A>', '<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Hi', '▁there', ',', '▁how', '▁can', '▁I', '▁help', '?', '</s>', '▁', '<0x0A>']
"""
```
#### Using transformers's chat_template
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("SeaLLMs/SeaLLM-7B-v2", torch_dtype=torch.bfloat16, device_map=device)
tokenizer = AutoTokenizer.from_pretrained("SeaLLMs/SeaLLM-7B-v2")
messages = [
{"role": "user", "content": "Hello world"},
{"role": "assistant", "content": "Hi there, how can I help you today?"},
{"role": "user", "content": "Explain general relativity in details."}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
print(tokenizer.convert_ids_to_tokens(encodeds[0]))
# ['<s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '</s>', '▁', '<0x0A>', '<', '|', 'im ....
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True, pad_token_id=tokenizer.pad_token_id)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
#### Using vLLM
```python
from vllm import LLM, SamplingParams
TURN_TEMPLATE = "<|im_start|>{role}\n{content}</s>"
TURN_PREFIX = "<|im_start|>{role}\n"
def seallm_chat_convo_format(conversations, add_assistant_prefix: bool, system_prompt=None):
# conversations: list of dict with key `role` and `content` (openai format)
if conversations[0]['role'] != 'system' and system_prompt is not None:
conversations = [{"role": "system", "content": system_prompt}] + conversations
text = ''
for turn_id, turn in enumerate(conversations):
prompt = TURN_TEMPLATE.format(role=turn['role'], content=turn['content'])
text += prompt
if add_assistant_prefix:
prompt = TURN_PREFIX.format(role='assistant')
text += prompt
return text
sparams = SamplingParams(temperature=0.1, max_tokens=1024, stop=['</s>', '<|im_start|>'])
llm = LLM("SeaLLMs/SeaLLM-7B-v2", dtype="bfloat16")
message = "Explain general relativity in details."
prompt = seallm_chat_convo_format(message, True)
gen = llm.generate(prompt, sampling_params)
print(gen[0].outputs[0].text)
```
## Acknowledgement to Our Linguists
We would like to express our special thanks to our professional and native linguists, Tantong Champaiboon, Nguyen Ngoc Yen Nhi and Tara Devina Putri, who helped build, evaluate, and fact-check our sampled pretraining and SFT dataset as well as evaluating our models across different aspects, especially safety.
## Citation
If you find our project useful, we hope you would kindly star our repo and cite our work as follows: Corresponding Author: [[email protected]](mailto:[email protected])
**Author list and order will change!**
* `*` and `^` are equal contributions.
```
@article{damonlpsg2023seallm,
author = {Xuan-Phi Nguyen*, Wenxuan Zhang*, Xin Li*, Mahani Aljunied*,
Zhiqiang Hu, Chenhui Shen^, Yew Ken Chia^, Xingxuan Li, Jianyu Wang,
Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang,
Chaoqun Liu, Hang Zhang, Lidong Bing},
title = {SeaLLMs - Large Language Models for Southeast Asia},
year = 2023,
Eprint = {arXiv:2312.00738},
}
```
|
mradermacher/UltraCatunaMayo-GGUF | mradermacher | 2024-05-06T06:02:10Z | 492 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/UltraMerge-7B",
"Eric111/CatunaMayo",
"en",
"base_model:Eric111/UltraCatunaMayo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-23T22:09:28Z | ---
base_model: Eric111/UltraCatunaMayo
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/UltraMerge-7B
- Eric111/CatunaMayo
---
## About
static quants of https://huggingface.co/Eric111/UltraCatunaMayo
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/UltraCatunaMayo-GGUF/resolve/main/UltraCatunaMayo.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
NyxKrage/llama3-42b-v0-imat-gguf | NyxKrage | 2024-04-22T01:56:38Z | 492 | 5 | null | [
"gguf",
"region:us"
]
| null | 2024-04-21T22:36:41Z | # llama-3-42b-v0 imatrix gguf
[chargoddard/llama-3-42b-v0](https://huggingface.co/chargoddard/llama3-42b-v0)
imatrix generated from [wikitext2](https://huggingface.co/datasets/wikitext) test split with fp16 model
Final estimate: PPL = 7.1996 +/- 0.04519
|
Niggendar/tPonynai3_v41OptimizedFromV4 | Niggendar | 2024-04-29T19:33:33Z | 492 | 7 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2024-04-29T19:27:12Z | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
nbeerbower/llama-3-bophades-v3-8B | nbeerbower | 2024-05-23T12:21:07Z | 492 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"dataset:jondurbin/truthy-dpo-v0.1",
"dataset:kyujinpy/orca_math_dpo",
"base_model:nbeerbower/llama-3-wissenschaft-8B",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-02T23:47:28Z | ---
library_name: transformers
base_model:
- nbeerbower/llama-3-wissenschaft-8B
datasets:
- jondurbin/truthy-dpo-v0.1
- kyujinpy/orca_math_dpo
license: other
license_name: llama3
---
# llama-3-bophades-v3-8B
This model is based on Llama-3-8b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)
[nbeerbower/llama-3-wissenschaft-8B](https://huggingface.co/nbeerbower/llama-3-wissenschaft-8B) finetuned on [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1) and [kyujinpy/orca_math_dpo](https://huggingface.co/datasets/kyujinpy/orca_math_dpo).
### Method
Finetuned using an A100 on Google Colab.
[Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne)
### Configuration
Dataset preperation and message formatting:
```python
def chatml_format(example):
# Initialize formatted system message
system = ""
# Check if 'system' field exists and is not None
if example.get('system'):
system = "<|im_start|>system\n" + example['system'] + "<|im_end|>\n"
# Format instruction
instruction = ""
if example.get('prompt'):
instruction = example['prompt']
if example.get('question'):
instruction = example['question']
prompt = "<|im_start|>user\n" + instruction + "<|im_end|>\n<|im_start|>assistant\n"
# Format chosen answer
chosen = example['chosen'] + "<|im_end|>\n"
# Format rejected answer
rejected = example['rejected'] + "<|im_end|>\n"
return {
"prompt": system + prompt,
"chosen": chosen,
"rejected": rejected,
}
# Array of datasets to concat
ds = [
"jondurbin/truthy-dpo-v0.1",
"kyujinpy/orca_math_dpo"
]
# load_dataset and combine all
loaded_datasets = [load_dataset(dataset_name, split='train') for dataset_name in ds]
dataset = concatenate_datasets(loaded_datasets)
# Save columns
original_columns = dataset.column_names
# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"
# Format dataset
dataset = dataset.map(
chatml_format,
remove_columns=original_columns
)
```
LoRA, model, and training settings:
```python
# LoRA configuration
peft_config = LoraConfig(
r=16,
lora_alpha=16,
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM",
target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
)
# Model to fine-tune
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
load_in_4bit=True
)
model.config.use_cache = False
# Reference model
ref_model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
load_in_4bit=True
)
# Training arguments
training_args = TrainingArguments(
per_device_train_batch_size=2,
gradient_accumulation_steps=4,
gradient_checkpointing=True,
learning_rate=5e-5,
lr_scheduler_type="cosine",
max_steps=1000,
save_strategy="no",
logging_steps=1,
output_dir=new_model,
optim="paged_adamw_32bit",
warmup_steps=100,
bf16=True,
report_to="wandb",
)
# Create DPO trainer
dpo_trainer = DPOTrainer(
model,
ref_model,
args=training_args,
train_dataset=dataset,
tokenizer=tokenizer,
peft_config=peft_config,
beta=0.1,
max_prompt_length=2048,
max_length=4096,
force_use_ref_model=True
)
# Fine-tune model with DPO
dpo_trainer.train()
``` |
mmnga/Meta-Llama-3-8B-Instruct-gguf | mmnga | 2024-05-12T08:08:38Z | 492 | 0 | null | [
"gguf",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"license:llama3",
"region:us"
]
| null | 2024-05-12T07:18:00Z |
---
license: llama3
language:
- en
- ja
datasets:
- TFMC/imatrix-dataset-for-japanese-llm
---
# Meta-Llama-3-8B-Instruct-gguf
[meta-llamaさんが公開しているMeta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)のggufフォーマット変換版です。
imatrixのデータは[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用して作成しました。
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'Meta-Llama-3-8B-Instruct-Q4_0.gguf' -n 128 -p 'こんにちわ.'
```
|
thesven/Mistral-7B-Instruct-v0.3-GGUF | thesven | 2024-05-24T19:03:04Z | 492 | 0 | null | [
"gguf",
"license:apache-2.0",
"region:us"
]
| null | 2024-05-23T11:43:08Z | ---
license: apache-2.0
---
# Model Card for Mistral-7B-Instruct-v0.3
## Quantization Description
This repo contains a GGUF Quantized versions of Mistral 7B Instruct v0.3
<div style="text-align: center;">
<a href="https://github.com/thesven/GGUF-n-Go">
<img src="https://github.com/thesven/GGUF-n-Go/blob/main/assets/quantized_with.png?raw=true" alt="image/png" style="max-width: 350px;">
</a>
</div>
## Model Description
The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.
Mistral-7B-v0.3 has the following changes compared to [Mistral-7B-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/edit/main/README.md)
- Extended vocabulary to 32768
- Supports v3 Tokenizer
- Supports function calling
## Generate with `transformers`
If you want to use Hugging Face `transformers` to generate text, you can do something like this.
```py
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
pretrained_model_name = "thesven/Mistral-7B-Instruct-v0.3-GPTQ"
device = "cuda:0"
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name)
# Load the model with the specified configuration and move to device
model = AutoModelForCausalLM.from_pretrained(
pretrained_model_name,
device_map="auto",
)
print(model)
# Set EOS token ID
model.eos_token_id = tokenizer.eos_token_id
# Move model to the specified device
model.to(device)
# Define the input text
input_text = "What is PEFT finetuning?"
# Encode the input text
input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
# Generate output
output = model.generate(input_ids, max_length=1000)
# Decode the generated output
decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)
# Print the decoded output
for i, sequence in enumerate(decoded_output):
print(f"Generated Sequence {i+1}: {sequence}")
del model
torch.cuda.empty_cache()
```
## Limitations
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall |
QuantFactory/Hermes-2-Theta-Llama-3-8B-GGUF | QuantFactory | 2024-05-24T07:05:40Z | 492 | 0 | null | [
"gguf",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"merges",
"text-generation",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Hermes-2-Theta-Llama-3-8B",
"license:apache-2.0",
"region:us"
]
| text-generation | 2024-05-24T05:00:49Z | ---
base_model: NousResearch/Hermes-2-Theta-Llama-3-8B
tags:
- Llama-3
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
- function calling
- json mode
- axolotl
- merges
model-index:
- name: Hermes-2-Pro-Llama-3-Instruct-8B-Merge
results: []
language:
- en
datasets:
- teknium/OpenHermes-2.5
widget:
- example_title: Hermes 2 Pro Llama-3 Instruct Merge
messages:
- role: system
content: >-
You are a sentient, superintelligent artificial general intelligence, here
to teach and assist me.
- role: user
content: >-
Write a short story about Goku discovering kirby has teamed up with Majin
Buu to destroy the world.
license: apache-2.0
pipeline_tag: text-generation
---
# - Hermes-2 Θ Llama-3 8B-GGUF
- This is quantized version of [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) created using llama.cpp
## Model Description
Hermes-2 Θ (Theta) is the first experimental merged model released by [Nous Research](https://nousresearch.com/), in collaboration with Charles Goddard at [Arcee](https://www.arcee.ai/), the team behind MergeKit.
Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model.
## Example Outputs
### Create New Mythos:
### Chat with a Meta-Cognitive Entity
### Ask for a structured JSON output:
# Prompt Format
Hermes 2 Θ uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling. While the system prompt looks complicated, we have created a GitHub repo containing code to easily build these based on real python functions.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5529|± |0.0145|
| | |acc_norm|0.5870|± |0.0144|
|arc_easy | 0|acc |0.8371|± |0.0076|
| | |acc_norm|0.8144|± |0.0080|
|boolq | 1|acc |0.8599|± |0.0061|
|hellaswag | 0|acc |0.6133|± |0.0049|
| | |acc_norm|0.7989|± |0.0040|
|openbookqa | 0|acc |0.3940|± |0.0219|
| | |acc_norm|0.4680|± |0.0223|
|piqa | 0|acc |0.8063|± |0.0092|
| | |acc_norm|0.8156|± |0.0090|
|winogrande | 0|acc |0.7372|± |0.0124|
```
Average: 72.59
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2441|± |0.0270|
| | |acc_norm|0.2441|± |0.0270|
|agieval_logiqa_en | 0|acc |0.3687|± |0.0189|
| | |acc_norm|0.3840|± |0.0191|
|agieval_lsat_ar | 0|acc |0.2304|± |0.0278|
| | |acc_norm|0.2174|± |0.0273|
|agieval_lsat_lr | 0|acc |0.5471|± |0.0221|
| | |acc_norm|0.5373|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6617|± |0.0289|
| | |acc_norm|0.6357|± |0.0294|
|agieval_sat_en | 0|acc |0.7670|± |0.0295|
| | |acc_norm|0.7379|± |0.0307|
|agieval_sat_en_without_passage| 0|acc |0.4417|± |0.0347|
| | |acc_norm|0.4223|± |0.0345|
|agieval_sat_math | 0|acc |0.4000|± |0.0331|
| | |acc_norm|0.3455|± |0.0321|
```
Average: 44.05
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.6000|± |0.0356|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6585|± |0.0247|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.2340|± |0.0224|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2980|± |0.0205|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2057|± |0.0153|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5367|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4040|± |0.0220|
|bigbench_navigate | 0|multiple_choice_grade|0.4970|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7075|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4821|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2295|± |0.0133|
|bigbench_snarks | 0|multiple_choice_grade|0.6906|± |0.0345|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5375|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.6270|± |0.0153|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2216|± |0.0118|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1594|± |0.0088|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5367|± |0.0288|
```
Average: 44.13
**IFEval**: 72.64
**MT_Bench**: Turn 1 - 8.3875, Turn 2 - 8.00625, Average - 8.196875
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Theta-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Theta-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
 |
RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf | RichardErkhov | 2024-05-27T06:50:23Z | 492 | 0 | null | [
"gguf",
"arxiv:1910.09700",
"region:us"
]
| null | 2024-05-26T08:50:42Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-3-70B-japanese-suzume-vector-v0.1 - GGUF
- Model creator: https://huggingface.co/mmnga/
- Original model: https://huggingface.co/mmnga/Llama-3-70B-japanese-suzume-vector-v0.1/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q2_K.gguf) | Q2_K | 24.56GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.IQ3_XS.gguf) | IQ3_XS | 27.29GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.IQ3_S.gguf) | IQ3_S | 28.79GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_S.gguf) | Q3_K_S | 28.79GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.IQ3_M.gguf) | IQ3_M | 29.74GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K.gguf) | Q3_K | 31.91GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_M.gguf) | Q3_K_M | 31.91GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_L.gguf) | Q3_K_L | 34.59GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.IQ4_XS.gguf) | IQ4_XS | 35.64GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q4_0.gguf) | Q4_0 | 37.22GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | IQ4_NL | 37.58GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q4_K_S | 37.58GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q4_K | 39.6GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q4_K_M | 39.6GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q4_1 | 41.27GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q5_0 | 45.32GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q5_K_S | 45.32GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q5_K | 46.52GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q5_K_M | 46.52GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q5_1 | 49.36GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q6_K | 53.91GB |
| [Llama-3-70B-japanese-suzume-vector-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/mmnga_-_Llama-3-70B-japanese-suzume-vector-v0.1-gguf/tree/main/) | Q8_0 | 69.83GB |
Original model description:
---
library_name: transformers
tags:
- llama3
license: llama3
language:
- ja
- en
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
*実験モデルです / This is an experimental model.*
[lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese)と、
[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)の差分をchat-vectorアプローチで抽出し、
[meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)に適用しました
## 結果
差分が小さいのかあまり変化がありませんでした
今後は倍率など付与してみようと思います.
## 手順/procedure
[chat_vector.ipynb](https://huggingface.co/mmnga/Llama-3-70B-japanese-suzume-vector/blob/main/notebook/chat_vector.ipynb)
- ja
1. `meta-llama/Meta-Llama-3-8B-Instruct`と`lightblue/suzume-llama-3-8B-japanese`の差分を作成
2. shapeが異なるので、差分をmeta-llama/Meta-Llama-3-70B-Instruct用にアップサンプリング
3. 前から 8-layer、最後から8-layerはそのまま適用
4. 中間layerを引き延ばして適用
- en
1. Create the difference between `meta-llama/Meta-Llama-3-8B-Instruct` and `lightblue/zume-llama-3-8B-japanese`
2. Since the shapes are different, the difference is upsampled for meta-llama/Meta-Llama-3-70B-Instruct
3. Apply the 8 layers from the front and 8 layers from the end as they are.
4. Continue applying the middle layer
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
kwoncho/gaincut_news_pre2021_2 | kwoncho | 2024-05-28T02:51:30Z | 492 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2024-05-28T02:50:36Z | Entry not found |
mradermacher/quill-7b-i1-GGUF | mradermacher | 2024-05-30T04:40:52Z | 492 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:billyjoe/quill-7b",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-29T17:01:25Z | ---
base_model: billyjoe/quill-7b
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/billyjoe/quill-7b
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/quill-7b-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/quill-7b-i1-GGUF/resolve/main/quill-7b.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
<!-- end -->
|
kaushiksiva07/Mistral-7B-Instruct-v0.2-Q4_0-GGUF | kaushiksiva07 | 2024-06-03T22:45:50Z | 492 | 0 | null | [
"gguf",
"finetuned",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
]
| text-generation | 2024-06-03T22:45:38Z | ---
license: apache-2.0
tags:
- finetuned
- llama-cpp
- gguf-my-repo
base_model: mistralai/Mistral-7B-Instruct-v0.2
pipeline_tag: text-generation
inference: true
widget:
- messages:
- role: user
content: What is your favorite condiment?
---
# kaushiksiva07/Mistral-7B-Instruct-v0.2-Q4_0-GGUF
This model was converted to GGUF format from [`mistralai/Mistral-7B-Instruct-v0.2`](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama --hf-repo kaushiksiva07/Mistral-7B-Instruct-v0.2-Q4_0-GGUF --hf-file mistral-7b-instruct-v0.2-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo kaushiksiva07/Mistral-7B-Instruct-v0.2-Q4_0-GGUF --hf-file mistral-7b-instruct-v0.2-q4_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./main --hf-repo kaushiksiva07/Mistral-7B-Instruct-v0.2-Q4_0-GGUF --hf-file mistral-7b-instruct-v0.2-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./server --hf-repo kaushiksiva07/Mistral-7B-Instruct-v0.2-Q4_0-GGUF --hf-file mistral-7b-instruct-v0.2-q4_0.gguf -c 2048
```
|
netcat420/MFANNv0.14-Q4_K_M-GGUF | netcat420 | 2024-06-24T05:07:43Z | 492 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"dataset:netcat420/MFANN",
"base_model:netcat420/MFANNv0.14",
"license:llama3",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-21T04:10:29Z | ---
base_model: netcat420/MFANNv0.14
datasets:
- netcat420/MFANN
language:
- en
library_name: transformers
license: llama3
tags:
- llama-cpp
- gguf-my-repo
---
System prompt:
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful, respectful and honest assistant. Always answer as helpfully as possible. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. <|eot_id|>
# netcat420/MFANNv0.14-Q4_K_M-GGUF
This model was converted to GGUF format from [`netcat420/MFANNv0.14`](https://huggingface.co/netcat420/MFANNv0.14) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/netcat420/MFANNv0.14) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo netcat420/MFANNv0.14-Q4_K_M-GGUF --hf-file mfannv0.14-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo netcat420/MFANNv0.14-Q4_K_M-GGUF --hf-file mfannv0.14-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo netcat420/MFANNv0.14-Q4_K_M-GGUF --hf-file mfannv0.14-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo netcat420/MFANNv0.14-Q4_K_M-GGUF --hf-file mfannv0.14-q4_k_m.gguf -c 2048
```
|
classla/bcms-bertic | classla | 2021-10-29T08:20:06Z | 491 | 9 | transformers | [
"transformers",
"pytorch",
"electra",
"pretraining",
"hr",
"bs",
"sr",
"cnr",
"hbs",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2022-03-02T23:29:05Z | ---
language:
- hr
- bs
- sr
- cnr
- hbs
license: apache-2.0
---
# BERTić* [bert-ich] /bɜrtitʃ/ - A transformer language model for Bosnian, Croatian, Montenegrin and Serbian
* The name should resemble the facts (1) that the model was trained in Zagreb, Croatia, where diminutives ending in -ić (as in fotić, smajlić, hengić etc.) are very popular, and (2) that most surnames in the countries where these languages are spoken end in -ić (with diminutive etymology as well).
This Electra model was trained on more than 8 billion tokens of Bosnian, Croatian, Montenegrin and Serbian text.
***new*** We have published a version of this model fine-tuned on the named entity recognition task ([bcms-bertic-ner](https://huggingface.co/classla/bcms-bertic-ner)) and on the hate speech detection task ([bcms-bertic-frenk-hate](https://huggingface.co/classla/bcms-bertic-frenk-hate)).
If you use the model, please cite the following paper:
```
@inproceedings{ljubesic-lauc-2021-bertic,
title = "{BERT}i{\'c} - The Transformer Language Model for {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
author = "Ljube{\v{s}}i{\'c}, Nikola and Lauc, Davor",
booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2021.bsnlp-1.5",
pages = "37--42",
}
```
## Benchmarking
Comparing this model to [multilingual BERT](https://huggingface.co/bert-base-multilingual-cased) and [CroSloEngual BERT](https://huggingface.co/EMBEDDIA/crosloengual-bert) on the tasks of (1) part-of-speech tagging, (2) named entity recognition, (3) geolocation prediction, and (4) commonsense causal reasoning, shows the BERTić model to be superior to the other two.
### Part-of-speech tagging
Evaluation metric is (seqeval) microF1. Reported are means of five runs. Best results are presented in bold. Statistical significance is calculated between two best-performing systems via a two-tailed t-test (* p<=0.05, ** p<=0.01, *** p<=0.001, ***** p<=0.0001).
Dataset | Language | Variety | CLASSLA | mBERT | cseBERT | BERTić
---|---|---|---|---|---|---
hr500k | Croatian | standard | 93.87 | 94.60 | 95.74 | **95.81*****
reldi-hr | Croatian | internet non-standard | - | 88.87 | 91.63 | **92.28*****
SETimes.SR | Serbian | standard | 95.00 | 95.50 | **96.41** | 96.31
reldi-sr | Serbian | internet non-standard | - | 91.26 | 93.54 | **93.90*****
### Named entity recognition
Evaluation metric is (seqeval) microF1. Reported are means of five runs. Best results are presented in bold. Statistical significance is calculated between two best-performing systems via a two-tailed t-test (* p<=0.05, ** p<=0.01, *** p<=0.001, ***** p<=0.0001).
Dataset | Language | Variety | CLASSLA | mBERT | cseBERT | BERTić
---|---|---|---|---|---|---
hr500k | Croatian | standard | 80.13 | 85.67 | 88.98 | **89.21******
reldi-hr | Croatian | internet non-standard | - | 76.06 | 81.38 | **83.05******
SETimes.SR | Serbian | standard | 84.64 | **92.41** | 92.28 | 92.02
reldi-sr | Serbian | internet non-standard | - | 81.29 | 82.76 | **87.92******
### Geolocation prediction
The dataset comes from the VarDial 2020 evaluation campaign's shared task on [Social Media variety Geolocation prediction](https://sites.google.com/view/vardial2020/evaluation-campaign). The task is to predict the latitude and longitude of a tweet given its text.
Evaluation metrics are median and mean of distance between gold and predicted geolocations (lower is better). No statistical significance is computed due to large test set (39,723 instances). Centroid baseline predicts each text to be created in the centroid of the training dataset.
System | Median | Mean
---|---|---
centroid | 107.10 | 145.72
mBERT | 42.25 | 82.05
cseBERT | 40.76 | 81.88
BERTić | **37.96** | **79.30**
### Choice Of Plausible Alternatives
The dataset is a translation of the [COPA dataset](https://people.ict.usc.edu/~gordon/copa.html) into Croatian ([link to the dataset](http://hdl.handle.net/11356/1404)).
Evaluation metric is accuracy. Reported are means of five runs. Best results are presented in bold. Statistical significance is calculated between two best-performing systems via a two-tailed t-test (* p<=0.05, ** p<=0.01, *** p<=0.001, ***** p<=0.0001).
System | Accuracy
---|---
random | 50.00
mBERT | 54.12
cseBERT | 61.80
BERTić | **65.76****
|
NeelNanda/Attn_Only_4L512W_C4_Code | NeelNanda | 2022-10-26T23:38:06Z | 491 | 0 | transformers | [
"transformers",
"endpoints_compatible",
"region:us"
]
| null | 2022-10-26T23:30:52Z | Entry not found |
timm/tresnet_m.miil_in1k | timm | 2023-04-21T20:56:10Z | 491 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2003.13630",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-04-21T20:55:38Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for tresnet_m.miil_in1k
A TResNet image classification model. Trained on ImageNet-1k by paper authors.
The weights for this model have been remapped and modified from the originals to work with standard BatchNorm instead of InplaceABN. `inplace_abn` can be problematic to build recently and ends up slower with `memory_format=channels_last`, torch.compile(), etc.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 31.4
- GMACs: 5.8
- Activations (M): 7.3
- Image size: 224 x 224
- **Papers:**
- TResNet: High Performance GPU-Dedicated Architecture: https://arxiv.org/abs/2003.13630
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/Alibaba-MIIL/TResNet
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tresnet_m.miil_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tresnet_m.miil_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tresnet_m.miil_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@misc{ridnik2020tresnet,
title={TResNet: High Performance GPU-Dedicated Architecture},
author={Tal Ridnik and Hussam Lawen and Asaf Noy and Itamar Friedman},
year={2020},
eprint={2003.13630},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
Sao10K/Stheno-Variants-L2-13B-GGUF | Sao10K | 2023-09-08T16:40:15Z | 491 | 0 | null | [
"gguf",
"en",
"license:llama2",
"region:us"
]
| null | 2023-08-31T16:44:27Z | ---
license: llama2
language:
- en
---
<img src="https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg" style="width: 70%; min-width: 300px; display: block; margin: auto;">
<br>An experimental merging of Several Models using two various methods, [Ties-Merge](https://github.com/cg123/ties-merge) and [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient)
**GGUF FILES HERE**
<br>Included Quants: Q4_K_S, Q5_K_M, Q6_K
Stheno-1.2-L2-13B - Merged at Heavier Densities, Final Gradient Merge uses unique ratios.
Stheno-Inverted-1.2-L2-13B - Merged at Heavier Densities, Final Gradient Merge uses unique ratios. Inverted Model Positions
Stheno-1.3-L2-13B - Merged at Heavier Densities, Final Gradient Merge uses unique ratios + SLERP implementation thanks to @Vali
[Stheno-L2-13B](https://huggingface.co/Sao10K/Stheno-L2-13B)
<br>[Stheno-Inverted-L2-13B](https://huggingface.co/Sao10K/Stheno-Inverted-L2-13B)
<br>Stheno-P1-L2-13B --FP16 Private--
<br>Stheno-P2-L2-13B --FP16 Private--
*Refer to original cards for more info*
Most formats could work, but my tests have all been done in Alpaca format and it works well.
```
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
Once Again, thanks to [Chargoddard](https://huggingface.co/chargoddard) for his amazing and simple [ties-merge](https://github.com/cg123/ties-merge) script, and [Gryphe](https://huggingface.co/Gryphe) for their great [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient) script.
Thanks to the original model creators too!
```
Art by wada_kazu / わだかず (pixiv page private?)
``` |
infgrad/stella-large-zh | infgrad | 2024-04-06T02:48:23Z | 491 | 25 | transformers | [
"transformers",
"pytorch",
"bert",
"feature-extraction",
"mteb",
"arxiv:1612.00796",
"model-index",
"endpoints_compatible",
"region:us"
]
| feature-extraction | 2023-09-10T07:51:33Z | ---
tags:
- mteb
model-index:
- name: stella-large-zh
results:
- task:
type: STS
dataset:
type: C-MTEB/AFQMC
name: MTEB AFQMC
config: default
split: validation
revision: None
metrics:
- type: cos_sim_pearson
value: 51.61327712288466
- type: cos_sim_spearman
value: 54.48753880097122
- type: euclidean_pearson
value: 52.68387289931342
- type: euclidean_spearman
value: 54.48753879487172
- type: manhattan_pearson
value: 52.635406372350026
- type: manhattan_spearman
value: 54.447390526317044
- task:
type: STS
dataset:
type: C-MTEB/ATEC
name: MTEB ATEC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 53.39178036427897
- type: cos_sim_spearman
value: 54.450028472876134
- type: euclidean_pearson
value: 56.87300033777842
- type: euclidean_spearman
value: 54.45002622056799
- type: manhattan_pearson
value: 56.84326996138951
- type: manhattan_spearman
value: 54.433880144849375
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (zh)
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 40.574000000000005
- type: f1
value: 38.87775700245793
- task:
type: STS
dataset:
type: C-MTEB/BQ
name: MTEB BQ
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 60.80957921870066
- type: cos_sim_spearman
value: 62.37707350882237
- type: euclidean_pearson
value: 61.29032932843765
- type: euclidean_spearman
value: 62.37707350713817
- type: manhattan_pearson
value: 61.23028102541801
- type: manhattan_spearman
value: 62.31280056582247
- task:
type: Clustering
dataset:
type: C-MTEB/CLSClusteringP2P
name: MTEB CLSClusteringP2P
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 40.27066616318565
- task:
type: Clustering
dataset:
type: C-MTEB/CLSClusteringS2S
name: MTEB CLSClusteringS2S
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 37.503323644484716
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv1-reranking
name: MTEB CMedQAv1
config: default
split: test
revision: None
metrics:
- type: map
value: 84.69295191328456
- type: mrr
value: 87.08992063492063
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv2-reranking
name: MTEB CMedQAv2
config: default
split: test
revision: None
metrics:
- type: map
value: 85.22650690364465
- type: mrr
value: 87.72158730158729
- task:
type: Retrieval
dataset:
type: C-MTEB/CmedqaRetrieval
name: MTEB CmedqaRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 23.54
- type: map_at_10
value: 35.591
- type: map_at_100
value: 37.549
- type: map_at_1000
value: 37.663000000000004
- type: map_at_3
value: 31.405
- type: map_at_5
value: 33.792
- type: mrr_at_1
value: 36.359
- type: mrr_at_10
value: 44.624
- type: mrr_at_100
value: 45.660000000000004
- type: mrr_at_1000
value: 45.707
- type: mrr_at_3
value: 42.002
- type: mrr_at_5
value: 43.535000000000004
- type: ndcg_at_1
value: 36.359
- type: ndcg_at_10
value: 42.28
- type: ndcg_at_100
value: 49.997
- type: ndcg_at_1000
value: 51.966
- type: ndcg_at_3
value: 36.851
- type: ndcg_at_5
value: 39.249
- type: precision_at_1
value: 36.359
- type: precision_at_10
value: 9.542
- type: precision_at_100
value: 1.582
- type: precision_at_1000
value: 0.183
- type: precision_at_3
value: 20.913999999999998
- type: precision_at_5
value: 15.404000000000002
- type: recall_at_1
value: 23.54
- type: recall_at_10
value: 53.005
- type: recall_at_100
value: 85.085
- type: recall_at_1000
value: 98.21
- type: recall_at_3
value: 36.944
- type: recall_at_5
value: 44.137
- task:
type: PairClassification
dataset:
type: C-MTEB/CMNLI
name: MTEB Cmnli
config: default
split: validation
revision: None
metrics:
- type: cos_sim_accuracy
value: 76.16355983162958
- type: cos_sim_ap
value: 85.14228023901842
- type: cos_sim_f1
value: 77.86752827140549
- type: cos_sim_precision
value: 72.18450479233228
- type: cos_sim_recall
value: 84.5218611176058
- type: dot_accuracy
value: 76.16355983162958
- type: dot_ap
value: 85.16266644596179
- type: dot_f1
value: 77.86752827140549
- type: dot_precision
value: 72.18450479233228
- type: dot_recall
value: 84.5218611176058
- type: euclidean_accuracy
value: 76.16355983162958
- type: euclidean_ap
value: 85.14227717790371
- type: euclidean_f1
value: 77.86752827140549
- type: euclidean_precision
value: 72.18450479233228
- type: euclidean_recall
value: 84.5218611176058
- type: manhattan_accuracy
value: 75.99518941671678
- type: manhattan_ap
value: 85.10764940972825
- type: manhattan_f1
value: 77.80804694048618
- type: manhattan_precision
value: 70.49553825707233
- type: manhattan_recall
value: 86.81318681318682
- type: max_accuracy
value: 76.16355983162958
- type: max_ap
value: 85.16266644596179
- type: max_f1
value: 77.86752827140549
- task:
type: Retrieval
dataset:
type: C-MTEB/CovidRetrieval
name: MTEB CovidRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 73.762
- type: map_at_10
value: 81.76299999999999
- type: map_at_100
value: 81.974
- type: map_at_1000
value: 81.977
- type: map_at_3
value: 80.23400000000001
- type: map_at_5
value: 81.189
- type: mrr_at_1
value: 74.18299999999999
- type: mrr_at_10
value: 81.792
- type: mrr_at_100
value: 81.994
- type: mrr_at_1000
value: 81.997
- type: mrr_at_3
value: 80.277
- type: mrr_at_5
value: 81.221
- type: ndcg_at_1
value: 74.078
- type: ndcg_at_10
value: 85.195
- type: ndcg_at_100
value: 86.041
- type: ndcg_at_1000
value: 86.111
- type: ndcg_at_3
value: 82.171
- type: ndcg_at_5
value: 83.90100000000001
- type: precision_at_1
value: 74.078
- type: precision_at_10
value: 9.684
- type: precision_at_100
value: 1.004
- type: precision_at_1000
value: 0.101
- type: precision_at_3
value: 29.470000000000002
- type: precision_at_5
value: 18.567
- type: recall_at_1
value: 73.762
- type: recall_at_10
value: 95.785
- type: recall_at_100
value: 99.368
- type: recall_at_1000
value: 99.895
- type: recall_at_3
value: 87.724
- type: recall_at_5
value: 91.93900000000001
- task:
type: Retrieval
dataset:
type: C-MTEB/DuRetrieval
name: MTEB DuRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 25.911
- type: map_at_10
value: 80.656
- type: map_at_100
value: 83.446
- type: map_at_1000
value: 83.485
- type: map_at_3
value: 55.998000000000005
- type: map_at_5
value: 70.577
- type: mrr_at_1
value: 90.14999999999999
- type: mrr_at_10
value: 93.35900000000001
- type: mrr_at_100
value: 93.419
- type: mrr_at_1000
value: 93.423
- type: mrr_at_3
value: 93.133
- type: mrr_at_5
value: 93.26100000000001
- type: ndcg_at_1
value: 90.14999999999999
- type: ndcg_at_10
value: 87.806
- type: ndcg_at_100
value: 90.4
- type: ndcg_at_1000
value: 90.776
- type: ndcg_at_3
value: 86.866
- type: ndcg_at_5
value: 85.619
- type: precision_at_1
value: 90.14999999999999
- type: precision_at_10
value: 42.045
- type: precision_at_100
value: 4.814
- type: precision_at_1000
value: 0.49
- type: precision_at_3
value: 78.0
- type: precision_at_5
value: 65.62
- type: recall_at_1
value: 25.911
- type: recall_at_10
value: 88.942
- type: recall_at_100
value: 97.56700000000001
- type: recall_at_1000
value: 99.62
- type: recall_at_3
value: 58.361
- type: recall_at_5
value: 75.126
- task:
type: Retrieval
dataset:
type: C-MTEB/EcomRetrieval
name: MTEB EcomRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 46.2
- type: map_at_10
value: 56.309
- type: map_at_100
value: 56.977
- type: map_at_1000
value: 56.995
- type: map_at_3
value: 53.55
- type: map_at_5
value: 55.19
- type: mrr_at_1
value: 46.2
- type: mrr_at_10
value: 56.309
- type: mrr_at_100
value: 56.977
- type: mrr_at_1000
value: 56.995
- type: mrr_at_3
value: 53.55
- type: mrr_at_5
value: 55.19
- type: ndcg_at_1
value: 46.2
- type: ndcg_at_10
value: 61.656
- type: ndcg_at_100
value: 64.714
- type: ndcg_at_1000
value: 65.217
- type: ndcg_at_3
value: 56.022000000000006
- type: ndcg_at_5
value: 58.962
- type: precision_at_1
value: 46.2
- type: precision_at_10
value: 7.86
- type: precision_at_100
value: 0.9249999999999999
- type: precision_at_1000
value: 0.097
- type: precision_at_3
value: 21.067
- type: precision_at_5
value: 14.06
- type: recall_at_1
value: 46.2
- type: recall_at_10
value: 78.60000000000001
- type: recall_at_100
value: 92.5
- type: recall_at_1000
value: 96.5
- type: recall_at_3
value: 63.2
- type: recall_at_5
value: 70.3
- task:
type: Classification
dataset:
type: C-MTEB/IFlyTek-classification
name: MTEB IFlyTek
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 47.03347441323585
- type: f1
value: 35.50895794566714
- task:
type: Classification
dataset:
type: C-MTEB/JDReview-classification
name: MTEB JDReview
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 86.73545966228893
- type: ap
value: 55.43694740493539
- type: f1
value: 81.47218440859787
- task:
type: STS
dataset:
type: C-MTEB/LCQMC
name: MTEB LCQMC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 70.49478085579923
- type: cos_sim_spearman
value: 76.28442852235379
- type: euclidean_pearson
value: 74.90910715249527
- type: euclidean_spearman
value: 76.28443517178847
- type: manhattan_pearson
value: 74.90744903779758
- type: manhattan_spearman
value: 76.2886829916495
- task:
type: Retrieval
dataset:
type: C-MTEB/MMarcoRetrieval
name: MTEB MMarcoRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 64.798
- type: map_at_10
value: 74.263
- type: map_at_100
value: 74.59
- type: map_at_1000
value: 74.601
- type: map_at_3
value: 72.382
- type: map_at_5
value: 73.59700000000001
- type: mrr_at_1
value: 67.049
- type: mrr_at_10
value: 74.86500000000001
- type: mrr_at_100
value: 75.155
- type: mrr_at_1000
value: 75.165
- type: mrr_at_3
value: 73.21600000000001
- type: mrr_at_5
value: 74.259
- type: ndcg_at_1
value: 67.049
- type: ndcg_at_10
value: 78.104
- type: ndcg_at_100
value: 79.56400000000001
- type: ndcg_at_1000
value: 79.85600000000001
- type: ndcg_at_3
value: 74.54499999999999
- type: ndcg_at_5
value: 76.587
- type: precision_at_1
value: 67.049
- type: precision_at_10
value: 9.493
- type: precision_at_100
value: 1.022
- type: precision_at_1000
value: 0.105
- type: precision_at_3
value: 28.189999999999998
- type: precision_at_5
value: 18.003
- type: recall_at_1
value: 64.798
- type: recall_at_10
value: 89.328
- type: recall_at_100
value: 95.916
- type: recall_at_1000
value: 98.223
- type: recall_at_3
value: 79.93599999999999
- type: recall_at_5
value: 84.789
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-CN)
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.01815736381977
- type: f1
value: 61.07806329750582
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-CN)
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.94754539340954
- type: f1
value: 68.76446930296682
- task:
type: Retrieval
dataset:
type: C-MTEB/MedicalRetrieval
name: MTEB MedicalRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 50.1
- type: map_at_10
value: 56.406
- type: map_at_100
value: 56.958
- type: map_at_1000
value: 57.007
- type: map_at_3
value: 55.083000000000006
- type: map_at_5
value: 55.952999999999996
- type: mrr_at_1
value: 50.1
- type: mrr_at_10
value: 56.401999999999994
- type: mrr_at_100
value: 56.955
- type: mrr_at_1000
value: 57.004
- type: mrr_at_3
value: 55.05
- type: mrr_at_5
value: 55.95
- type: ndcg_at_1
value: 50.1
- type: ndcg_at_10
value: 59.384
- type: ndcg_at_100
value: 62.339
- type: ndcg_at_1000
value: 63.756
- type: ndcg_at_3
value: 56.657999999999994
- type: ndcg_at_5
value: 58.267
- type: precision_at_1
value: 50.1
- type: precision_at_10
value: 6.87
- type: precision_at_100
value: 0.832
- type: precision_at_1000
value: 0.095
- type: precision_at_3
value: 20.4
- type: precision_at_5
value: 13.04
- type: recall_at_1
value: 50.1
- type: recall_at_10
value: 68.7
- type: recall_at_100
value: 83.2
- type: recall_at_1000
value: 94.6
- type: recall_at_3
value: 61.199999999999996
- type: recall_at_5
value: 65.2
- task:
type: Reranking
dataset:
type: C-MTEB/Mmarco-reranking
name: MTEB MMarcoReranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 27.159122893681587
- type: mrr
value: 25.659126984126985
- task:
type: Classification
dataset:
type: C-MTEB/MultilingualSentiment-classification
name: MTEB MultilingualSentiment
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 73.02666666666667
- type: f1
value: 72.47691397067602
- task:
type: PairClassification
dataset:
type: C-MTEB/OCNLI
name: MTEB Ocnli
config: default
split: validation
revision: None
metrics:
- type: cos_sim_accuracy
value: 67.0817541959935
- type: cos_sim_ap
value: 72.29133043915637
- type: cos_sim_f1
value: 72.71207689093188
- type: cos_sim_precision
value: 60.16597510373444
- type: cos_sim_recall
value: 91.86906019007391
- type: dot_accuracy
value: 67.0817541959935
- type: dot_ap
value: 72.29133043915637
- type: dot_f1
value: 72.71207689093188
- type: dot_precision
value: 60.16597510373444
- type: dot_recall
value: 91.86906019007391
- type: euclidean_accuracy
value: 67.0817541959935
- type: euclidean_ap
value: 72.29133043915637
- type: euclidean_f1
value: 72.71207689093188
- type: euclidean_precision
value: 60.16597510373444
- type: euclidean_recall
value: 91.86906019007391
- type: manhattan_accuracy
value: 66.91932864103953
- type: manhattan_ap
value: 72.20070509521395
- type: manhattan_f1
value: 72.52839713925118
- type: manhattan_precision
value: 60.27972027972028
- type: manhattan_recall
value: 91.02428722280888
- type: max_accuracy
value: 67.0817541959935
- type: max_ap
value: 72.29133043915637
- type: max_f1
value: 72.71207689093188
- task:
type: Classification
dataset:
type: C-MTEB/OnlineShopping-classification
name: MTEB OnlineShopping
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 90.75000000000001
- type: ap
value: 87.99706544930007
- type: f1
value: 90.72973221476978
- task:
type: STS
dataset:
type: C-MTEB/PAWSX
name: MTEB PAWSX
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 33.57372874898899
- type: cos_sim_spearman
value: 37.9718472605281
- type: euclidean_pearson
value: 38.52264008741102
- type: euclidean_spearman
value: 37.97184654854654
- type: manhattan_pearson
value: 38.50412571398273
- type: manhattan_spearman
value: 37.98038173979437
- task:
type: STS
dataset:
type: C-MTEB/QBQTC
name: MTEB QBQTC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 37.510457667606225
- type: cos_sim_spearman
value: 37.83522430820119
- type: euclidean_pearson
value: 36.65815519443564
- type: euclidean_spearman
value: 37.83519816393499
- type: manhattan_pearson
value: 36.66835898210608
- type: manhattan_spearman
value: 37.85390202705368
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 66.9953337569138
- type: cos_sim_spearman
value: 67.27632129468024
- type: euclidean_pearson
value: 65.83716645437758
- type: euclidean_spearman
value: 67.27632129468024
- type: manhattan_pearson
value: 65.81209103940279
- type: manhattan_spearman
value: 67.26678679870099
- task:
type: STS
dataset:
type: C-MTEB/STSB
name: MTEB STSB
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 75.73719311549382
- type: cos_sim_spearman
value: 75.71173848950517
- type: euclidean_pearson
value: 75.23070020894484
- type: euclidean_spearman
value: 75.71173839940812
- type: manhattan_pearson
value: 75.23517292603057
- type: manhattan_spearman
value: 75.74250916645184
- task:
type: Reranking
dataset:
type: C-MTEB/T2Reranking
name: MTEB T2Reranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 66.8596523608508
- type: mrr
value: 76.9288884590171
- task:
type: Retrieval
dataset:
type: C-MTEB/T2Retrieval
name: MTEB T2Retrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 26.618000000000002
- type: map_at_10
value: 74.884
- type: map_at_100
value: 78.65299999999999
- type: map_at_1000
value: 78.724
- type: map_at_3
value: 52.507999999999996
- type: map_at_5
value: 64.52799999999999
- type: mrr_at_1
value: 88.453
- type: mrr_at_10
value: 91.157
- type: mrr_at_100
value: 91.263
- type: mrr_at_1000
value: 91.268
- type: mrr_at_3
value: 90.672
- type: mrr_at_5
value: 90.96499999999999
- type: ndcg_at_1
value: 88.453
- type: ndcg_at_10
value: 82.759
- type: ndcg_at_100
value: 86.709
- type: ndcg_at_1000
value: 87.41499999999999
- type: ndcg_at_3
value: 84.194
- type: ndcg_at_5
value: 82.645
- type: precision_at_1
value: 88.453
- type: precision_at_10
value: 41.369
- type: precision_at_100
value: 4.9910000000000005
- type: precision_at_1000
value: 0.515
- type: precision_at_3
value: 73.79400000000001
- type: precision_at_5
value: 61.80799999999999
- type: recall_at_1
value: 26.618000000000002
- type: recall_at_10
value: 81.772
- type: recall_at_100
value: 94.55
- type: recall_at_1000
value: 98.184
- type: recall_at_3
value: 54.26499999999999
- type: recall_at_5
value: 67.963
- task:
type: Classification
dataset:
type: C-MTEB/TNews-classification
name: MTEB TNews
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 50.690000000000005
- type: f1
value: 48.77079213417325
- task:
type: Clustering
dataset:
type: C-MTEB/ThuNewsClusteringP2P
name: MTEB ThuNewsClusteringP2P
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 62.14566804144758
- task:
type: Clustering
dataset:
type: C-MTEB/ThuNewsClusteringS2S
name: MTEB ThuNewsClusteringS2S
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 54.66890415410679
- task:
type: Retrieval
dataset:
type: C-MTEB/VideoRetrieval
name: MTEB VideoRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 55.900000000000006
- type: map_at_10
value: 66.188
- type: map_at_100
value: 66.67699999999999
- type: map_at_1000
value: 66.691
- type: map_at_3
value: 64.017
- type: map_at_5
value: 65.462
- type: mrr_at_1
value: 55.800000000000004
- type: mrr_at_10
value: 66.13799999999999
- type: mrr_at_100
value: 66.62700000000001
- type: mrr_at_1000
value: 66.64099999999999
- type: mrr_at_3
value: 63.967
- type: mrr_at_5
value: 65.412
- type: ndcg_at_1
value: 55.900000000000006
- type: ndcg_at_10
value: 70.961
- type: ndcg_at_100
value: 73.22
- type: ndcg_at_1000
value: 73.583
- type: ndcg_at_3
value: 66.61
- type: ndcg_at_5
value: 69.18900000000001
- type: precision_at_1
value: 55.900000000000006
- type: precision_at_10
value: 8.58
- type: precision_at_100
value: 0.9610000000000001
- type: precision_at_1000
value: 0.099
- type: precision_at_3
value: 24.7
- type: precision_at_5
value: 16.06
- type: recall_at_1
value: 55.900000000000006
- type: recall_at_10
value: 85.8
- type: recall_at_100
value: 96.1
- type: recall_at_1000
value: 98.9
- type: recall_at_3
value: 74.1
- type: recall_at_5
value: 80.30000000000001
- task:
type: Classification
dataset:
type: C-MTEB/waimai-classification
name: MTEB Waimai
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 86.77
- type: ap
value: 70.21134107638184
- type: f1
value: 85.22521777795022
---
**新闻 | News**
**[2024-04-06]** 开源[puff](https://huggingface.co/infgrad/puff-base-v1)系列模型，**专门针对检索和语义匹配任务，更多的考虑泛化性和私有通用测试集效果，向量维度可变，中英双语**。
**[2024-02-27]** 开源stella-mrl-large-zh-v3.5-1792d模型，支持**向量可变维度**。
**[2024-02-17]** 开源stella v3系列、dialogue编码模型和相关训练数据。
**[2023-10-19]** 开源stella-base-en-v2 使用简单，**不需要任何前缀文本**。
**[2023-10-12]** 开源stella-base-zh-v2和stella-large-zh-v2, 效果更好且使用简单，**不需要任何前缀文本**。
**[2023-09-11]** 开源stella-base-zh和stella-large-zh
欢迎去[本人主页](https://huggingface.co/infgrad)查看最新模型，并提出您的宝贵意见！
## stella model
stella是一个通用的文本编码模型，主要有以下模型：
| Model Name | Model Size (GB) | Dimension | Sequence Length | Language | Need instruction for retrieval? |
|:------------------:|:---------------:|:---------:|:---------------:|:--------:|:-------------------------------:|
| stella-base-en-v2 | 0.2 | 768 | 512 | English | No |
| stella-large-zh-v2 | 0.65 | 1024 | 1024 | Chinese | No |
| stella-base-zh-v2 | 0.2 | 768 | 1024 | Chinese | No |
| stella-large-zh | 0.65 | 1024 | 1024 | Chinese | Yes |
| stella-base-zh | 0.2 | 768 | 1024 | Chinese | Yes |
完整的训练思路和训练过程已记录在[博客1](https://zhuanlan.zhihu.com/p/655322183)和[博客2](https://zhuanlan.zhihu.com/p/662209559)，欢迎阅读讨论。
**训练数据：**
1. 开源数据(wudao_base_200GB[1]、m3e[2]和simclue[3])，着重挑选了长度大于512的文本
2. 在通用语料库上使用LLM构造一批(question, paragraph)和(sentence, paragraph)数据
**训练方法：**
1. 对比学习损失函数
2. 带有难负例的对比学习损失函数(分别基于bm25和vector构造了难负例)
3. EWC(Elastic Weights Consolidation)[4]
4. cosent loss[5]
5. 每一种类型的数据一个迭代器，分别计算loss进行更新
stella-v2在stella模型的基础上，使用了更多的训练数据，同时知识蒸馏等方法去除了前置的instruction(
比如piccolo的`查询:`, `结果:`, e5的`query:`和`passage:`)。
**初始权重：**\
stella-base-zh和stella-large-zh分别以piccolo-base-zh[6]和piccolo-large-zh作为基础模型，512-1024的position
embedding使用层次分解位置编码[7]进行初始化。\
感谢商汤科技研究院开源的[piccolo系列模型](https://huggingface.co/sensenova)。
stella is a general-purpose text encoder, which mainly includes the following models:
| Model Name | Model Size (GB) | Dimension | Sequence Length | Language | Need instruction for retrieval? |
|:------------------:|:---------------:|:---------:|:---------------:|:--------:|:-------------------------------:|
| stella-base-en-v2 | 0.2 | 768 | 512 | English | No |
| stella-large-zh-v2 | 0.65 | 1024 | 1024 | Chinese | No |
| stella-base-zh-v2 | 0.2 | 768 | 1024 | Chinese | No |
| stella-large-zh | 0.65 | 1024 | 1024 | Chinese | Yes |
| stella-base-zh | 0.2 | 768 | 1024 | Chinese | Yes |
The training data mainly includes:
1. Open-source training data (wudao_base_200GB, m3e, and simclue), with a focus on selecting texts with lengths greater
than 512.
2. A batch of (question, paragraph) and (sentence, paragraph) data constructed on a general corpus using LLM.
The loss functions mainly include:
1. Contrastive learning loss function
2. Contrastive learning loss function with hard negative examples (based on bm25 and vector hard negatives)
3. EWC (Elastic Weights Consolidation)
4. cosent loss
Model weight initialization:\
stella-base-zh and stella-large-zh use piccolo-base-zh and piccolo-large-zh as the base models, respectively, and the
512-1024 position embedding uses the initialization strategy of hierarchical decomposed position encoding.
Training strategy:\
One iterator for each type of data, separately calculating the loss.
Based on stella models, stella-v2 use more training data and remove instruction by Knowledge Distillation.
## Metric
#### C-MTEB leaderboard (Chinese)
| Model Name | Model Size (GB) | Dimension | Sequence Length | Average (35) | Classification (9) | Clustering (4) | Pair Classification (2) | Reranking (4) | Retrieval (8) | STS (8) |
|:------------------:|:---------------:|:---------:|:---------------:|:------------:|:------------------:|:--------------:|:-----------------------:|:-------------:|:-------------:|:-------:|
| stella-large-zh-v2 | 0.65 | 1024 | 1024 | 65.13 | 69.05 | 49.16 | 82.68 | 66.41 | 70.14 | 58.66 |
| stella-base-zh-v2 | 0.2 | 768 | 1024 | 64.36 | 68.29 | 49.4 | 79.95 | 66.1 | 70.08 | 56.92 |
| stella-large-zh | 0.65 | 1024 | 1024 | 64.54 | 67.62 | 48.65 | 78.72 | 65.98 | 71.02 | 58.3 |
| stella-base-zh | 0.2 | 768 | 1024 | 64.16 | 67.77 | 48.7 | 76.09 | 66.95 | 71.07 | 56.54 |
#### MTEB leaderboard (English)
| Model Name | Model Size (GB) | Dimension | Sequence Length | Average (56) | Classification (12) | Clustering (11) | Pair Classification (3) | Reranking (4) | Retrieval (15) | STS (10) | Summarization (1) |
|:-----------------:|:---------------:|:---------:|:---------------:|:------------:|:-------------------:|:---------------:|:-----------------------:|:-------------:|:--------------:|:--------:|:------------------:|
| stella-base-en-v2 | 0.2 | 768 | 512 | 62.61 | 75.28 | 44.9 | 86.45 | 58.77 | 50.1 | 83.02 | 32.52 |
#### Reproduce our results
**C-MTEB:**
```python
import torch
import numpy as np
from typing import List
from mteb import MTEB
from sentence_transformers import SentenceTransformer
class FastTextEncoder():
def __init__(self, model_name):
self.model = SentenceTransformer(model_name).cuda().half().eval()
self.model.max_seq_length = 512
def encode(
self,
input_texts: List[str],
*args,
**kwargs
):
new_sens = list(set(input_texts))
new_sens.sort(key=lambda x: len(x), reverse=True)
vecs = self.model.encode(
new_sens, normalize_embeddings=True, convert_to_numpy=True, batch_size=256
).astype(np.float32)
sen2arrid = {sen: idx for idx, sen in enumerate(new_sens)}
vecs = vecs[[sen2arrid[sen] for sen in input_texts]]
torch.cuda.empty_cache()
return vecs
if __name__ == '__main__':
model_name = "infgrad/stella-base-zh-v2"
output_folder = "zh_mteb_results/stella-base-zh-v2"
task_names = [t.description["name"] for t in MTEB(task_langs=['zh', 'zh-CN']).tasks]
model = FastTextEncoder(model_name)
for task in task_names:
MTEB(tasks=[task], task_langs=['zh', 'zh-CN']).run(model, output_folder=output_folder)
```
**MTEB:**
You can use official script to reproduce our result. [scripts/run_mteb_english.py](https://github.com/embeddings-benchmark/mteb/blob/main/scripts/run_mteb_english.py)
#### Evaluation for long text
经过实际观察发现，C-MTEB的评测数据长度基本都是小于512的，
更致命的是那些长度大于512的文本，其重点都在前半部分
这里以CMRC2018的数据为例说明这个问题：
```
question: 《无双大蛇z》是谁旗下ω-force开发的动作游戏？
passage：《无双大蛇z》是光荣旗下ω-force开发的动作游戏，于2009年3月12日登陆索尼playstation3，并于2009年11月27日推......
```
passage长度为800多，大于512，但是对于这个question而言只需要前面40个字就足以检索，多的内容对于模型而言是一种噪声，反而降低了效果。\
简言之，现有数据集的2个问题：\
1）长度大于512的过少\
2）即便大于512，对于检索而言也只需要前512的文本内容\
导致**无法准确评估模型的长文本编码能力。**
为了解决这个问题，搜集了相关开源数据并使用规则进行过滤，最终整理了6份长文本测试集,他们分别是：
- CMRC2018，通用百科
- CAIL，法律阅读理解
- DRCD，繁体百科，已转简体
- Military，军工问答
- Squad，英文阅读理解，已转中文
- Multifieldqa_zh，清华的大模型长文本理解能力评测数据[9]
处理规则是选取答案在512长度之后的文本，短的测试数据会欠采样一下，长短文本占比约为1:2，所以模型既得理解短文本也得理解长文本。
除了Military数据集，我们提供了其他5个测试数据的下载地址：https://drive.google.com/file/d/1WC6EWaCbVgz-vPMDFH4TwAMkLyh5WNcN/view?usp=sharing
评测指标为Recall@5, 结果如下：
| Dataset | piccolo-base-zh | piccolo-large-zh | bge-base-zh | bge-large-zh | stella-base-zh | stella-large-zh |
|:---------------:|:---------------:|:----------------:|:-----------:|:------------:|:--------------:|:---------------:|
| CMRC2018 | 94.34 | 93.82 | 91.56 | 93.12 | 96.08 | 95.56 |
| CAIL | 28.04 | 33.64 | 31.22 | 33.94 | 34.62 | 37.18 |
| DRCD | 78.25 | 77.9 | 78.34 | 80.26 | 86.14 | 84.58 |
| Military | 76.61 | 73.06 | 75.65 | 75.81 | 83.71 | 80.48 |
| Squad | 91.21 | 86.61 | 87.87 | 90.38 | 93.31 | 91.21 |
| Multifieldqa_zh | 81.41 | 83.92 | 83.92 | 83.42 | 79.9 | 80.4 |
| **Average** | 74.98 | 74.83 | 74.76 | 76.15 | **78.96** | **78.24** |
**注意：** 因为长文本评测数据数量稀少，所以构造时也使用了train部分，如果自行评测，请注意模型的训练数据以免数据泄露。
## Usage
#### stella 中文系列模型
stella-base-zh 和 stella-large-zh: 本模型是在piccolo基础上训练的，因此**用法和piccolo完全一致**
，即在检索重排任务上给query和passage加上`查询: `和`结果: `。对于短短匹配不需要做任何操作。
stella-base-zh-v2 和 stella-large-zh-v2: 本模型使用简单，**任何使用场景中都不需要加前缀文本**。
stella中文系列模型均使用mean pooling做为文本向量。
在sentence-transformer库中的使用方法：
```python
from sentence_transformers import SentenceTransformer
sentences = ["数据1", "数据2"]
model = SentenceTransformer('infgrad/stella-base-zh-v2')
print(model.max_seq_length)
embeddings_1 = model.encode(sentences, normalize_embeddings=True)
embeddings_2 = model.encode(sentences, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
```
直接使用transformers库：
```python
from transformers import AutoModel, AutoTokenizer
from sklearn.preprocessing import normalize
model = AutoModel.from_pretrained('infgrad/stella-base-zh-v2')
tokenizer = AutoTokenizer.from_pretrained('infgrad/stella-base-zh-v2')
sentences = ["数据1", "数据ABCDEFGH"]
batch_data = tokenizer(
batch_text_or_text_pairs=sentences,
padding="longest",
return_tensors="pt",
max_length=1024,
truncation=True,
)
attention_mask = batch_data["attention_mask"]
model_output = model(**batch_data)
last_hidden = model_output.last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
vectors = normalize(vectors, norm="l2", axis=1, )
print(vectors.shape) # 2,768
```
#### stella models for English
**Using Sentence-Transformers:**
```python
from sentence_transformers import SentenceTransformer
sentences = ["one car come", "one car go"]
model = SentenceTransformer('infgrad/stella-base-en-v2')
print(model.max_seq_length)
embeddings_1 = model.encode(sentences, normalize_embeddings=True)
embeddings_2 = model.encode(sentences, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
```
**Using HuggingFace Transformers:**
```python
from transformers import AutoModel, AutoTokenizer
from sklearn.preprocessing import normalize
model = AutoModel.from_pretrained('infgrad/stella-base-en-v2')
tokenizer = AutoTokenizer.from_pretrained('infgrad/stella-base-en-v2')
sentences = ["one car come", "one car go"]
batch_data = tokenizer(
batch_text_or_text_pairs=sentences,
padding="longest",
return_tensors="pt",
max_length=512,
truncation=True,
)
attention_mask = batch_data["attention_mask"]
model_output = model(**batch_data)
last_hidden = model_output.last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
vectors = normalize(vectors, norm="l2", axis=1, )
print(vectors.shape) # 2,768
```
## Training Detail
**硬件：** 单卡A100-80GB
**环境：** torch1.13.*; transformers-trainer + deepspeed + gradient-checkpointing
**学习率：** 1e-6
**batch_size：** base模型为1024，额外增加20%的难负例；large模型为768，额外增加20%的难负例
**数据量：** 第一版模型约100万，其中用LLM构造的数据约有200K. LLM模型大小为13b。v2系列模型到了2000万训练数据。
## ToDoList
**评测的稳定性：**
评测过程中发现Clustering任务会和官方的结果不一致，大约有±0.0x的小差距，原因是聚类代码没有设置random_seed，差距可以忽略不计，不影响评测结论。
**更高质量的长文本训练和测试数据：** 训练数据多是用13b模型构造的，肯定会存在噪声。
测试数据基本都是从mrc数据整理来的，所以问题都是factoid类型，不符合真实分布。
**OOD的性能：** 虽然近期出现了很多向量编码模型，但是对于不是那么通用的domain，这一众模型包括stella、openai和cohere,
它们的效果均比不上BM25。
## Reference
1. https://www.scidb.cn/en/detail?dataSetId=c6a3fe684227415a9db8e21bac4a15ab
2. https://github.com/wangyuxinwhy/uniem
3. https://github.com/CLUEbenchmark/SimCLUE
4. https://arxiv.org/abs/1612.00796
5. https://kexue.fm/archives/8847
6. https://huggingface.co/sensenova/piccolo-base-zh
7. https://kexue.fm/archives/7947
8. https://github.com/FlagOpen/FlagEmbedding
9. https://github.com/THUDM/LongBench
|
maddes8cht/georgesung-open_llama_7b_qlora_uncensored-gguf | maddes8cht | 2023-11-25T17:57:51Z | 491 | 1 | null | [
"gguf",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-25T11:17:35Z | ---
license: apache-2.0
datasets:
- ehartford/wizard_vicuna_70k_unfiltered
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# open_llama_7b_qlora_uncensored - GGUF
- Model creator: [georgesung](https://huggingface.co/georgesung)
- Original model: [open_llama_7b_qlora_uncensored](https://huggingface.co/georgesung/open_llama_7b_qlora_uncensored)
OpenLlama is a free reimplementation of the original Llama Model which is licensed under Apache 2 license.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
# Overview
Fine-tuned [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b) with an uncensored/unfiltered Wizard-Vicuna conversation dataset [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered).
Used QLoRA for fine-tuning. Trained for one epoch on a 24GB GPU (NVIDIA A10G) instance, took ~18 hours to train.
# Prompt style
The model was trained with the following prompt style:
```
### HUMAN:
Hello
### RESPONSE:
Hi, how are you?
### HUMAN:
I'm fine.
### RESPONSE:
How can I help you?
...
```
# Training code
Code used to train the model is available [here](https://github.com/georgesung/llm_qlora).
# Demo
For a Gradio chat application using this model, clone [this HuggingFace Space](https://huggingface.co/spaces/georgesung/open_llama_7b_qlora_uncensored_chat/tree/main) and run it on top of a GPU instance.
The basic T4 GPU instance will work.
# Blog post
Since this was my first time fine-tuning an LLM, I also wrote an accompanying blog post about how I performed the training :)
https://georgesung.github.io/ai/qlora-ift/
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
<center>
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)
</center> |
TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF | TheBloke | 2023-12-04T09:55:31Z | 491 | 24 | transformers | [
"transformers",
"gguf",
"mistral",
"dataset:Open-Orca/SlimOrca",
"base_model:Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B",
"license:apache-2.0",
"text-generation-inference",
"region:us"
]
| null | 2023-12-03T18:27:10Z | ---
base_model: Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
datasets:
- Open-Orca/SlimOrca
inference: false
license: apache-2.0
model_creator: "Ya\u011F\u0131z \xC7al\u0131k"
model_name: OpenHermes 2.5 Neural Chat 7B V3-2 7B
model_type: mistral
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
tags:
- mistral
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# OpenHermes 2.5 Neural Chat 7B V3-2 7B - GGUF
- Model creator: [Yağız Çalık](https://huggingface.co/Weyaxi)
- Original model: [OpenHermes 2.5 Neural Chat 7B V3-2 7B](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Yağız Çalık's OpenHermes 2.5 Neural Chat 7B V3-2 7B](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF)
* [Yağız Çalık's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q2_K.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.17 GB| 5.67 GB | very small, high quality loss |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q5_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q6_K.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [openhermes-2.5-neural-chat-7b-v3-2-7b.Q8_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF/blob/main/openhermes-2.5-neural-chat-7b-v3-2-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF and below it, a specific filename to download, such as: openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./openhermes-2.5-neural-chat-7b-v3-2-7b.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Yağız Çalık's OpenHermes 2.5 Neural Chat 7B V3-2 7B
### *Weights*
- [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B): 0.5
- [Intel/neural-chat-7b-v3-2](https://huggingface.co/Intel/neural-chat-7b-v3-2): 0.3
### *Density*
- [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B): 0.5
- [Intel/neural-chat-7b-v3-2](https://huggingface.co/Intel/neural-chat-7b-v3-2): 0.5
# Prompt Templates
You can use these prompt templates, but I recommend using ChatML.
### ChatML [(OpenHermes-2.5-Mistral-7B)](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B):
```
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>
```
### [neural-chat-7b-v3-2](https://huggingface.co/Intel/neural-chat-7b-v3-2):
```
### System:
{system}
### User:
{usr}
### Assistant:
```
<!-- original-model-card end -->
|
FremyCompany/BioLORD-2023-S | FremyCompany | 2024-02-28T13:51:33Z | 491 | 2 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"medical",
"biology",
"en",
"dataset:FremyCompany/BioLORD-Dataset",
"dataset:FremyCompany/AGCT-Dataset",
"arxiv:2311.16075",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| sentence-similarity | 2024-02-12T19:00:33Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- medical
- biology
language: en
license: other
license_name: ihtsdo-and-nlm-licences
license_link: https://www.nlm.nih.gov/databases/umls.html
datasets:
- FremyCompany/BioLORD-Dataset
- FremyCompany/AGCT-Dataset
widget:
- source_sentence: bartonellosis
sentences:
- cat scratch disease
- cat scratch wound
- tick-borne orbivirus fever
- cat fur
---
# FremyCompany/BioLORD-2023-S
This model was trained using BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts.
State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations.
BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD-2023 establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (EHR-Rel-B).
This model is based on [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) and was further finetuned on the [BioLORD-Dataset](https://huggingface.co/datasets/FremyCompany/BioLORD-Dataset) and LLM-generated definitions from the [Automatic Glossary of Clinical Terminology (AGCT)](https://huggingface.co/datasets/FremyCompany/AGCT-Dataset).
## Sibling models
This model is accompanied by other models in the BioLORD-2023 series, which you might want to check:
- [BioLORD-2023-M](https://huggingface.co/FremyCompany/BioLORD-2023-M) (multilingual model; distilled from BioLORD-2023)
- [BioLORD-2023](https://huggingface.co/FremyCompany/BioLORD-2023) (best model after model averaging)
- [BioLORD-2023-S](https://huggingface.co/FremyCompany/BioLORD-2023-S) (best hyperparameters; no model averaging; this model)
- [BioLORD-2023-C](https://huggingface.co/FremyCompany/BioLORD-2023-C) (contrastive training only; for NEL tasks)
You can also take a look at last year's model and paper:
- [BioLORD-2022](https://huggingface.co/FremyCompany/BioLORD-STAMB2-v1) (also known as BioLORD-STAMB2-v1)
## Training strategy
### Summary of the 3 phases
### Contrastive phase: details
### Self-distallation phase: details
## Citation
This model accompanies the [BioLORD-2023: Learning Ontological Representations from Definitions](https://arxiv.org/abs/2311.16075) paper. When you use this model, please cite the original paper as follows:
```latex
@article{remy-etal-2023-biolord,
author = {Remy, François and Demuynck, Kris and Demeester, Thomas},
title = "{BioLORD-2023: semantic textual representations fusing large language models and clinical knowledge graph insights}",
journal = {Journal of the American Medical Informatics Association},
pages = {ocae029},
year = {2024},
month = {02},
issn = {1527-974X},
doi = {10.1093/jamia/ocae029},
url = {https://doi.org/10.1093/jamia/ocae029},
eprint = {https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocae029/56772025/ocae029.pdf},
}
```
## Usage (Sentence-Transformers)
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. This model has been finentuned for the biomedical domain. While it preserves a good ability to produce embeddings for general-purpose text, it will be more useful to you if you are trying to process medical documents such as EHR records or clinical notes. Both sentences and phrases can be embedded in the same latent space.
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["Cat scratch injury", "Cat scratch disease", "Bartonellosis"]
model = SentenceTransformer('FremyCompany/BioLORD-2023-S')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ["Cat scratch injury", "Cat scratch disease", "Bartonellosis"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('FremyCompany/BioLORD-2023-S')
model = AutoModel.from_pretrained('FremyCompany/BioLORD-2023-S')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
## License
My own contributions for this model are covered by the MIT license.
However, given the data used to train this model originates from UMLS and SnomedCT, you will need to ensure you have proper licensing of UMLS and SnomedCT before using this model. Both UMLS and SnomedCT are free of charge in most countries, but you might have to create an account and report on your usage of the data yearly to keep a valid license. |
TheBlock/Mistral-7B-Instruct-v0.2-GGUF | TheBlock | 2024-02-15T18:52:32Z | 491 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"finetuned",
"text-generation",
"arxiv:2310.06825",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-02-15T18:42:09Z | ---
base_model: mistralai/Mistral-7B-Instruct-v0.2
inference: false
license: apache-2.0
model_creator: Mistral AI_
model_name: Mistral 7B Instruct v0.2
model_type: mistral
pipeline_tag: text-generation
prompt_template: '<s>[INST] {prompt} [/INST]
'
quantized_by: TheBlock
tags:
- finetuned
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ce54005f233e28db1f48a9/FCPpgCFyrsQE8EsROXDmS.jpeg" alt="TheBlockAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/TheBlockai">Chat & support: TheBlock's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlockAI">Want to contribute? TheBlock's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBlock's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Mistral 7B Instruct v0.2 - GGUF
- Model creator: [Mistral AI_](https://huggingface.co/mistralai)
- Original model: [Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Mistral AI_'s Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF)
* [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Mistral
```
<s>[INST] {prompt} [/INST]
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [mistral-7b-instruct-v0.2.Q2_K.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [mistral-7b-instruct-v0.2.Q3_K_S.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [mistral-7b-instruct-v0.2.Q3_K_M.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [mistral-7b-instruct-v0.2.Q3_K_L.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [mistral-7b-instruct-v0.2.Q4_0.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mistral-7b-instruct-v0.2.Q4_K_S.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [mistral-7b-instruct-v0.2.Q4_K_M.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [mistral-7b-instruct-v0.2.Q5_0.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mistral-7b-instruct-v0.2.Q5_K_S.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [mistral-7b-instruct-v0.2.Q5_K_M.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [mistral-7b-instruct-v0.2.Q6_K.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [mistral-7b-instruct-v0.2.Q8_0.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBlock/Mistral-7B-Instruct-v0.2-GGUF and below it, a specific filename to download, such as: mistral-7b-instruct-v0.2.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBlock/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBlock/Mistral-7B-Instruct-v0.2-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBlock/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m mistral-7b-instruct-v0.2.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<s>[INST] {prompt} [/INST]"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./mistral-7b-instruct-v0.2.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<s>[INST] {prompt} [/INST]", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./mistral-7b-instruct-v0.2.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBlock AI's Discord server](https://discord.gg/TheBlokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Mistral AI_'s Mistral 7B Instruct v0.2
# Model Card for Mistral-7B-Instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).
For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/).
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
```
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
```
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## Troubleshooting
- If you see the following error:
```
Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'
```
Installing transformers from source should solve the issue
pip install git+https://github.com/huggingface/transformers
This should not be required after transformers-v4.33.4.
## Limitations
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
<!-- original-model-card end -->
|
ls-da3m0ns/bge_large_medical | ls-da3m0ns | 2024-02-29T10:40:07Z | 491 | 1 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| sentence-similarity | 2024-02-28T17:19:26Z | ---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 38 with parameters:
```
{'batch_size': 20, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 50,
"evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 38,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
TechxGenus/starcoder2-15b-instruct | TechxGenus | 2024-03-05T16:20:49Z | 491 | 6 | transformers | [
"transformers",
"safetensors",
"starcoder2",
"text-generation",
"code",
"license:bigcode-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-03-05T14:53:06Z | ---
tags:
- code
- starcoder2
library_name: transformers
pipeline_tag: text-generation
license: bigcode-openrail-m
---
<p align="center">
<img width="300px" alt="starcoder2-instruct" src="https://huggingface.co/TechxGenus/starcoder2-15b-instruct/resolve/main/starcoder2-instruct.jpg">
</p>
### starcoder2-instruct
We've fine-tuned starcoder2-15b with an additional 0.7 billion high-quality, code-related tokens for 3 epochs. We used DeepSpeed ZeRO 3 and Flash Attention 2 to accelerate the training process. It achieves **77.4 pass@1** on HumanEval-Python. This model operates using the Alpaca instruction format (excluding the system prompt).
### Usage
Here give some examples of how to use our model:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
PROMPT = """### Instruction
{instruction}
### Response
"""
instruction = <Your code instruction here>
prompt = PROMPT.format(instruction=instruction)
tokenizer = AutoTokenizer.from_pretrained("TechxGenus/starcoder2-15b-instruct")
model = AutoModelForCausalLM.from_pretrained(
"TechxGenus/starcoder2-15b-instruct",
torch_dtype=torch.bfloat16,
device_map="auto",
)
inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=2048)
print(tokenizer.decode(outputs[0]))
```
With text-generation pipeline:
```python
from transformers import pipeline
import torch
PROMPT = """### Instruction
{instruction}
### Response
"""
instruction = <Your code instruction here>
prompt = PROMPT.format(instruction=instruction)
generator = pipeline(
model="TechxGenus/starcoder2-15b-instruct",
task="text-generation",
torch_dtype=torch.bfloat16,
device_map="auto",
)
result = generator(prompt, max_length=2048)
print(result[0]["generated_text"])
```
### Note
Model may sometimes make errors, produce misleading contents, or struggle to manage tasks that are not related to coding. It has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.
|
selmamalak/organamnist-swin-base-finetuned | selmamalak | 2024-05-18T17:46:21Z | 491 | 0 | peft | [
"peft",
"safetensors",
"generated_from_trainer",
"dataset:medmnist-v2",
"base_model:microsoft/swin-large-patch4-window7-224-in22k",
"license:apache-2.0",
"region:us"
]
| null | 2024-05-18T13:38:51Z | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/swin-large-patch4-window7-224-in22k
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: organamnist-swin-base-finetuned
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# organamnist-swin-base-finetuned
This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on the medmnist-v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2521
- Accuracy: 0.9387
- Precision: 0.9430
- Recall: 0.9343
- F1: 0.9373
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6172 | 1.0 | 540 | 0.1913 | 0.9373 | 0.9481 | 0.9427 | 0.9422 |
| 0.6346 | 2.0 | 1081 | 0.0756 | 0.9760 | 0.9799 | 0.9752 | 0.9770 |
| 0.6405 | 3.0 | 1621 | 0.1310 | 0.9553 | 0.9600 | 0.9515 | 0.9537 |
| 0.5005 | 4.0 | 2162 | 0.1138 | 0.9663 | 0.9757 | 0.9718 | 0.9729 |
| 0.5669 | 5.0 | 2702 | 0.1142 | 0.9603 | 0.9704 | 0.9647 | 0.9665 |
| 0.5548 | 6.0 | 3243 | 0.0569 | 0.9772 | 0.9812 | 0.9785 | 0.9795 |
| 0.4298 | 7.0 | 3783 | 0.0989 | 0.9663 | 0.9770 | 0.9723 | 0.9736 |
| 0.3932 | 8.0 | 4324 | 0.0335 | 0.9884 | 0.9903 | 0.9887 | 0.9894 |
| 0.3409 | 9.0 | 4864 | 0.0371 | 0.9878 | 0.9900 | 0.9877 | 0.9887 |
| 0.3111 | 9.99 | 5400 | 0.0433 | 0.9846 | 0.9888 | 0.9864 | 0.9874 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 |
QuantFactory/internlm2-math-plus-1_8b-GGUF | QuantFactory | 2024-05-31T05:19:36Z | 491 | 0 | null | [
"gguf",
"math",
"text-generation",
"en",
"zh",
"base_model:internlm/internlm2-math-plus-1_8b",
"license:other",
"region:us"
]
| text-generation | 2024-05-31T02:24:08Z | ---
pipeline_tag: text-generation
license: other
language:
- en
- zh
tags:
- math
base_model: internlm/internlm2-math-plus-1_8b
---
# InternLM-Math-Plus-GGUF
This is quantized version of [internlm/internlm2-math-plus-1_8b]() created using llama.cpp
# Model Description
<div align="center">
<img src="https://raw.githubusercontent.com/InternLM/InternLM/main/assets/logo.svg" width="200"/>
<div> </div>
<div align="center">
<b><font size="5">InternLM-Math</font></b>
<sup>
<a href="https://internlm.intern-ai.org.cn/">
<i><font size="4">Plus</font></i>
</a>
</sup>
<div> </div>
</div>
State-of-the-art bilingual open-sourced Math reasoning LLMs.
A **solver**, **prover**, **verifier**, **augmentor**.
# News
- [2024.05.24] We release updated version InternLM2-Math-Plus with 4 sizes and state-of-the-art performances including 1.8B, 7B, 20B, and 8x22B. We improve informal math reasoning performance (chain-of-thought and code-intepreter) and formal math reasoning performance (LEAN 4 translation and LEAN 4 theorem proving) significantly.
- [2024.02.10] We add tech reports and citation reference.
- [2024.01.31] We add MiniF2F results with evaluation codes!
- [2024.01.29] We add checkpoints from ModelScope. Update results about majority voting and Code Intepreter. Tech report is on the way!
- [2024.01.26] We add checkpoints from OpenXLab, which ease Chinese users to download!
# Performance
## Formal Math Reasoning
We evaluate the performance of InternLM2-Math-Plus on formal math reasoning benchmark MiniF2F-test. The evaluation setting is same as Llemma with LEAN 4.
| Models | MiniF2F-test |
| -------------------------------- | ------------ |
| ReProver | 26.5 |
| LLMStep | 27.9 |
| GPT-F | 36.6 |
| HTPS | 41.0 |
| Llemma-7B | 26.2 |
| Llemma-34B | 25.8 |
| InternLM2-Math-7B-Base | 30.3 |
| InternLM2-Math-20B-Base | 29.5 |
| InternLM2-Math-Plus-1.8B | 38.9 |
| InternLM2-Math-Plus-7B | **43.4** |
| InternLM2-Math-Plus-20B | 42.6 |
| InternLM2-Math-Plus-Mixtral8x22B | 37.3 |
## Informal Math Reasoning
We evaluate the performance of InternLM2-Math-Plus on informal math reasoning benchmark MATH and GSM8K. InternLM2-Math-Plus-1.8B outperforms MiniCPM-2B in the smallest size setting. InternLM2-Math-Plus-7B outperforms Deepseek-Math-7B-RL which is the state-of-the-art math reasoning open source model. InternLM2-Math-Plus-Mixtral8x22B achieves 68.5 on MATH (with Python) and 91.8 on GSM8K.
| Model | MATH | MATH-Python | GSM8K |
| -------------------------------- | -------- | ----------- | -------- |
| MiniCPM-2B | 10.2 | - | 53.8 |
| InternLM2-Math-Plus-1.8B | **37.0** | **41.5** | **58.8** |
| InternLM2-Math-7B | 34.6 | 50.9 | 78.1 |
| Deepseek-Math-7B-RL | 51.7 | 58.8 | **88.2** |
| InternLM2-Math-Plus-7B | **53.0** | **59.7** | 85.8 |
| InternLM2-Math-20B | 37.7 | 54.3 | 82.6 |
| InternLM2-Math-Plus-20B | **53.8** | **61.8** | **87.7** |
| Mixtral8x22B-Instruct-v0.1 | 41.8 | - | 78.6 |
| Eurux-8x22B-NCA | 49.0 | - | - |
| InternLM2-Math-Plus-Mixtral8x22B | **58.1** | **68.5** | **91.8** |
We also evaluate models on [MathBench-A](https://github.com/open-compass/MathBench). InternLM2-Math-Plus-Mixtral8x22B has comparable performance compared to Claude 3 Opus.
| Model | Arithmetic | Primary | Middle | High | College | Average |
| -------------------------------- | ---------- | ------- | ------ | ---- | ------- | ------- |
| GPT-4o-0513 | 77.7 | 87.7 | 76.3 | 59.0 | 54.0 | 70.9 |
| Claude 3 Opus | 85.7 | 85.0 | 58.0 | 42.7 | 43.7 | 63.0 |
| Qwen-Max-0428 | 72.3 | 86.3 | 65.0 | 45.0 | 27.3 | 59.2 |
| Qwen-1.5-110B | 70.3 | 82.3 | 64.0 | 47.3 | 28.0 | 58.4 |
| Deepseek-V2 | 82.7 | 89.3 | 59.0 | 39.3 | 29.3 | 59.9 |
| Llama-3-70B-Instruct | 70.3 | 86.0 | 53.0 | 38.7 | 34.7 | 56.5 |
| InternLM2-Math-Plus-Mixtral8x22B | 77.5 | 82.0 | 63.6 | 50.3 | 36.8 | 62.0 |
| InternLM2-Math-20B | 58.7 | 70.0 | 43.7 | 24.7 | 12.7 | 42.0 |
| InternLM2-Math-Plus-20B | 65.8 | 79.7 | 59.5 | 47.6 | 24.8 | 55.5 |
| Llama3-8B-Instruct | 54.7 | 71.0 | 25.0 | 19.0 | 14.0 | 36.7 |
| InternLM2-Math-7B | 53.7 | 67.0 | 41.3 | 18.3 | 8.0 | 37.7 |
| Deepseek-Math-7B-RL | 68.0 | 83.3 | 44.3 | 33.0 | 23.0 | 50.3 |
| InternLM2-Math-Plus-7B | 61.4 | 78.3 | 52.5 | 40.5 | 21.7 | 50.9 |
| MiniCPM-2B | 49.3 | 51.7 | 18.0 | 8.7 | 3.7 | 26.3 |
| InternLM2-Math-Plus-1.8B | 43.0 | 43.3 | 25.4 | 18.9 | 4.7 | 27.1 |
|
axs531622/TinyLlama-1.1B-Chat-v1.0-solidworks-intro | axs531622 | 2024-05-31T02:50:00Z | 491 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-31T02:46:22Z | ---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
widget:
- example_title: Fibonacci (Python)
messages:
- role: system
content: You are a chatbot who can help code!
- role: user
content: Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.
---
<div align="center">
# TinyLlama-1.1B
</div>
https://github.com/jzhang38/TinyLlama
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
#### This Model
This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4."
#### How to use
You will need the transformers>=4.34
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# ...
``` |
Felladrin/gguf-sharded-Qwen2-1.5B-Instruct | Felladrin | 2024-06-07T09:25:51Z | 491 | 0 | null | [
"gguf",
"base_model:Qwen/Qwen2-1.5B-Instruct",
"license:apache-2.0",
"region:us"
]
| null | 2024-06-07T09:20:00Z | ---
license: apache-2.0
base_model: Qwen/Qwen2-1.5B-Instruct
---
Sharded GGUF version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct).
|
laituan245/molt5-base | laituan245 | 2022-05-03T18:07:36Z | 490 | 0 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"arxiv:2204.11817",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2022-05-03T17:40:19Z | ---
license: apache-2.0
---
## Example Usage
```python
from transformers import AutoTokenizer, T5ForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("laituan245/molt5-base", model_max_length=512)
model = T5ForConditionalGeneration.from_pretrained('laituan245/molt5-base')
```
## Paper
For more information, please take a look at our paper.
Paper: [Translation between Molecules and Natural Language](https://arxiv.org/abs/2204.11817)
Authors: *Carl Edwards\*, Tuan Lai\*, Kevin Ros, Garrett Honke, Heng Ji*
|
timm/vit_medium_patch16_gap_256.sw_in12k_ft_in1k | timm | 2023-05-06T00:26:57Z | 490 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-12k",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
]
| image-classification | 2022-12-02T01:56:59Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-12k
---
# Model card for vit_medium_patch16_gap_256.sw_in12k_ft_in1k
A Vision Transformer (ViT) image classification model. This is a `timm` specific variation of the architecture with token global average pooling. Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in `timm` using recipe template described below.
Recipe details:
* Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes)
* AdamW optimizer, gradient clipping, EMA weight averaging
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 38.9
- GMACs: 9.8
- Activations (M): 14.3
- Image size: 256 x 256
- **Papers:**
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-12k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_medium_patch16_gap_256.sw_in12k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_medium_patch16_gap_256.sw_in12k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 256, 512) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
|
allenai/cosmo-xl | allenai | 2023-01-24T17:21:46Z | 490 | 83 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"conversational",
"dialogue",
"response generation",
"en",
"dataset:allenai/soda",
"dataset:allenai/prosocial-dialog",
"arxiv:2212.10465",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2022-12-22T07:53:06Z | ---
language:
- en
tags:
- conversational
- dialogue
- response generation
license: apache-2.0
datasets:
- allenai/soda
- allenai/prosocial-dialog
---
# Model Card for 🧑🏻🚀COSMO
🧑🏻🚀COSMO is a conversation agent with greater generalizability on both in- and out-of-domain chitchat datasets (e.g., DailyDialog, BlendedSkillTalk). It is trained on two datasets: SODA and ProsocialDialog. COSMO is especially aiming to model natural human conversations. It can accept situation descriptions as well as instructions on what role it should play in the situation.
## Model Description
- **Repository:** [Code](https://github.com/skywalker023/sodaverse)
- **Paper:** [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://arxiv.org/abs/2212.10465)
- **Point of Contact:** [Hyunwoo Kim](mailto:[email protected])
## Model Training
🧑🏻🚀COSMO is trained on our two recent datasets: 🥤[SODA](https://huggingface.co/datasets/allenai/soda) and [Prosocial Dialog](https://huggingface.co/datasets/allenai/prosocial-dialog).
The backbone model of COSMO is the [lm-adapted T5](https://huggingface.co/google/t5-xl-lm-adapt).
### How to use
> 💡 <b>Note:</b> The HuggingFace inference API for Cosmo is not working correctly, we gently guide you to [our repository](https://hyunw.kim/sodaverse) to try out the demo code!
> 🚨 <b>Disclaimer:</b> We would like to emphasize that COSMO is trained on SODA and ProsocialDialog mainly for academic/research purposes. We discourage using COSMO in real-world applications or services as is. Model outputs should not be used for advice for humans, and could be potentially offensive, problematic, or harmful. The model’s output does not necessarily reflect the views and opinions of the authors and their associated affiliations.
Below is a simple code snippet to get Cosmo running :)
```python
import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained("allenai/cosmo-xl")
model = AutoModelForSeq2SeqLM.from_pretrained("allenai/cosmo-xl").to(device)
def set_input(situation_narrative, role_instruction, conversation_history):
input_text = " <turn> ".join(conversation_history)
if role_instruction != "":
input_text = "{} <sep> {}".format(role_instruction, input_text)
if situation_narrative != "":
input_text = "{} <sep> {}".format(situation_narrative, input_text)
return input_text
def generate(situation_narrative, role_instruction, conversation_history):
"""
situation_narrative: the description of situation/context with the characters included (e.g., "David goes to an amusement park")
role_instruction: the perspective/speaker instruction (e.g., "Imagine you are David and speak to his friend Sarah").
conversation_history: the previous utterances in the conversation in a list
"""
input_text = set_input(situation_narrative, role_instruction, conversation_history)
inputs = tokenizer([input_text], return_tensors="pt").to(device)
outputs = model.generate(inputs["input_ids"], max_new_tokens=128, temperature=1.0, top_p=.95, do_sample=True)
response = tokenizer.decode(outputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
return response
situation = "Cosmo had a really fun time participating in the EMNLP conference at Abu Dhabi."
instruction = "You are Cosmo and you are talking to a friend." # You can also leave the instruction empty
conversation = [
"Hey, how was your trip to Abu Dhabi?"
]
response = generate(situation, instruction, conversation)
print(response)
```
### Further Details, Social Impacts, Bias, and Limitations
Please refer to our [paper](https://arxiv.org/abs/2212.10465).
Cosmo is mostly trained on social chitchat. Therefore, we do not encourage having knowledge-intensive conversations (e.g., science, medical issues, law).
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. 2021](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. 2021](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
## Additional Information
For a brief summary of our paper, please see this [tweet](https://twitter.com/hyunw__kim/status/1605400305126248448).
### Citation
Please cite our work if you find the resources in this repository useful:
```
@article{kim2022soda,
title={SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization},
author={Hyunwoo Kim and Jack Hessel and Liwei Jiang and Peter West and Ximing Lu and Youngjae Yu and Pei Zhou and Ronan Le Bras and Malihe Alikhani and Gunhee Kim and Maarten Sap and Yejin Choi},
journal={ArXiv},
year={2022},
volume={abs/2212.10465}
}
``` |
entropy/gpt2_zinc_87m | entropy | 2023-09-15T19:02:07Z | 490 | 2 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"chemistry",
"molecule",
"drug",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-05-11T00:35:11Z | ---
license: mit
tags:
- chemistry
- molecule
- drug
---
# GPT2 Zinc 87m
This is a GPT2 style autoregressive language model trained on ~480m SMILES strings from the [ZINC database](https://zinc.docking.org/).
The model has ~87m parameters and was trained for 175000 iterations with a batch size of 3072 to a validation loss of ~.615. This model is useful for generating druglike molecules or generating embeddings from SMILES strings
## How to use
```python
from transformers import GPT2TokenizerFast, GPT2LMHeadModel
tokenizer = GPT2TokenizerFast.from_pretrained("entropy/gpt2_zinc_87m", max_len=256)
model = GPT2LMHeadModel.from_pretrained('entropy/gpt2_zinc_87m')
```
To generate molecules:
```python
inputs = torch.tensor([[tokenizer.bos_token_id]])
gen = model.generate(
inputs,
do_sample=True,
max_length=256,
temperature=1.,
early_stopping=True,
pad_token_id=tokenizer.pad_token_id,
num_return_sequences=32
)
smiles = tokenizer.batch_decode(gen, skip_special_tokens=True)
```
To compute embeddings:
```python
from transformers import DataCollatorWithPadding
collator = DataCollatorWithPadding(tokenizer, padding=True, return_tensors='pt')
inputs = collator(tokenizer(smiles))
outputs = model(**inputs, output_hidden_states=True)
full_embeddings = outputs[-1][-1]
mask = inputs['attention_mask']
embeddings = ((full_embeddings * mask.unsqueeze(-1)).sum(1) / mask.sum(-1).unsqueeze(-1))
```
### WARNING
This model was trained with `bos` and `eos` tokens around SMILES inputs. The `GPT2TokenizerFast` tokenizer DOES NOT ADD special tokens,
even when `add_special_tokens=True`. Huggingface says this is [intended behavior](https://github.com/huggingface/transformers/issues/3311#issuecomment-693719190).
It may be necessary to manually add these tokens
```python
inputs = collator(tokenizer([tokenizer.bos_token+i+tokenizer.eos_token for i in smiles]))
```
## Model Performance
To test generation performance, 1m compounds were generated at various temperature values. Generated compounds were checked for uniqueness and structural validity.
* `percent_unique` denotes `n_unique_smiles/n_total_smiles`
* `percent_valid` denotes `n_valid_smiles/n_unique_smiles`
* `percent_unique_and_valid` denotes `n_valid_smiles/n_total_smiles`
| temperature | percent_unique | percent_valid | percent_unique_and_valid |
|--------------:|-----------------:|----------------:|---------------------------:|
| 0.5 | 0.928074 | 1 | 0.928074 |
| 0.75 | 0.998468 | 0.999967 | 0.998436 |
| 1 | 0.999659 | 0.999164 | 0.998823 |
| 1.25 | 0.999514 | 0.99351 | 0.993027 |
| 1.5 | 0.998749 | 0.970223 | 0.96901 |
Property histograms computed over 1m generated compounds:
|
TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ | TheBloke | 2023-09-27T12:44:25Z | 490 | 548 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"uncensored",
"en",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"base_model:ehartford/Wizard-Vicuna-30B-Uncensored",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
]
| text-generation | 2023-05-30T03:11:00Z | ---
language:
- en
license: other
tags:
- uncensored
datasets:
- ehartford/wizard_vicuna_70k_unfiltered
model_name: Wizard Vicuna 30B Uncensored
base_model: ehartford/Wizard-Vicuna-30B-Uncensored
inference: false
model_creator: Eric Hartford
model_type: llama
prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the user''s questions.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Wizard Vicuna 30B Uncensored - GPTQ
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Wizard Vicuna 30B Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Eric Hartford's Wizard-Vicuna-30B-Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-fp16)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Vicuna
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/main) | 4 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 16.94 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 19.44 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 18.18 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 17.55 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 32.99 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 33.73 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 12.92 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| [gptq-3bit-128g-actorder_False](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ/tree/gptq-3bit-128g-actorder_False) | 3 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.51 GB | No | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ:main`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Wizard-Vicuna-30B-Uncensored-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .
```
### For CodeLlama models only: you must use Transformers 4.33.0 or later.
If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
```shell
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Eric Hartford's Wizard-Vicuna-30B-Uncensored
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Eric Hartford's Wizard-Vicuna-30B-Uncensored GPTQ
This is an fp16 models of [Eric Hartford's Wizard-Vicuna 30B](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored).
It is the result of converting Eric's original fp32 upload to fp16.
## Repositories available
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ).
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GGML).
* [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-fp16).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card
This is [wizard-vicuna-13b](https://huggingface.co/junelee/wizard-vicuna-13b) trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
Shout out to the open source AI/ML community, and everyone who helped me out.
Note:
An uncensored model has no guardrails.
You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.
Publishing anything this model generates is the same as publishing it yourself.
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
|
Yntec/GOLDFish | Yntec | 2023-09-23T13:35:34Z | 490 | 5 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"OLDFish",
"RMHF",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-17T10:26:48Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
- OLDFish
- RMHF
---
# GOLDFish
A mix between the models OLDFIsh by timevisitor and RMHF_2.5D_v2 by TkskKurumi.
Preview image by Digiplay:
Original pages:
https://civitai.com/models/14978?modelVersionId=40101
https://civitai.com/models/101518?modelVersionId=110456 |
TheBloke/qCammel-13-GGUF | TheBloke | 2023-09-27T12:47:39Z | 490 | 3 | transformers | [
"transformers",
"gguf",
"llama",
"pytorch",
"llama-2",
"qCammel-13",
"text-generation",
"en",
"arxiv:2305.12031",
"arxiv:2305.14314",
"arxiv:2302.13971",
"base_model:augtoma/qCammel-13",
"license:other",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-09-05T14:41:24Z | ---
language:
- en
license: other
library_name: transformers
tags:
- pytorch
- llama
- llama-2
- qCammel-13
model_name: qCammel 13
base_model: augtoma/qCammel-13
inference: false
model_creator: augtoma
model_type: llama
pipeline_tag: text-generation
prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the user''s questions.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# qCammel 13 - GGUF
- Model creator: [augtoma](https://huggingface.co/augtoma)
- Original model: [qCammel 13](https://huggingface.co/augtoma/qCammel-13)
<!-- description start -->
## Description
This repo contains GGUF format model files for [augtoma's qCammel 13](https://huggingface.co/augtoma/qCammel-13).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/qCammel-13-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/qCammel-13-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/qCammel-13-GGUF)
* [augtoma's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/augtoma/qCammel-13)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Vicuna
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [augtoma's qCammel 13](https://huggingface.co/augtoma/qCammel-13).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [qcammel-13.Q2_K.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [qcammel-13.Q3_K_S.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [qcammel-13.Q3_K_M.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [qcammel-13.Q3_K_L.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [qcammel-13.Q4_0.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [qcammel-13.Q4_K_S.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [qcammel-13.Q4_K_M.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [qcammel-13.Q5_0.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [qcammel-13.Q5_K_S.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [qcammel-13.Q5_K_M.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [qcammel-13.Q6_K.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [qcammel-13.Q8_0.gguf](https://huggingface.co/TheBloke/qCammel-13-GGUF/blob/main/qcammel-13.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/qCammel-13-GGUF and below it, a specific filename to download, such as: qcammel-13.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/qCammel-13-GGUF qcammel-13.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/qCammel-13-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/qCammel-13-GGUF qcammel-13.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m qcammel-13.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/qCammel-13-GGUF", model_file="qcammel-13.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: augtoma's qCammel 13
# qCammel-13
qCammel-13 is a fine-tuned version of Llama-2 13B model, trained on a distilled dataset of 15,000 instructions using QLoRA. This model is optimized for academic medical knowledge and instruction-following capabilities.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept their License before downloading this model .*
The fine-tuning process applied to qCammel-13 involves a distilled dataset of 15,000 instructions and is trained with QLoRA,
**Variations** The original Llama 2 has parameter sizes of 7B, 13B, and 70B. This is the fine-tuned version of the 13B model.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** qCammel-13 is based on the Llama 2 architecture, an auto-regressive language model that uses a decoder only transformer architecture.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved
**Research Papers**
- [Clinical Camel: An Open-Source Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding](https://arxiv.org/abs/2305.12031)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)
- [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
<!-- original-model-card end -->
|
TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF | TheBloke | 2023-10-18T08:40:29Z | 490 | 7 | transformers | [
"transformers",
"gguf",
"mistral",
"en",
"dataset:PocketDoc/Floyd-Text-Adventures",
"dataset:PocketDoc/Choose-Your-Story-Long-Text-Adventures",
"base_model:PocketDoc/Dans-AdventurousWinds-Mk2-7b",
"license:apache-2.0",
"text-generation-inference",
"region:us"
]
| null | 2023-10-18T08:34:10Z | ---
base_model: PocketDoc/Dans-AdventurousWinds-Mk2-7b
datasets:
- PocketDoc/Floyd-Text-Adventures
- PocketDoc/Choose-Your-Story-Long-Text-Adventures
inference: false
language:
- en
license: apache-2.0
model_creator: PocketDoc Labs
model_name: Dans AdventurousWinds Mk2 7B
model_type: mistral
prompt_template: '[Genres: Science Fiction]
[Tags: humor, old school, sci fi]
[Mode: Adventure]
[Description: A puzzle about committing acts of financial skulduggery and exploiting
ridiculous magical items.]
[Misc: Writing era: 1993]
[Intro]
It is the year 2045. You are a young man in his twenties living in New York City.
Your father was an inventor who died when you were very small; your mother raised
you alone for many years until she remarried. Now you live with your stepfather,
but he doesn''t care much for you and has never given you any money to help support
yourself. You have no job and little hope of getting one because of your lack of
experience. However, you do have some unusual abilities that could be put to good
use if only you knew how...
> {prompt}
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Dans AdventurousWinds Mk2 7B - GGUF
- Model creator: [PocketDoc Labs](https://huggingface.co/PocketDoc)
- Original model: [Dans AdventurousWinds Mk2 7B](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-Mk2-7b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [PocketDoc Labs's Dans AdventurousWinds Mk2 7B](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-Mk2-7b).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF)
* [PocketDoc Labs's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-Mk2-7b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Adventure
```
[Genres: Science Fiction]
[Tags: humor, old school, sci fi]
[Mode: Adventure]
[Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]
[Misc: Writing era: 1993]
[Intro]
It is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how...
> {prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [dans-adventurouswinds-mk2-7b.Q2_K.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [dans-adventurouswinds-mk2-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [dans-adventurouswinds-mk2-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [dans-adventurouswinds-mk2-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [dans-adventurouswinds-mk2-7b.Q4_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [dans-adventurouswinds-mk2-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [dans-adventurouswinds-mk2-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [dans-adventurouswinds-mk2-7b.Q5_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [dans-adventurouswinds-mk2-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [dans-adventurouswinds-mk2-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [dans-adventurouswinds-mk2-7b.Q6_K.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [dans-adventurouswinds-mk2-7b.Q8_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF/blob/main/dans-adventurouswinds-mk2-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF and below it, a specific filename to download, such as: dans-adventurouswinds-mk2-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF dans-adventurouswinds-mk2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF dans-adventurouswinds-mk2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m dans-adventurouswinds-mk2-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[Genres: Science Fiction]\n[Tags: humor, old school, sci fi]\n[Mode: Adventure]\n[Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]\n[Misc: Writing era: 1993]\n[Intro]\nIt is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how...\n\n> {prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Dans-AdventurousWinds-Mk2-7B-GGUF", model_file="dans-adventurouswinds-mk2-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: PocketDoc Labs's Dans AdventurousWinds Mk2 7B
**16k training sequences**
# What is the model for?
This model is proficient in crafting text-based adventure games. It can both concise replies and more expansive, novel-like descriptions. The ability to alternate between these two response styles can be triggered by a distinct system message.
# What's in the sausage?
This model was trained on [Mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) using a custom version of the floyd and cys datasets from the skein text adventure dataset. The dataset has been improved over what was used in my previous model Dans-AdventurousWinds, in addition it had been trained on 16k sequence lengths.
## Prompt format and examples:
#### Format description:
Traditional adventure format with a description of the genre, tags, and other misc information at the top followed by an optional introductory message. User messages are prefixed with two new lines and "> ", model messages are one new line after the last user message or the description message if an introductory message is desired.
#### Examples of shorter responses:
> [Genres: Science Fiction]
> [Tags: humor, old school, sci fi]
> [Mode: Adventure]
> [Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]
> [Misc: Writing era: 1993]
> [Intro]
> You are an interstellar trader.
>
> On your way to the galactic capital of Coruscant to sell a large quantity of fettucini, you make a detour through a planetary system with a reputation for being dangerous and unstable. The reason is simple -- there is a very powerful magical item known as "The Sword Of Damocles" up for sale. You have no idea what it does, but you've heard that the previous owners all ended up dead or broke. In other words, these people were so desperate to get rid of the sword that they would probably be willing to take almost any price. It sounds like a great deal!
>
> Of course, you don't have enough money to buy the sword outright, which means that you will need to find some way to finance the purchase. There is only one possible source of funds in this part of space -- the loan sharks who operate out of a nearby planet called Riggerton. But these loans come at a high interest rate; if you can't pay them back quickly, you may end up losing everything.
>
> You also know that there are several potential buyers vying for ownership of the sword, including some of the most ruthless criminals in the galaxy. These people might be willing to kill each other over this object, making it more valuable than ever before! However, they are notoriously paranoid and suspicious, so you must proceed with extreme caution when dealing with them...
>
> Finally, there is always the chance that someone else will beat you to the punch by buying the sword first. If that happens then you won't be able to afford it anymore anyway, so maybe it doesn't matter too much?
>
> In any case, good luck! And remember: never borrow money from anyone unless you absolutely trust him completely. Otherwise he could turn around and sell YOU into slavery instead!
>
> Ready? Then let's begin...
>
> \> You snap out of your daydream and remember you're still in port.
> You should probably get ready to go somewhere now...
>
> There are three main places where traders usually hang out: the docking bay (where ships land), the casino (a place where people gamble) and the black market (an illegal bazaar). Each has its own advantages and disadvantages depending on what kind of goods you want to trade. For example, the docking bay is the safest option because it's run by the government, but it charges higher taxes; while the black market is riskier but cheaper.
>
> So where do you think you ought to go?
>
> \> You get ready for launch
> Okay, I guess we better start looking for something interesting then...
>
> Before we leave though, I just wanted to mention that there are two ways to travel between planets: hyperspace jumps and wormholes. Both methods require special technology that only exists inside starships, but they work differently.
>
> A hyperspace jump involves using a hyperdrive engine to accelerate faster than light speed until you reach another galaxy entirely. Once there, you slow down again and return home. This method takes longer than a wormhole, but it allows you to visit distant worlds without having to worry about getting lost along the way.
>
> Wormholes however, allow you to travel instantly across vast distances without needing to slow down at either end. Unfortunately, this type of transportation isn't available everywhere, plus it requires extremely powerful computers to map out their locations accurately. Still, if you happen to find yourself near one of these things then I strongly recommend taking advantage of it since it saves time.
>
> Anyway, let me know whenever you're ready to go. We'll see how far away our next stop lies...
>
> \> You check the database on wormhole technology
> Okay, here goes nothing...
>
> According to my research, there are currently three types of wormholes known to science: stable, unstable and artificial. Stable ones occur naturally throughout the universe and tend to stay open permanently. Unstable ones close after passing through once, whereas artificially created ones remain open indefinitely.
>
> As far as I know, none of these types are suitable for commercial use yet. However, scientists believe that further development will eventually lead to practical applications in areas such as teleportation and faster-than-light travel. Until then though, I doubt whether anything useful can be achieved simply by reading books about the subject.
>
> Sorry if I disappointed you there, but I hope this information proves useful nonetheless. Good luck with whatever comes next!
>
> P.S.: Before leaving, please ensure that all loose objects have been put away properly. Otherwise they could fall off the ship during flight and cause damage later on. Thanks!
#### Examples of longer novel like responses:
> [Genres: grimdark fantasy] [Tags: Fantasy, Grimdark, Serious, Villain Protagonist, War] [Description: This story is definitely more "story" than "game", however there are two distinct paths that can be followed, each with their own pitfalls and additional choices. This story can get long, and assuming you're surviving, years do pass in it and you and your environment will change.] [First message intro] [Mode: Interactive Storyteller]
> You have been a mercenary for many years now. You are an accomplished warrior and battlefield commander. Your company consists of about 50 men and women. Most are veteran soldiers from different countries, some even from as far away as the Americas. They are all loyal to you. The only thing keeping them from being devoted followers would be your atheism.
>
> The war has raged on for many years now. The enemy, the Kingdom of Erenland, is a nation of fanatics who worship a single god called Galdrin. Their religion spread across the land like wildfire after their king ascended to the throne. He declared himself a prophet and made his people believe they were invincible. They started invading neighboring nations to bring them into the fold. The king of your homeland, King Dagor, was one of the first to resist this. When he refused to allow missionaries into his country, the Erenlanders invaded anyway. It took several years before King Dagor managed to gather enough forces to repel the invasion. The war lasted for decades and finally ended when Dagor's grandson ascended to the throne. At that point, both sides realized how much blood had already been spilled and agreed to a truce.
>
> Unfortunately, the peace didn't last very long. A few years ago, King Dagor II died without any children. His cousin became the new monarch but she was weak and incompetent. She allowed her advisors to make most of the important decisions while she spent her time partying with nobles from other nations. One of these advisors convinced the queen to send troops to help quell rebellions that were taking place in the Erenlander cities. These rebellions were caused by dissatisfaction with the way the crown was handling things. They wanted to overthrow their ruler and install a new one that would listen to them.
>
> When word reached the court that the rebels had succeeded in killing the king, everyone panicked. The Queen ordered her army to march north immediately. Unfortunately, she hadn't thought through what would happen if the enemy army attacked during this period of chaos. The result was disastrous. The Erenlanders caught our army completely off guard and annihilated us almost entirely. Only a handful survived to tell the tale. Among those survivors was you.
>
> You have come back home to bury your fallen comrades. You know you won't find rest until you avenge their deaths. But where do you begin? How do you stop an entire nation from going to war against yours? And how do you convince others to join you when they see you as nothing more than a madman bent on destruction?
>
> These questions haunt you every night. You lie awake staring at the ceiling wondering how you could possibly make things right again. Then you remember something...
>
> There was once a great hero named Galadar who lived hundreds of years ago. He fought against tyranny and oppression throughout his lifetime. People said that he possessed magical powers which gave him strength beyond anything mortal. Some even claimed that he walked among the stars. After retiring from active duty, Galadar vanished mysteriously. No one knows where he went or why. Rumors say that he returned to fight alongside the gods against evil forces threatening to destroy existence itself. Whatever happened to him, no one knows for sure. All we do know is that his legacy lives on today through those who follow his example. Perhaps you too can become such a person. Perhaps you can use your talents to save the world from darkness just like he did so long ago. If you feel ready, then take up arms and prepare yourself for battle!
>
> Your journey begins here...
>
> You wake up feeling refreshed after a good night's sleep. You look around your bedroom and notice that everything seems normal. There isn't anyone else around except for your wife, who lies sleeping next to you. You turn towards her and smile softly. She stirs slightly and mumbles something incoherent. You stroke her hair gently and whisper sweet nothings into her ear. Soon she falls back asleep and you decide to leave her alone.
>
> As soon as you step outside your house, you hear voices coming from behind you. Turning quickly, you spot three young boys running down the street toward you. They stop suddenly and stare at you wide eyed. "Are you the man who killed the giants?" one asks nervously.
>
> You nod slowly. "Yes," you reply.
>
> "Then I guess we should thank you." Another boy adds.
>
> "Yeah," says the third one. "We heard that giants ate babies."
>
> You shake your head sadly. "No," you explain. "Giants don't eat babies. That's just a myth."
>
> "Oh really?" the first boy says skeptically. "Well then why did my parents move away from their village?"
>
> "I dunno," you shrug. "Maybe because they believed the same thing you did."
>
> The three kids look surprised. Then they laugh heartily together. "Haha!" they giggle. "That's funny!"
>
> You grin back at them. "Thanks."
>
> They run off laughing hysterically. You chuckle quietly to yourself. Kids are always full of surprises.
>
> After spending some quality time with your family, you return home early in the afternoon. You grab a cup of tea and sit down at the kitchen table to read the newspaper. As usual, most of the stories involve wars somewhere else in the world. There aren't any articles related to your own conflict yet though. Maybe tomorrow...
>
> Suddenly, you hear loud knocking on the front door. You stand up abruptly and rush over to answer it. Standing before you is an old man wearing a long beard and holding a staff in his hand. He looks familiar somehow.
>
> "Hello sir," he greets politely. "My name is Galanis. I am here representing the Academy of Magic Studies."
>
> "Ah yes," you respond. "I remember seeing advertisements for your school everywhere recently. What can I do for you?"
>
> "Well sir," he begins, "we have received reports that you possess certain abilities which fall under our area of expertise. Specifically, we understand that you are capable of controlling fire using mental telepathy. Is this true?"
>
> You nod slowly. "It certainly is."
>
> "Excellent," he smiles happily. "In light of these circumstances, I would like to offer you a position teaching at our academy. We require instructors skilled in various aspects of magic including conjuration, enchantment, necromancy, divination, alchemy, and astrology."
>
> You shake your head firmly. "I appreciate the offer Mr. Galanis but I must decline. My duties lie elsewhere right now."
>
> His face falls momentarily. "Very well then," he sighs dejectedly. "Perhaps another opportunity will arise later on."
>
> With that said, he turns around and leaves without saying another word. You watch him depart silently wondering whether you should have accepted his proposal. On the one hand, it might provide some distraction from the war. On the other hand, you doubt you could ever fit into such a structured environment. Besides, you wouldn't want to spend years away from home either. In the end, you decide to stay put and continue doing what you've always done best - fighting for justice.
>
> \> You go to the great library
> You enter the Great Library of Alexandria hoping to gain knowledge about the Erenlander religion. Unfortunately, you find out that nobody there knows anything about it. The closest thing resembling a book on the subject is a small pamphlet titled "A Brief Overview Of Religion". According to its author, the writer claims that religions differ mainly due to differences between societies. Each society creates its own beliefs based upon its unique experiences. Since no two cultures are alike, there cannot be any universal truth regarding divine matters. Therefore, there is no reason to expect one religion to be superior over another.
>
> You think deeply about this concept. Does it apply to the Erenlander faith? Are their beliefs simply an expression of local customs rather than absolute truths? Or does their doctrine truly reflect reality? These thoughts weigh heavily upon your mind. Suddenly, you hear someone calling your name. Turning around, you spot a librarian approaching you.
>
> "Mr. Thane," he says cheerfully. "Can I help you find something specific?"
>
> "Actually yes," you reply. "Do you happen to know anything about the Erenlander religion?"
>
> He scratches his chin thoughtfully. "Not really," he admits. "But let me show you something anyway." He leads you over to a large table covered with books. Picking one up randomly, he starts reading aloud from it.
>
> "According to ancient legends, Galdrin created the universe out of nothingness. Before that, nothing existed except pure chaos. Out of this void came forth life and light. With these gifts, Galdrin blessed humanity with wisdom and understanding. Through hard work and determination, humankind learned how to cultivate crops, build shelters, manufacture weapons, develop technology, establish governments, maintain order, and defend itself against enemies. By following the teachings of Galdrin, humans were able to rise above mere animals and achieve greatness beyond compare. Those who rejected his teachings fell victim to ignorance and decay. Eventually, their civilization collapsed leaving only ruins behind. Today, descendants of those original settlers still live amongst us. Although their culture has changed considerably since antiquity, they retain many traditions common among modern-day peoples. Their language remains virtually unchanged despite centuries of contact with foreign languages. Their art forms range widely ranging from poetry to sculpture to music. Their religion continues to flourish despite attempts to suppress it throughout history. And most importantly, their belief system continues to guide them along the path of righteousness."
>
> You listen intently as he speaks. His words seem familiar somehow. Has he told you this story before? Or perhaps it was passed down through generations within your family? Either way, you find yourself drawn into the narrative. Before long, you forget everything else happening around you. Everything fades away except for the sound of his voice echoing throughout your ears.
>
> "So why did Galdrin create the world?" the librarian finishes. "Because he loved us," he answers softly. "And because he knew we needed somewhere safe to call home."
>
> You nod slowly. "Thank you," you murmur. "That was quite interesting."
>
> "Glad to hear it," he grins broadly. "If you ever need anything else, please feel free to ask."
>
> You bid farewell to the librarian and walk back home. During the journey, you ponder over what you learned earlier. Did Galdrin actually exist? Was he real or imaginary? Could he possibly be connected to the Erenlander faith somehow? So many questions remain unanswered. Still, you sense that something significant occurred tonight. Something special transpired inside the library walls. Now, you must figure out exactly what happened.
# Some quick and dirty training details:
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="150" height="24"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- Sequence length: 16384
- \# of epochs: 3
- Training time: 5 hours
- Hardware: 4x RTX 4090
- Training type: QLoRA
- PEFT R/A: 32/32
# Credits:
### Skein Text Adventure Data:
Thank you to the [Kobold AI](https://huggingface.co/KoboldAI) community for curating the Skein dataset, which is pivotal to this model's capabilities.
<!-- original-model-card end -->
|
mradermacher/OptiMerged7B-GGUF | mradermacher | 2024-05-06T06:05:29Z | 490 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/AlphaMonarch-7B",
"mlabonne/NeuralMonarch-7B",
"Kukedlc/NeuralMaxime-7B-slerp",
"en",
"base_model:CultriX/OptiMerged7B",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-21T10:13:11Z | ---
base_model: CultriX/OptiMerged7B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/AlphaMonarch-7B
- mlabonne/NeuralMonarch-7B
- Kukedlc/NeuralMaxime-7B-slerp
---
## About
static quants of https://huggingface.co/CultriX/OptiMerged7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/OptiMerged7B-GGUF/resolve/main/OptiMerged7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF | mradermacher | 2024-05-06T04:39:00Z | 490 | 12 | transformers | [
"transformers",
"gguf",
"uncensored",
"llama",
"llama-3",
"unsloth",
"llama-factory",
"en",
"base_model:Replete-AI/DevsDoCode-LLama-3-8b-Uncensored",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-19T16:56:57Z | ---
base_model: Replete-AI/DevsDoCode-LLama-3-8b-Uncensored
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- uncensored
- transformers
- llama
- llama-3
- unsloth
- llama-factory
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Replete-AI/DevsDoCode-LLama-3-8b-Uncensored
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/phi-3-22b-GGUF | mradermacher | 2024-05-23T04:51:30Z | 490 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:ontocord/phi-3-22b",
"license:mit",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-23T03:34:03Z | ---
base_model: ontocord/phi-3-22b
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/ontocord/phi-3-22b
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q2_K.gguf) | Q2_K | 8.2 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.IQ3_XS.gguf) | IQ3_XS | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.IQ3_S.gguf) | IQ3_S | 9.7 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q3_K_S.gguf) | Q3_K_S | 9.7 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.IQ3_M.gguf) | IQ3_M | 10.3 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q3_K_M.gguf) | Q3_K_M | 11.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q3_K_L.gguf) | Q3_K_L | 12.0 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.IQ4_XS.gguf) | IQ4_XS | 12.0 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q4_K_S.gguf) | Q4_K_S | 12.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q4_K_M.gguf) | Q4_K_M | 13.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q5_K_S.gguf) | Q5_K_S | 15.3 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q5_K_M.gguf) | Q5_K_M | 16.1 | |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q6_K.gguf) | Q6_K | 18.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/phi-3-22b-GGUF/resolve/main/phi-3-22b.Q8_0.gguf) | Q8_0 | 23.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
DLight1551/JSH_c556 | DLight1551 | 2024-05-28T05:32:41Z | 490 | 0 | transformers | [
"transformers",
"pytorch",
"clip",
"zero-shot-image-classification",
"endpoints_compatible",
"region:us"
]
| zero-shot-image-classification | 2024-05-28T05:27:59Z | Entry not found |
mradermacher/CatunaMayo3B-GGUF | mradermacher | 2024-05-31T18:43:51Z | 490 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"Eric111/CatunaMayo",
"Eric111/CatunaLaserPi",
"en",
"base_model:Eric111/CatunaMayo3B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-31T17:31:16Z | ---
base_model: Eric111/CatunaMayo3B
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- Eric111/CatunaMayo
- Eric111/CatunaLaserPi
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Eric111/CatunaMayo3B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q2_K.gguf) | Q2_K | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.IQ3_XS.gguf) | IQ3_XS | 1.8 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q3_K_S.gguf) | Q3_K_S | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.IQ3_S.gguf) | IQ3_S | 1.9 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.IQ3_M.gguf) | IQ3_M | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q3_K_L.gguf) | Q3_K_L | 2.2 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.IQ4_XS.gguf) | IQ4_XS | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q5_K_S.gguf) | Q5_K_S | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q5_K_M.gguf) | Q5_K_M | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q6_K.gguf) | Q6_K | 3.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/CatunaMayo3B-GGUF/resolve/main/CatunaMayo3B.f16.gguf) | f16 | 8.0 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
KoboldAI/GPT-Neo-2.7B-Janeway | KoboldAI | 2022-03-20T12:57:50Z | 489 | 6 | transformers | [
"transformers",
"pytorch",
"gpt_neo",
"text-generation",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2022-03-02T23:29:04Z | ---
language: en
license: mit
---
# GPT-Neo 2.7B - Janeway
## Model Description
GPT-Neo 2.7B-Janeway is a finetune created using EleutherAI's GPT-Neo 2.7B model.
## Training data
The training data contains around 2210 ebooks, mostly in the sci-fi and fantasy genres. The dataset is based on the same dataset used by GPT-Neo-2.7B-Picard, with 20% more data in various genres.
Some parts of the dataset have been prepended using the following text: `[Genre: <genre1>,<genre2>]`
### How to use
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
```py
>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/GPT-Neo-2.7B-Janeway')
>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt's all right," Janeway said. "I'm certain that you're doing your best to keep me informed of what\'s going on."'}]
```
### Limitations and Biases
GPT-Neo was trained as an autoregressive language model. This means that its core functionality is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work.
GPT-Neo was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending on your usecase GPT-Neo may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile.
As with all language models, it is hard to predict in advance how GPT-Neo will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.
### BibTeX entry and citation info
The model is made using the following software:
```bibtex
@software{gpt-neo,
author = {Black, Sid and
Leo, Gao and
Wang, Phil and
Leahy, Connor and
Biderman, Stella},
title = {{GPT-Neo: Large Scale Autoregressive Language
Modeling with Mesh-Tensorflow}},
month = mar,
year = 2021,
note = {{If you use this software, please cite it using
these metadata.}},
publisher = {Zenodo},
version = {1.0},
doi = {10.5281/zenodo.5297715},
url = {https://doi.org/10.5281/zenodo.5297715}
}
``` |
describeai/gemini | describeai | 2022-05-14T00:46:52Z | 489 | 26 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"Explain code",
"Code Summarization",
"Summarization",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2022-03-02T23:29:05Z | ---
language: en
tags:
- Explain code
- Code Summarization
- Summarization
license: mit
---
# Gemini
For in-depth understanding of our model and methods, please see our blog [here](https://www.describe-ai.com/gemini)
## Model description
Gemini is a transformer based on Google's T5 model. The model is pre-trained on approximately 800k code/description pairs and then fine-tuned on 10k higher-level explanations that were synthetically generated. Gemini is capable of summarization/explaining short to medium code snippets in:
- Python
- Javascript (mostly vanilla JS, however, it can handle frameworks like React as well)
- Java
- Ruby
- Go
And outputs a description in English.
## Intended uses
Gemini without any additional fine-tuning is capable of explaining code in a sentence or two and typically performs best in Python and Javascript. We recommend using Gemini for either simple code explanation, documentation or producing more synthetic data to improve its explanations.
### How to use
You can use this model directly with a pipeline for Text2Text generation, as shown below:
```python
from transformers import pipeline, set_seed
summarizer = pipeline('text2text-generation', model='describeai/gemini')
code = "print('hello world!')"
response = summarizer(code, max_length=100, num_beams=3)
print("Summarized code: " + response[0]['generated_text'])
```
Which should yield something along the lines of:
```
Summarized code: The following code is greeting the world.
```
### Model sizes
- Gemini (this repo): 770 Million Parameters
- Gemini-Small - 220 Million Parameters
### Limitations
Typically, Gemini may produce overly simplistic descriptions that don't encompass the entire code snippet. We suspect with more training data, this could be circumvented and will produce better results.
### About Us
A Describe.ai, we are focused on building Artificial Intelligence systems that can understand language as well as humans. While a long path, we plan to contribute our findings to our API to the Open Source community. |
w11wo/javanese-bert-small-imdb-classifier | w11wo | 2023-07-01T07:17:16Z | 489 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"text-classification",
"javanese-bert-small-imdb-classifier",
"jv",
"dataset:w11wo/imdb-javanese",
"arxiv:1810.04805",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2022-03-02T23:29:05Z | ---
language: jv
tags:
- javanese-bert-small-imdb-classifier
license: mit
datasets:
- w11wo/imdb-javanese
widget:
- text: "Dhuh Gusti, film iki elek banget. Aku getun ndelok !!!"
---
## Javanese BERT Small IMDB Classifier
Javanese BERT Small IMDB Classifier is a movie-classification model based on the [BERT model](https://arxiv.org/abs/1810.04805). It was trained on Javanese IMDB movie reviews.
The model was originally [`w11wo/javanese-bert-small-imdb`](https://huggingface.co/w11wo/javanese-bert-small-imdb) which is then fine-tuned on the [`w11wo/imdb-javanese`](https://huggingface.co/datasets/w11wo/imdb-javanese) dataset consisting of Javanese IMDB movie reviews. It achieved an accuracy of 76.37% on the validation dataset. Many of the techniques used are based on a Hugging Face tutorial [notebook](https://github.com/huggingface/notebooks/blob/master/examples/text_classification.ipynb) written by [Sylvain Gugger](https://github.com/sgugger).
Hugging Face's `Trainer` class from the [Transformers](https://huggingface.co/transformers) library was used to train the model. PyTorch was used as the backend framework during training, but the model remains compatible with TensorFlow nonetheless.
## Model
| Model | #params | Arch. | Training/Validation data (text) |
|---------------------------------------|----------|----------------|---------------------------------|
| `javanese-bert-small-imdb-classifier` | 110M | BERT Small | Javanese IMDB (47.5 MB of text) |
## Evaluation Results
The model was trained for 5 epochs and the following is the final result once the training ended.
| train loss | valid loss | accuracy | total time |
|------------|------------|------------|------------|
| 0.131 | 1.113 | 0.763 | 59:16 |
## How to Use
### As Text Classifier
```python
from transformers import pipeline
pretrained_name = "w11wo/javanese-bert-small-imdb-classifier"
nlp = pipeline(
"sentiment-analysis",
model=pretrained_name,
tokenizer=pretrained_name
)
nlp("Film sing apik banget!")
```
## Disclaimer
Do consider the biases which came from the IMDB review that may be carried over into the results of this model.
## Author
Javanese BERT Small IMDB Classifier was trained and evaluated by [Wilson Wongso](https://w11wo.github.io/). All computation and development are done on Google Colaboratory using their free GPU access.
## Citation
If you use any of our models in your research, please cite:
```bib
@inproceedings{wongso2021causal,
title={Causal and Masked Language Modeling of Javanese Language using Transformer-based Architectures},
author={Wongso, Wilson and Setiawan, David Samuel and Suhartono, Derwin},
booktitle={2021 International Conference on Advanced Computer Science and Information Systems (ICACSIS)},
pages={1--7},
year={2021},
organization={IEEE}
}
```
|
AIARTCHAN/xtracolor.v11 | AIARTCHAN | 2023-02-28T07:28:58Z | 489 | 9 | diffusers | [
"diffusers",
"stable-diffusion",
"aiartchan",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-02-28T07:03:21Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
- aiartchan
---
# xtracolor.v11
[원본글](https://arca.live/b/aiart/70564359)
[civitai](https://civitai.com/models/12622/xtracolorv11)
# Download
- [original 7.7GB](https://civitai.com/api/download/models/14883)
- [safetensors 4.41GB](https://huggingface.co/AIARTCHAN/xtracolor.v11/resolve/main/xtracolor.v11-no-ema.safetensors)
- [safetensors fp16 2.13GB](https://huggingface.co/AIARTCHAN/xtracolor.v11/resolve/main/xtracolor.v11-fp16.safetensors)
추천 설정
프롬: (beautiful detailed glow:1.0~1.1), Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 9, Size: 512x768 or 768x512, upscaler: latent, Denoising strength: 0.57, Clip skip: 2
파워컬러v1, 니지저니 돚거 로라, 오랜지2, dalcefo 모델 병합한 결과물
|
timm/xception41p.ra3_in1k | timm | 2023-04-21T23:43:31Z | 489 | 1 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2110.00476",
"arxiv:1802.02611",
"arxiv:1610.02357",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-04-21T23:43:12Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for xception41p.ra3_in1k
An Aligned Xception image classification model. Pretrained on ImageNet-1k in `timm` by Ross Wightman using RandAugment `RA3` recipe. Related to `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476).
This Xception variation uses a `timm` specific pre-activation Xception block.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 26.9
- GMACs: 9.2
- Activations (M): 39.9
- Image size: 299 x 299
- **Papers:**
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation: https://arxiv.org/abs/1802.02611
- Xception: Deep Learning with Depthwise Separable Convolutions: https://arxiv.org/abs/1610.02357
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('xception41p.ra3_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'xception41p.ra3_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 128, 150, 150])
# torch.Size([1, 256, 75, 75])
# torch.Size([1, 728, 38, 38])
# torch.Size([1, 1024, 19, 19])
# torch.Size([1, 2048, 10, 10])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'xception41p.ra3_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 10, 10) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@inproceedings{deeplabv3plus2018,
title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
booktitle={ECCV},
year={2018}
}
```
```bibtex
@misc{chollet2017xception,
title={Xception: Deep Learning with Depthwise Separable Convolutions},
author={François Chollet},
year={2017},
eprint={1610.02357},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
|
Doctor-Shotgun/Nous-Capybara-limarpv3-34B | Doctor-Shotgun | 2023-11-16T06:20:24Z | 489 | 25 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-11-16T05:58:09Z | Entry not found |
Yntec/mistoonEmerald2 | Yntec | 2023-12-23T09:53:28Z | 489 | 3 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Cartoon",
"Fanart",
"Inzaniak",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-11-17T23:56:46Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Cartoon
- Fanart
- Inzaniak
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
---
# mistoonEmerald 2
This model with the MoistMistV2 VAE baked in. Original page: https://civitai.com/models/28322?modelVersionId=57368
Comparison:
Sample and prompt:
pretty cute little, Library Background,action,Pigtails,Crew Top,final fantasy, socks, chibi, masterpiece, detailed, highres, 90s |
Erin/mist-zh | Erin | 2023-12-01T12:36:01Z | 489 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"feature-extraction",
"mteb",
"model-index",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
]
| feature-extraction | 2023-11-30T08:24:39Z | ---
tags:
- mteb
model-index:
- name: mist-zh
results:
- task:
type: STS
dataset:
type: C-MTEB/AFQMC
name: MTEB AFQMC
config: default
split: validation
revision: None
metrics:
- type: cos_sim_pearson
value: 44.80910972039708
- type: cos_sim_spearman
value: 46.97947004057185
- type: euclidean_pearson
value: 45.36774158404125
- type: euclidean_spearman
value: 46.97947004232487
- type: manhattan_pearson
value: 45.23486628014998
- type: manhattan_spearman
value: 46.87721960765866
- task:
type: STS
dataset:
type: C-MTEB/ATEC
name: MTEB ATEC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 49.5294624928126
- type: cos_sim_spearman
value: 51.34771777448503
- type: euclidean_pearson
value: 53.56859824288157
- type: euclidean_spearman
value: 51.34771439634126
- type: manhattan_pearson
value: 53.581640877132685
- type: manhattan_spearman
value: 51.349656519071274
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (zh)
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 39.318
- type: f1
value: 37.37720144558489
- task:
type: STS
dataset:
type: C-MTEB/BQ
name: MTEB BQ
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 62.12016334764962
- type: cos_sim_spearman
value: 65.08208654969742
- type: euclidean_pearson
value: 63.53078822303454
- type: euclidean_spearman
value: 65.0820865487212
- type: manhattan_pearson
value: 63.510532363654725
- type: manhattan_spearman
value: 65.06622789125241
- task:
type: Clustering
dataset:
type: C-MTEB/CLSClusteringP2P
name: MTEB CLSClusteringP2P
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 39.5071157612481
- task:
type: Clustering
dataset:
type: C-MTEB/CLSClusteringS2S
name: MTEB CLSClusteringS2S
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 37.99964332311132
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv1-reranking
name: MTEB CMedQAv1
config: default
split: test
revision: None
metrics:
- type: map
value: 84.67010533089491
- type: mrr
value: 86.99488095238095
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv2-reranking
name: MTEB CMedQAv2
config: default
split: test
revision: None
metrics:
- type: map
value: 85.27288868896477
- type: mrr
value: 87.5929761904762
- task:
type: Retrieval
dataset:
type: C-MTEB/CmedqaRetrieval
name: MTEB CmedqaRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 23.949
- type: map_at_10
value: 35.394
- type: map_at_100
value: 37.235
- type: map_at_1000
value: 37.364999999999995
- type: map_at_3
value: 31.433
- type: map_at_5
value: 33.668
- type: mrr_at_1
value: 36.834
- type: mrr_at_10
value: 44.451
- type: mrr_at_100
value: 45.445
- type: mrr_at_1000
value: 45.501000000000005
- type: mrr_at_3
value: 42.010999999999996
- type: mrr_at_5
value: 43.34
- type: ndcg_at_1
value: 36.834
- type: ndcg_at_10
value: 41.803000000000004
- type: ndcg_at_100
value: 49.091
- type: ndcg_at_1000
value: 51.474
- type: ndcg_at_3
value: 36.736000000000004
- type: ndcg_at_5
value: 38.868
- type: precision_at_1
value: 36.834
- type: precision_at_10
value: 9.354999999999999
- type: precision_at_100
value: 1.5310000000000001
- type: precision_at_1000
value: 0.183
- type: precision_at_3
value: 20.78
- type: precision_at_5
value: 15.238999999999999
- type: recall_at_1
value: 23.949
- type: recall_at_10
value: 51.68000000000001
- type: recall_at_100
value: 81.938
- type: recall_at_1000
value: 98.091
- type: recall_at_3
value: 36.408
- type: recall_at_5
value: 42.952
- task:
type: PairClassification
dataset:
type: C-MTEB/CMNLI
name: MTEB Cmnli
config: default
split: validation
revision: None
metrics:
- type: cos_sim_accuracy
value: 76.24774503908598
- type: cos_sim_ap
value: 84.76081551540754
- type: cos_sim_f1
value: 77.76321537789427
- type: cos_sim_precision
value: 72.96577167452347
- type: cos_sim_recall
value: 83.23591302314706
- type: dot_accuracy
value: 76.24774503908598
- type: dot_ap
value: 84.75968761251127
- type: dot_f1
value: 77.76321537789427
- type: dot_precision
value: 72.96577167452347
- type: dot_recall
value: 83.23591302314706
- type: euclidean_accuracy
value: 76.24774503908598
- type: euclidean_ap
value: 84.7608250840413
- type: euclidean_f1
value: 77.76321537789427
- type: euclidean_precision
value: 72.96577167452347
- type: euclidean_recall
value: 83.23591302314706
- type: manhattan_accuracy
value: 76.19963920625375
- type: manhattan_ap
value: 84.76313920535411
- type: manhattan_f1
value: 77.74253527288636
- type: manhattan_precision
value: 73.0374023838882
- type: manhattan_recall
value: 83.09562777647884
- type: max_accuracy
value: 76.24774503908598
- type: max_ap
value: 84.76313920535411
- type: max_f1
value: 77.76321537789427
- task:
type: Retrieval
dataset:
type: C-MTEB/CovidRetrieval
name: MTEB CovidRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 66.149
- type: map_at_10
value: 75.22999999999999
- type: map_at_100
value: 75.536
- type: map_at_1000
value: 75.542
- type: map_at_3
value: 73.384
- type: map_at_5
value: 74.459
- type: mrr_at_1
value: 66.28
- type: mrr_at_10
value: 75.232
- type: mrr_at_100
value: 75.52799999999999
- type: mrr_at_1000
value: 75.534
- type: mrr_at_3
value: 73.446
- type: mrr_at_5
value: 74.473
- type: ndcg_at_1
value: 66.386
- type: ndcg_at_10
value: 79.295
- type: ndcg_at_100
value: 80.741
- type: ndcg_at_1000
value: 80.891
- type: ndcg_at_3
value: 75.613
- type: ndcg_at_5
value: 77.46300000000001
- type: precision_at_1
value: 66.386
- type: precision_at_10
value: 9.283
- type: precision_at_100
value: 0.996
- type: precision_at_1000
value: 0.101
- type: precision_at_3
value: 27.503
- type: precision_at_5
value: 17.408
- type: recall_at_1
value: 66.149
- type: recall_at_10
value: 91.886
- type: recall_at_100
value: 98.52499999999999
- type: recall_at_1000
value: 99.684
- type: recall_at_3
value: 81.849
- type: recall_at_5
value: 86.275
- task:
type: Retrieval
dataset:
type: C-MTEB/DuRetrieval
name: MTEB DuRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 25.166
- type: map_at_10
value: 78.805
- type: map_at_100
value: 81.782
- type: map_at_1000
value: 81.818
- type: map_at_3
value: 54.226
- type: map_at_5
value: 68.783
- type: mrr_at_1
value: 88.6
- type: mrr_at_10
value: 92.244
- type: mrr_at_100
value: 92.31899999999999
- type: mrr_at_1000
value: 92.321
- type: mrr_at_3
value: 91.867
- type: mrr_at_5
value: 92.119
- type: ndcg_at_1
value: 88.6
- type: ndcg_at_10
value: 86.432
- type: ndcg_at_100
value: 89.357
- type: ndcg_at_1000
value: 89.688
- type: ndcg_at_3
value: 84.90299999999999
- type: ndcg_at_5
value: 84.137
- type: precision_at_1
value: 88.6
- type: precision_at_10
value: 41.685
- type: precision_at_100
value: 4.811
- type: precision_at_1000
value: 0.48900000000000005
- type: precision_at_3
value: 76.44999999999999
- type: precision_at_5
value: 64.87
- type: recall_at_1
value: 25.166
- type: recall_at_10
value: 88.227
- type: recall_at_100
value: 97.597
- type: recall_at_1000
value: 99.359
- type: recall_at_3
value: 56.946
- type: recall_at_5
value: 74.261
- task:
type: Retrieval
dataset:
type: C-MTEB/EcomRetrieval
name: MTEB EcomRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 48.3
- type: map_at_10
value: 57.635999999999996
- type: map_at_100
value: 58.306000000000004
- type: map_at_1000
value: 58.326
- type: map_at_3
value: 54.900000000000006
- type: map_at_5
value: 56.620000000000005
- type: mrr_at_1
value: 48.3
- type: mrr_at_10
value: 57.635999999999996
- type: mrr_at_100
value: 58.306000000000004
- type: mrr_at_1000
value: 58.326
- type: mrr_at_3
value: 54.900000000000006
- type: mrr_at_5
value: 56.620000000000005
- type: ndcg_at_1
value: 48.3
- type: ndcg_at_10
value: 62.638000000000005
- type: ndcg_at_100
value: 65.726
- type: ndcg_at_1000
value: 66.253
- type: ndcg_at_3
value: 57.081
- type: ndcg_at_5
value: 60.217
- type: precision_at_1
value: 48.3
- type: precision_at_10
value: 7.85
- type: precision_at_100
value: 0.9249999999999999
- type: precision_at_1000
value: 0.097
- type: precision_at_3
value: 21.133
- type: precision_at_5
value: 14.219999999999999
- type: recall_at_1
value: 48.3
- type: recall_at_10
value: 78.5
- type: recall_at_100
value: 92.5
- type: recall_at_1000
value: 96.6
- type: recall_at_3
value: 63.4
- type: recall_at_5
value: 71.1
- task:
type: Classification
dataset:
type: C-MTEB/IFlyTek-classification
name: MTEB IFlyTek
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 47.9646017699115
- type: f1
value: 35.03552351349023
- task:
type: Classification
dataset:
type: C-MTEB/JDReview-classification
name: MTEB JDReview
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 84.8968105065666
- type: ap
value: 52.564605306946774
- type: f1
value: 79.59880155481291
- task:
type: STS
dataset:
type: C-MTEB/LCQMC
name: MTEB LCQMC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 70.03662039861051
- type: cos_sim_spearman
value: 76.9642260444222
- type: euclidean_pearson
value: 75.47376966815843
- type: euclidean_spearman
value: 76.9642282583736
- type: manhattan_pearson
value: 75.45535385433548
- type: manhattan_spearman
value: 76.94609742735338
- task:
type: Retrieval
dataset:
type: C-MTEB/MMarcoRetrieval
name: MTEB MMarcoRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 65.604
- type: map_at_10
value: 74.522
- type: map_at_100
value: 74.878
- type: map_at_1000
value: 74.889
- type: map_at_3
value: 72.61
- type: map_at_5
value: 73.882
- type: mrr_at_1
value: 67.75099999999999
- type: mrr_at_10
value: 75.08399999999999
- type: mrr_at_100
value: 75.402
- type: mrr_at_1000
value: 75.412
- type: mrr_at_3
value: 73.446
- type: mrr_at_5
value: 74.531
- type: ndcg_at_1
value: 67.75099999999999
- type: ndcg_at_10
value: 78.172
- type: ndcg_at_100
value: 79.753
- type: ndcg_at_1000
value: 80.06400000000001
- type: ndcg_at_3
value: 74.607
- type: ndcg_at_5
value: 76.728
- type: precision_at_1
value: 67.75099999999999
- type: precision_at_10
value: 9.443999999999999
- type: precision_at_100
value: 1.023
- type: precision_at_1000
value: 0.105
- type: precision_at_3
value: 28.009
- type: precision_at_5
value: 17.934
- type: recall_at_1
value: 65.604
- type: recall_at_10
value: 88.84100000000001
- type: recall_at_100
value: 95.954
- type: recall_at_1000
value: 98.425
- type: recall_at_3
value: 79.497
- type: recall_at_5
value: 84.515
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-CN)
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.64963012777405
- type: f1
value: 65.01092085388518
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-CN)
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.9724277067922
- type: f1
value: 72.48003852874602
- task:
type: Retrieval
dataset:
type: C-MTEB/MedicalRetrieval
name: MTEB MedicalRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 48.9
- type: map_at_10
value: 55.189
- type: map_at_100
value: 55.687
- type: map_at_1000
value: 55.74400000000001
- type: map_at_3
value: 53.75
- type: map_at_5
value: 54.555
- type: mrr_at_1
value: 49.1
- type: mrr_at_10
value: 55.289
- type: mrr_at_100
value: 55.788000000000004
- type: mrr_at_1000
value: 55.845
- type: mrr_at_3
value: 53.849999999999994
- type: mrr_at_5
value: 54.655
- type: ndcg_at_1
value: 48.9
- type: ndcg_at_10
value: 58.275
- type: ndcg_at_100
value: 60.980000000000004
- type: ndcg_at_1000
value: 62.672000000000004
- type: ndcg_at_3
value: 55.282
- type: ndcg_at_5
value: 56.749
- type: precision_at_1
value: 48.9
- type: precision_at_10
value: 6.800000000000001
- type: precision_at_100
value: 0.8130000000000001
- type: precision_at_1000
value: 0.095
- type: precision_at_3
value: 19.900000000000002
- type: precision_at_5
value: 12.659999999999998
- type: recall_at_1
value: 48.9
- type: recall_at_10
value: 68.0
- type: recall_at_100
value: 81.3
- type: recall_at_1000
value: 95.0
- type: recall_at_3
value: 59.699999999999996
- type: recall_at_5
value: 63.3
- task:
type: Classification
dataset:
type: C-MTEB/MultilingualSentiment-classification
name: MTEB MultilingualSentiment
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 71.53666666666668
- type: f1
value: 70.74267338218574
- task:
type: PairClassification
dataset:
type: C-MTEB/OCNLI
name: MTEB Ocnli
config: default
split: validation
revision: None
metrics:
- type: cos_sim_accuracy
value: 70.43854899837575
- type: cos_sim_ap
value: 75.25713109733296
- type: cos_sim_f1
value: 73.18777292576418
- type: cos_sim_precision
value: 62.397617274758
- type: cos_sim_recall
value: 88.48996832101372
- type: dot_accuracy
value: 70.43854899837575
- type: dot_ap
value: 75.25713109733296
- type: dot_f1
value: 73.18777292576418
- type: dot_precision
value: 62.397617274758
- type: dot_recall
value: 88.48996832101372
- type: euclidean_accuracy
value: 70.43854899837575
- type: euclidean_ap
value: 75.25713109733296
- type: euclidean_f1
value: 73.18777292576418
- type: euclidean_precision
value: 62.397617274758
- type: euclidean_recall
value: 88.48996832101372
- type: manhattan_accuracy
value: 70.60097455332972
- type: manhattan_ap
value: 75.22177995740668
- type: manhattan_f1
value: 73.13750532141337
- type: manhattan_precision
value: 61.26961483594865
- type: manhattan_recall
value: 90.70749736008447
- type: max_accuracy
value: 70.60097455332972
- type: max_ap
value: 75.25713109733296
- type: max_f1
value: 73.18777292576418
- task:
type: Classification
dataset:
type: C-MTEB/OnlineShopping-classification
name: MTEB OnlineShopping
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 91.3
- type: ap
value: 89.03601366589187
- type: f1
value: 91.28612226957141
- task:
type: STS
dataset:
type: C-MTEB/PAWSX
name: MTEB PAWSX
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 24.254041798082984
- type: cos_sim_spearman
value: 30.029755057178846
- type: euclidean_pearson
value: 30.394005237465905
- type: euclidean_spearman
value: 30.029751825186153
- type: manhattan_pearson
value: 30.400683181995863
- type: manhattan_spearman
value: 29.981240616043326
- task:
type: STS
dataset:
type: C-MTEB/QBQTC
name: MTEB QBQTC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 35.09911024323138
- type: cos_sim_spearman
value: 37.49790006053554
- type: euclidean_pearson
value: 35.65689785105493
- type: euclidean_spearman
value: 37.498032509597344
- type: manhattan_pearson
value: 35.68350134483341
- type: manhattan_spearman
value: 37.54046578100128
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 68.26707578158273
- type: cos_sim_spearman
value: 69.19741429899995
- type: euclidean_pearson
value: 68.53026048034656
- type: euclidean_spearman
value: 69.1974135636389
- type: manhattan_pearson
value: 70.02306646353263
- type: manhattan_spearman
value: 70.46158498712836
- task:
type: STS
dataset:
type: C-MTEB/STSB
name: MTEB STSB
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 78.88749955421177
- type: cos_sim_spearman
value: 79.56695106617856
- type: euclidean_pearson
value: 79.13787024514338
- type: euclidean_spearman
value: 79.56690827015423
- type: manhattan_pearson
value: 79.08154812411563
- type: manhattan_spearman
value: 79.52391077945943
- task:
type: Reranking
dataset:
type: C-MTEB/T2Reranking
name: MTEB T2Reranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 65.78663254562939
- type: mrr
value: 74.9786877626248
- task:
type: Retrieval
dataset:
type: C-MTEB/T2Retrieval
name: MTEB T2Retrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 26.169999999999998
- type: map_at_10
value: 74.009
- type: map_at_100
value: 77.788
- type: map_at_1000
value: 77.866
- type: map_at_3
value: 51.861000000000004
- type: map_at_5
value: 63.775000000000006
- type: mrr_at_1
value: 87.748
- type: mrr_at_10
value: 90.737
- type: mrr_at_100
value: 90.84400000000001
- type: mrr_at_1000
value: 90.849
- type: mrr_at_3
value: 90.257
- type: mrr_at_5
value: 90.54299999999999
- type: ndcg_at_1
value: 87.748
- type: ndcg_at_10
value: 82.114
- type: ndcg_at_100
value: 86.148
- type: ndcg_at_1000
value: 86.913
- type: ndcg_at_3
value: 83.54599999999999
- type: ndcg_at_5
value: 81.987
- type: precision_at_1
value: 87.748
- type: precision_at_10
value: 41.076
- type: precision_at_100
value: 4.976
- type: precision_at_1000
value: 0.515
- type: precision_at_3
value: 73.282
- type: precision_at_5
value: 61.351
- type: recall_at_1
value: 26.169999999999998
- type: recall_at_10
value: 81.292
- type: recall_at_100
value: 94.285
- type: recall_at_1000
value: 98.221
- type: recall_at_3
value: 53.824000000000005
- type: recall_at_5
value: 67.547
- task:
type: Classification
dataset:
type: C-MTEB/TNews-classification
name: MTEB TNews
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 51.564
- type: f1
value: 49.711462885083286
- task:
type: Clustering
dataset:
type: C-MTEB/ThuNewsClusteringP2P
name: MTEB ThuNewsClusteringP2P
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 62.57078038998942
- task:
type: Clustering
dataset:
type: C-MTEB/ThuNewsClusteringS2S
name: MTEB ThuNewsClusteringS2S
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 57.842602165392144
- task:
type: Retrieval
dataset:
type: C-MTEB/VideoRetrieval
name: MTEB VideoRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 52.0
- type: map_at_10
value: 62.932
- type: map_at_100
value: 63.471999999999994
- type: map_at_1000
value: 63.483999999999995
- type: map_at_3
value: 60.516999999999996
- type: map_at_5
value: 62.097
- type: mrr_at_1
value: 52.0
- type: mrr_at_10
value: 62.932
- type: mrr_at_100
value: 63.471999999999994
- type: mrr_at_1000
value: 63.483999999999995
- type: mrr_at_3
value: 60.516999999999996
- type: mrr_at_5
value: 62.097
- type: ndcg_at_1
value: 52.0
- type: ndcg_at_10
value: 67.963
- type: ndcg_at_100
value: 70.598
- type: ndcg_at_1000
value: 70.896
- type: ndcg_at_3
value: 63.144
- type: ndcg_at_5
value: 65.988
- type: precision_at_1
value: 52.0
- type: precision_at_10
value: 8.36
- type: precision_at_100
value: 0.959
- type: precision_at_1000
value: 0.098
- type: precision_at_3
value: 23.567
- type: precision_at_5
value: 15.52
- type: recall_at_1
value: 52.0
- type: recall_at_10
value: 83.6
- type: recall_at_100
value: 95.89999999999999
- type: recall_at_1000
value: 98.2
- type: recall_at_3
value: 70.7
- type: recall_at_5
value: 77.60000000000001
- task:
type: Classification
dataset:
type: C-MTEB/waimai-classification
name: MTEB Waimai
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 86.65999999999998
- type: ap
value: 69.91988858863054
- type: f1
value: 84.92982698422784
- task:
type: Reranking
dataset:
type: C-MTEB/Mmarco-reranking
name: MTEB MMarcoReranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 27.838972963193315
- type: mrr
value: 26.65238095238095
--- |
MBZUAI/GLaMM-RefSeg | MBZUAI | 2023-12-26T22:51:19Z | 489 | 0 | transformers | [
"transformers",
"pytorch",
"llava",
"text-generation",
"arxiv:2311.03356",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-12-26T18:26:20Z | ---
license: apache-2.0
---
# 👁️ GLaMM-RefSeg
---
## 📝 Description
GLaMM-RegCap-VG is the model specific to referring expression segmentation. "RefSeg" denotes its focus on segmentation tasks related to referring expressions.
## 💻 Download
To get started with GLaMM-RefSeg, follow these steps:
```
git lfs install
git clone https://huggingface.co/MBZUAI/GLaMM-RefSeg
```
## 📚 Additional Resources
- **Paper:** [ArXiv](https://arxiv.org/abs/2311.03356).
- **GitHub Repository:** For training and updates: [GitHub - GLaMM](https://github.com/mbzuai-oryx/groundingLMM).
- **Project Page:** For a detailed overview and insights into the project, visit our [Project Page - GLaMM](https://mbzuai-oryx.github.io/groundingLMM/).
## 📜 Citations and Acknowledgments
```bibtex
@article{hanoona2023GLaMM,
title={GLaMM: Pixel Grounding Large Multimodal Model},
author={Rasheed, Hanoona and Maaz, Muhammad and Shaji, Sahal and Shaker, Abdelrahman and Khan, Salman and Cholakkal, Hisham and Anwer, Rao M. and Xing, Eric and Yang, Ming-Hsuan and Khan, Fahad S.},
journal={ArXiv 2311.03356},
year={2023}
}
|
Legalaz/5HLAHFXp6nMMfD83oeVdGW8m68ozYQhSf1jd81ZW6r51wiBR_vgg | Legalaz | 2024-02-21T01:40:08Z | 489 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-02-18T20:50:34Z | Entry not found |
PORTULAN/gervasio-7b-portuguese-ptbr-decoder | PORTULAN | 2024-04-02T20:12:18Z | 489 | 9 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"gervasio-pt*",
"gervasio-ptpt",
"gervasio-ptbr",
"gervasio-7b-portuguese-ptpt-decoder",
"gervasio-7b-portuguese-ptbr-decoder",
"portulan",
"albertina-pt*",
"clm",
"gpt",
"portuguese",
"decoder",
"foundation model",
"pt",
"dataset:PORTULAN/extraglue",
"dataset:PORTULAN/extraglue-instruct",
"arxiv:2402.18766",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-02-28T14:47:55Z | ---
license: mit
language:
- pt
tags:
- gervasio-pt*
- gervasio-ptpt
- gervasio-ptbr
- gervasio-7b-portuguese-ptpt-decoder
- gervasio-7b-portuguese-ptbr-decoder
- portulan
- albertina-pt*
- clm
- gpt
- portuguese
- decoder
- foundation model
datasets:
- PORTULAN/extraglue
- PORTULAN/extraglue-instruct
---
</br>
</br>
<img align="left" width="40" height="40" src="https://github.githubassets.com/images/icons/emoji/unicode/1f917.png">
<p style="text-align: center;"> This is the model card for Gervásio 7B PTBR Decoder.
You may be interested in some of the other models in the <a href="https://huggingface.co/PORTULAN">Albertina (encoders) and Gervásio (decoders) families</a>.
</p>
</br>
</br>
# Gervásio 7B PTBR
</br>
**Gervásio PT*** is a **fully open** decoder for the **Portuguese language**.
It is a **decoder** of the LLaMA family, based on the neural architecture Transformer and developed over the LLaMA-2 7B model.
Its further improvement through additional training was done over language resources that include new instruction data sets of Portuguese prepared for this purpose ([extraGLUE-Instruct
](https://huggingface.co/datasets/PORTULAN/extraglue-instruct)).
It has different versions that were trained for different variants of Portuguese (PT),
namely for the European variant, spoken in Portugal ([**gervasio-7b-portuguese-ptpt-decoder**](https://huggingface.co/PORTULAN/gervasio-7b-portuguese-ptpt-decoder)), and for the American variant, spoken in Brazil ([**gervasio-7b-portuguese-ptbr-decoder**](https://huggingface.co/PORTULAN/gervasio-7b-portuguese-ptbr-decoder)).
All versions of Gervásio are **openly distributed for free under an open license**, including thus for research and commercial purposes, and given its size, can
be run on consumer-grade hardware.
**Gervásio 7B PTBR** is developed by NLX-Natural Language and Speech Group, at the University of Lisbon, Faculty of Sciences, Department of Informatics, Portugal.
For the record, its full name is **Gervásio Produz Textos em Português**, to which corresponds the natural acronym **GPT PT**,
and which is known more shortly as **Gervásio PT*** or, even more briefly, just as **Gervásio**, among its acquaintances.
Gervásio 7B PTBR is developed by a team from the University of Lisbon, Portugal.
For a fully detailed description, check the respective [publication](https://arxiv.org/abs/2402.18766):
``` latex
@misc{gervasio,
title={Advancing Generative AI for Portuguese with
Open Decoder Gervásio PT-*},
author={Rodrigo Santos, João Silva, Luís Gomes,
João Rodrigues, António Branco},
year={2024},
eprint={2402.18766},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
Please use the above cannonical reference when using or citing this model.
<br>
# Model Description
**This model card is for Gervásio 7B PTBR**, with 7 billion parameters, a hidden size of 4,096 units, an intermediate size of 11,008 units, 32 attention heads, 32 hidden layers, and a tokenizer obtained using the Byte-Pair Encoding (BPE) algorithm implemented with SentencePiece, featuring a vocabulary size of 32,000.
Gervásio 7B PTBR is distributed under an [MIT license](https://huggingface.co/PORTULAN/gervasio-7b-portuguese-ptpt-decoder/blob/main/LICENSE).
<br>
# Training Data
**Gervásio 7B PTBR** was trained over standard supervised fine-tuning, and to keep some alignment with mainstream benchmarks for English, we resorted to tasks and respective datasets in the GLUE and the SuperGLUE collections.
We selected those datasets where the outcome of their machine translation into Portuguese could preserve, in the target language, the linguistic properties at stake.
From GLUE, we resorted to the following four tasks:
- MRPC (paraphrase Detection).
- RTE (recognizing Textual Entailment).
- STS-B (semantic textual similarity).
- WNLI (coreference and natural language inference).
And from SuperGLUE, we included these other four tasks:
- BoolQ (yes/no question answering).
- CB (inference with 3 labels).
- COPA (reasoning)
- MultiRC (question answering).
These datasets were machine translated into American Portuguese and from the [extraGLUE](https://huggingface.co/datasets/PORTULAN/extraglue) dataset.
Furthermore, instruction templates have been manually crafted for each task.
These take the various fields in the dataset and arrange them into prompts, which were collected into the [extraGLUE-instruct](https://huggingface.co/datasets/PORTULAN/extraglue-instruct) dataset.
We also employed data augmentation techniques to enhance the size and diversity of our dataset.
This involved repurposing the tasks in various ways, such as generation of answers from MultiRC, question generation from BoolQ, and other relevant modifications.
# Training Details
We applied supervised fine-tuning with a causal language modeling training objective following a zero-out technique during the fine-tuning process.
Specifically, while the entire prompt received attention during fine-tuning, only the response tokens were subjected to back-propagation.
In terms of hyper-parameters, the model was trained with a learning rate of 2 * 10^-5, a weight decay of 0.1, a two-epoch training regime without warm-up, and to ensure the same number of tokens back-propagated per step, we employed an input sequence of 512 tokens with a batch size of 16 and 16 accumulation steps.
Due to hardware limitations that imposed a shorter sequence length (512) compared to the base model (4096), instead of the typical practice of concatenating all training examples and then dividing them into batches with the same input sequence length, we separated each example individually.
In other words, each example occupies the full input sequence length.
# Performance
For testing, we reserved the translated datasets MRPC (similarity) and RTE (inference), from GLUE, and COPA (reasoning/qa), from SuperGLUE, which were taken as representatives of three major types of tasks, and were not seen during training.
| Model | MRPC (F1) | RTE (F1) | COPA (F1) |
|--------------------------|----------------|----------------|-----------|
| **Gervásio 7B PTBR** | **0.7822** | **0.8321** | 0.2134 |
| **LLaMA-2 (English)** | 0.0369 | 0.0516 | 0.4867 |
| **LLaMA-2 Chat (English)** | 0.5432 | 0.3807 | **0.5493**|
For further testing our decoder, in addition to the testing data described above, we also used datasets that were originally developed with texts from Portuguese: ASSIN2 RTE (entailment) and ASSIN2 STS (similarity), BLUEX (question answering), ENEM 2022 (question answering) and FaQuAD (extractive question-answering).
| Model | ENEM 2022 (Accuracy) | BLUEX (Accuracy)| RTE (F1) | STS (Pearson) |
|--------------------------|----------------------|-----------------|-----------|---------------|
| **Gervásio 7B PTBR** | 0.1977 | 0.2640 | **0.7469**| **0.2136** |
| **LLaMA-2 (English)** | **0.2458** | 0.2903 | 0.0913 | 0.1034 |
| **LLaMA-2 Chat (English)** | 0.2231 | **0.2959** | 0.5546 | 0.1750 |
In comparison with other decoder of the same dimension, namely Sabiá 1.5B, Gervásio shows a superior
or competitive performance for the tasks in PTBR, while being the sole encoder of 1.5B dimmension for the PTPT
variant of Portuguese and thus the state of art
in this respect at the time of its publishing. For further evaluation data,
see the respective [publication](https://arxiv.org/abs/2402.18766).
<br>
# How to use
You can use this model directly with a pipeline for causal language modeling:
```python3
>>> from transformers import pipeline
>>> generator = pipeline(model='PORTULAN/gervasio-7b-portuguese-ptbr-decoder')
>>> generator("A música brasileira é", max_new_tokens=10)
```
<br>
# Acknowledgments
The research reported here was partially supported by: PORTULAN CLARIN—Research Infrastructure for the Science and Technology of Language,
funded by Lisboa 2020, Alentejo 2020 and FCT—Fundação para a Ciência e Tecnologia under the
grant PINFRA/22117/2016; research project GPT-PT - Transformer-based Decoder for the Portuguese Language, funded by FCT—Fundação para a Ciência e Tecnologia under the
grant CPCA-IAC/AV/478395/2022; innovation project
ACCELERAT.AI - Multilingual Intelligent Contact Centers, funded by IAPMEI, I.P. - Agência para a Competitividade e Inovação
under the grant C625734525-00462629, of Plano de Recuperação e Resiliência,
call RE-C05-i01.01 – Agendas/Alianças Mobilizadoras para a Reindustrialização. |
ChrisWilson010101/5EqJVz7ayN7aXzi72JH7biVugWN2iwvNgm2mLrXcFEwTRE24_vgg | ChrisWilson010101 | 2024-03-03T23:16:28Z | 489 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-03-01T16:07:42Z | Entry not found |
BigData-KSU/RS-llava-v1.5-7b-LoRA | BigData-KSU | 2024-04-23T13:37:46Z | 489 | 1 | transformers | [
"transformers",
"llava",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-03-21T13:10:44Z | ---
license: mit
---
## RS-LLaVA: Large Vision Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery
- **Repository:** https://github.com/BigData-KSU/RS-LLaVA
- **Paper:** https://www.mdpi.com/2072-4292/16/9/1477
- **Demo:** Soon.
## How to Get Started with the Model
### Install
1. Clone this repository and navigate to RS-LLaVA folder
```
git clone https://github.com/BigData-KSU/RS-LLaVA.git
cd RS-LLaVA
```
2. Install Package
```
conda create -n rs-llava python=3.10 -y
conda activate rs-llava
pip install --upgrade pip # enable PEP 660 support
```
3. Install additional packages
```
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
pip install transformers==4.35
pip install einops
pip inastall SentencePiece
pip install accelerate
pip install peft
```
---
### Inference
Use the code below to get started with the model.
```python
import torch
import os
from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
from llava.conversation import conv_templates, SeparatorStyle
from llava.model.builder import load_pretrained_model
from llava.utils import disable_torch_init
from llava.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from PIL import Image
import math
######## model here.................
model_path = 'BigData-KSU/RS-llava-v1.5-7b-LoRA'
model_base = 'Intel/neural-chat-7b-v3-3'
#### Further instrcutions here..........
conv_mode = 'llava_v1'
disable_torch_init()
model_name = get_model_name_from_path(model_path)
print('model name', model_name)
print('model base', model_base)
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, model_base, model_name)
def chat_with_RS_LLaVA(cur_prompt,image_name):
# Prepare the input text, adding image-related tokens if needed
image_mem = Image.open(image_name)
image_tensor = image_processor.preprocess(image_mem, return_tensors='pt')['pixel_values'][0]
if model.config.mm_use_im_start_end:
cur_prompt = f"{DEFAULT_IM_START_TOKEN} {DEFAULT_IMAGE_TOKEN} {DEFAULT_IM_END_TOKEN}\n{cur_prompt}"
else:
cur_prompt = f"{DEFAULT_IMAGE_TOKEN}\n{cur_prompt}"
# Create a copy of the conversation template
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], cur_prompt)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
# Process image inputs if provided
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0) .cuda()
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=image_tensor.unsqueeze(0).half().cuda(),
do_sample=True,
temperature=0.2,
top_p=None,
num_beams=1,
no_repeat_ngram_size=3,
max_new_tokens=2048,
use_cache=True)
input_token_len = input_ids.shape[1]
n_diff_input_output = (input_ids != output_ids[:, :input_token_len]).sum().item()
if n_diff_input_output > 0:
print(f'[Warning] {n_diff_input_output} output_ids are not the same as the input_ids')
outputs = tokenizer.batch_decode(output_ids[:, input_token_len:], skip_special_tokens=True)[0]
outputs = outputs.strip()
return outputs
if __name__ == "__main__":
print('Model input...............')
cur_prompt='Generate three questions and answers about the content of this image. Then, compile a summary.'
image_name='assets/example_images/parking_lot_010.jpg'
outputs=chat_with_RS_LLaVA(cur_prompt,image_name)
print('Model Response.....')
print(outputs)
```
## Training Details
Training RS-LLaVa is carried out in three stages:
#### Stage 1: Pretraining (Feature alignment) stage:
Using LAION/CC/SBU BLIP-Caption Concept-balanced 558K dataset, and two RS datasets, [NWPU](https://github.com/HaiyanHuang98/NWPU-Captions) and [RSICD](https://huggingface.co/datasets/arampacha/rsicd).
| Dataset | Size | Link |
| --- | --- |--- |
|CC-3M Concept-balanced 595K|211 MB|[Link](https://github.com/haotian-liu/LLaVA/blob/main/docs/Data.md)|
|NWPU-RSICD-Pretrain|16.6 MB|[Link](https://huggingface.co/datasets/BigData-KSU/RS-instructions-dataset/blob/main/NWPU-RSICD-pretrain.json)|
#### Stage 2: Visual Instruction Tuning:
To teach the model to follow instructions, we used the proposed RS-Instructions Dataset plus LLaVA-Instruct-150K dataset.
| Dataset | Size | Link |
| --- | --- |--- |
|RS-Instructions|91.3 MB|[Link](https://huggingface.co/datasets/BigData-KSU/RS-instructions-dataset/blob/main/NWPU-RSICD-UAV-UCM-LR-DOTA-intrcutions.json)|
|llava_v1_5_mix665k|1.03 GB|[Link](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/llava_v1_5_mix665k.json)|
#### Stage 3: Downstram Task Tuning:
In this stage, the model is fine-tuned on one of the downstream tasks (e.g., RS image captioning or VQA)
## Citation
**BibTeX:**
```bibtex
@Article{rs16091477,
AUTHOR = {Bazi, Yakoub and Bashmal, Laila and Al Rahhal, Mohamad Mahmoud and Ricci, Riccardo and Melgani, Farid},
TITLE = {RS-LLaVA: A Large Vision-Language Model for Joint Captioning and Question Answering in Remote Sensing Imagery},
JOURNAL = {Remote Sensing},
VOLUME = {16},
YEAR = {2024},
NUMBER = {9},
ARTICLE-NUMBER = {1477},
URL = {https://www.mdpi.com/2072-4292/16/9/1477},
ISSN = {2072-4292},
DOI = {10.3390/rs16091477}
}
```
|
mradermacher/TimeMax-20B-GGUF | mradermacher | 2024-05-06T05:24:37Z | 489 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:R136a1/TimeMax-20B",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-01T16:14:35Z | ---
base_model: R136a1/TimeMax-20B
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
static quants of https://huggingface.co/R136a1/TimeMax-20B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/TimeMax-20B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q2_K.gguf) | Q2_K | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.IQ3_XS.gguf) | IQ3_XS | 8.5 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.IQ3_S.gguf) | IQ3_S | 9.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q3_K_S.gguf) | Q3_K_S | 9.0 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.IQ3_M.gguf) | IQ3_M | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q3_K_M.gguf) | Q3_K_M | 10.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q3_K_L.gguf) | Q3_K_L | 10.9 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.IQ4_XS.gguf) | IQ4_XS | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q4_K_S.gguf) | Q4_K_S | 11.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q4_K_M.gguf) | Q4_K_M | 12.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q5_K_S.gguf) | Q5_K_S | 14.1 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q5_K_M.gguf) | Q5_K_M | 14.5 | |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q6_K.gguf) | Q6_K | 16.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/TimeMax-20B-GGUF/resolve/main/TimeMax-20B.Q8_0.gguf) | Q8_0 | 21.5 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/StoryFusion-7B-GGUF | mradermacher | 2024-05-11T18:50:36Z | 489 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"mergekit",
"kasper52786/StoryWeaver-7b-Instruct-v0.1",
"N8Programs/Coxcomb",
"Norquinal/Mistral-7B-storywriter",
"en",
"base_model:OmnicromsBrain/StoryFusion-7B",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-09T13:52:55Z | ---
base_model: OmnicromsBrain/StoryFusion-7B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- merge
- mergekit
- kasper52786/StoryWeaver-7b-Instruct-v0.1
- N8Programs/Coxcomb
- Norquinal/Mistral-7B-storywriter
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/OmnicromsBrain/StoryFusion-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/StoryFusion-7B-GGUF/resolve/main/StoryFusion-7B.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
GuiCas/Phi-3-Phituguese-3b-q4_k_m | GuiCas | 2024-06-14T18:38:49Z | 489 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"phi",
"pt",
"dataset:dominguesm/Canarim-Instruct-PTBR-Dataset",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-30T15:33:40Z | ---
language:
- pt
license: mit
tags:
- text-generation-inference
- transformers
- unsloth
- phi
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
datasets:
- dominguesm/Canarim-Instruct-PTBR-Dataset
model-index:
- name: Phituguese_FP16
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: ENEM Challenge (No Images)
type: eduagarcia/enem_challenge
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 49.97
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BLUEX (No Images)
type: eduagarcia-temp/BLUEX_without_images
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 43.25
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: OAB Exams
type: eduagarcia/oab_exams
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 38.13
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 RTE
type: assin2
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 74.75
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 STS
type: eduagarcia/portuguese_benchmark
split: test
args:
num_few_shot: 15
metrics:
- type: pearson
value: 71.93
name: pearson
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: FaQuAD NLI
type: ruanchaves/faquad-nli
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 43.97
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HateBR Binary
type: ruanchaves/hatebr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 57.34
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: PT Hate Speech Binary
type: hate_speech_portuguese
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 60.48
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia/tweetsentbr_fewshot
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 61.11
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=GuiCas/Phituguese_FP16
name: Open Portuguese LLM Leaderboard
---
# Uploaded model
- **Developed by:** GuiCas
- **License:** mit
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/GuiCas/Phituguese_FP16) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
| Metric | Value |
|--------------------------|---------|
|Average |**55.66**|
|ENEM Challenge (No Images)| 49.97|
|BLUEX (No Images) | 43.25|
|OAB Exams | 38.13|
|Assin2 RTE | 74.75|
|Assin2 STS | 71.93|
|FaQuAD NLI | 43.97|
|HateBR Binary | 57.34|
|PT Hate Speech Binary | 60.48|
|tweetSentBR | 61.11|
|
njwright92/ComicBot_v.2-gguf | njwright92 | 2024-07-02T22:02:43Z | 489 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"comedy",
"text-generation",
"en",
"license:mit",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-22T00:41:04Z | ---
license: mit
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- comedy
--- |
Johnyquest7/medllama3-v20-Q4_K_M-GGUF | Johnyquest7 | 2024-06-22T17:24:19Z | 489 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:ProbeMedicalYonseiMAILab/medllama3-v20",
"license:llama3",
"region:us"
]
| null | 2024-06-22T17:23:57Z | ---
base_model: ProbeMedicalYonseiMAILab/medllama3-v20
license: llama3
tags:
- llama-cpp
- gguf-my-repo
---
# Johnyquest7/medllama3-v20-Q4_K_M-GGUF
This model was converted to GGUF format from [`ProbeMedicalYonseiMAILab/medllama3-v20`](https://huggingface.co/ProbeMedicalYonseiMAILab/medllama3-v20) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/ProbeMedicalYonseiMAILab/medllama3-v20) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Johnyquest7/medllama3-v20-Q4_K_M-GGUF --hf-file medllama3-v20-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Johnyquest7/medllama3-v20-Q4_K_M-GGUF --hf-file medllama3-v20-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Johnyquest7/medllama3-v20-Q4_K_M-GGUF --hf-file medllama3-v20-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Johnyquest7/medllama3-v20-Q4_K_M-GGUF --hf-file medllama3-v20-q4_k_m.gguf -c 2048
```
|
nalf3in2/Llama-3-Instruct-8B-SPPO-Iter3-Q5_K_S-GGUF | nalf3in2 | 2024-06-26T14:22:33Z | 489 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"dataset:openbmb/UltraFeedback",
"base_model:UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3",
"license:apache-2.0",
"region:us"
]
| text-generation | 2024-06-26T14:22:02Z | ---
base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
datasets:
- openbmb/UltraFeedback
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# nalf3in2/Llama-3-Instruct-8B-SPPO-Iter3-Q5_K_S-GGUF
This model was converted to GGUF format from [`UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3`](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo nalf3in2/Llama-3-Instruct-8B-SPPO-Iter3-Q5_K_S-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-q5_k_s-imat.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo nalf3in2/Llama-3-Instruct-8B-SPPO-Iter3-Q5_K_S-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-q5_k_s-imat.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo nalf3in2/Llama-3-Instruct-8B-SPPO-Iter3-Q5_K_S-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-q5_k_s-imat.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo nalf3in2/Llama-3-Instruct-8B-SPPO-Iter3-Q5_K_S-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-q5_k_s-imat.gguf -c 2048
```
|
larenspear/Yi-1.5-6B-Chat-Q3_K_S-GGUF | larenspear | 2024-07-01T01:33:50Z | 489 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:01-ai/Yi-1.5-6B-Chat",
"license:apache-2.0",
"region:us"
]
| null | 2024-07-01T01:33:39Z | ---
base_model: 01-ai/Yi-1.5-6B-Chat
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# larenspear/Yi-1.5-6B-Chat-Q3_K_S-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-6B-Chat`](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo larenspear/Yi-1.5-6B-Chat-Q3_K_S-GGUF --hf-file yi-1.5-6b-chat-q3_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo larenspear/Yi-1.5-6B-Chat-Q3_K_S-GGUF --hf-file yi-1.5-6b-chat-q3_k_s.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo larenspear/Yi-1.5-6B-Chat-Q3_K_S-GGUF --hf-file yi-1.5-6b-chat-q3_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo larenspear/Yi-1.5-6B-Chat-Q3_K_S-GGUF --hf-file yi-1.5-6b-chat-q3_k_s.gguf -c 2048
```
|
Helsinki-NLP/opus-mt-fr-hu | Helsinki-NLP | 2023-08-16T11:36:34Z | 488 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"fr",
"hu",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| translation | 2022-03-02T23:29:04Z | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-fr-hu
* source languages: fr
* target languages: hu
* OPUS readme: [fr-hu](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fr-hu/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/fr-hu/opus-2020-01-26.zip)
* test set translations: [opus-2020-01-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fr-hu/opus-2020-01-26.test.txt)
* test set scores: [opus-2020-01-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fr-hu/opus-2020-01-26.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.fr.hu | 41.3 | 0.629 |
|
allenai/wmt19-de-en-6-6-big | allenai | 2023-01-24T16:28:51Z | 488 | 7 | transformers | [
"transformers",
"pytorch",
"fsmt",
"text2text-generation",
"translation",
"wmt19",
"allenai",
"de",
"en",
"dataset:wmt19",
"arxiv:2006.10369",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| translation | 2022-03-02T23:29:05Z |
---
language:
- de
- en
thumbnail:
tags:
- translation
- wmt19
- allenai
license: apache-2.0
datasets:
- wmt19
metrics:
- bleu
---
# FSMT
## Model description
This is a ported version of fairseq-based [wmt19 transformer](https://github.com/jungokasai/deep-shallow/) for de-en.
For more details, please, see [Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation](https://arxiv.org/abs/2006.10369).
2 models are available:
* [wmt19-de-en-6-6-big](https://huggingface.co/allenai/wmt19-de-en-6-6-big)
* [wmt19-de-en-6-6-base](https://huggingface.co/allenai/wmt19-de-en-6-6-base)
## Intended uses & limitations
#### How to use
```python
from transformers import FSMTForConditionalGeneration, FSMTTokenizer
mname = "allenai/wmt19-de-en-6-6-big"
tokenizer = FSMTTokenizer.from_pretrained(mname)
model = FSMTForConditionalGeneration.from_pretrained(mname)
input = "Maschinelles Lernen ist großartig, nicht wahr?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded) # Machine learning is great, isn't it?
```
#### Limitations and bias
## Training data
Pretrained weights were left identical to the original model released by allenai. For more details, please, see the [paper](https://arxiv.org/abs/2006.10369).
## Eval results
Here are the BLEU scores:
model | transformers
-------|---------
wmt19-de-en-6-6-big | 39.9
The score was calculated using this code:
```bash
git clone https://github.com/huggingface/transformers
cd transformers
export PAIR=de-en
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=8
export NUM_BEAMS=5
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target
echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py allenai/wmt19-de-en-6-6-big $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
### BibTeX entry and citation info
```
@misc{kasai2020deep,
title={Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation},
author={Jungo Kasai and Nikolaos Pappas and Hao Peng and James Cross and Noah A. Smith},
year={2020},
eprint={2006.10369},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
anton-l/xtreme_s_xlsr_300m_minds14 | anton-l | 2022-04-03T18:54:43Z | 488 | 2 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"audio-classification",
"minds14",
"google/xtreme_s",
"generated_from_trainer",
"all",
"dataset:google/xtreme_s",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| audio-classification | 2022-03-17T17:24:20Z | ---
language:
- all
license: apache-2.0
tags:
- minds14
- google/xtreme_s
- generated_from_trainer
datasets:
- google/xtreme_s
metrics:
- f1
- accuracy
model-index:
- name: xtreme_s_xlsr_300m_minds14
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xtreme_s_xlsr_300m_minds14
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the GOOGLE/XTREME_S - MINDS14.ALL dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.9033
- Accuracy Cs-cz: 0.9164
- Accuracy De-de: 0.9477
- Accuracy En-au: 0.9235
- Accuracy En-gb: 0.9324
- Accuracy En-us: 0.9326
- Accuracy Es-es: 0.9177
- Accuracy Fr-fr: 0.9444
- Accuracy It-it: 0.9167
- Accuracy Ko-kr: 0.8649
- Accuracy Nl-nl: 0.9450
- Accuracy Pl-pl: 0.9146
- Accuracy Pt-pt: 0.8940
- Accuracy Ru-ru: 0.8667
- Accuracy Zh-cn: 0.7291
- F1: 0.9015
- F1 Cs-cz: 0.9154
- F1 De-de: 0.9467
- F1 En-au: 0.9199
- F1 En-gb: 0.9334
- F1 En-us: 0.9308
- F1 Es-es: 0.9158
- F1 Fr-fr: 0.9436
- F1 It-it: 0.9135
- F1 Ko-kr: 0.8642
- F1 Nl-nl: 0.9440
- F1 Pl-pl: 0.9159
- F1 Pt-pt: 0.8883
- F1 Ru-ru: 0.8646
- F1 Zh-cn: 0.7249
- Loss: 0.4119
- Loss Cs-cz: 0.3790
- Loss De-de: 0.2649
- Loss En-au: 0.3459
- Loss En-gb: 0.2853
- Loss En-us: 0.2203
- Loss Es-es: 0.2731
- Loss Fr-fr: 0.1909
- Loss It-it: 0.3520
- Loss Ko-kr: 0.5431
- Loss Nl-nl: 0.2515
- Loss Pl-pl: 0.4113
- Loss Pt-pt: 0.4798
- Loss Ru-ru: 0.6470
- Loss Zh-cn: 1.1216
- Predict Samples: 4086
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 50.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
| 2.6739 | 5.41 | 200 | 2.5687 | 0.0430 | 0.1190 |
| 1.4953 | 10.81 | 400 | 1.6052 | 0.5550 | 0.5692 |
| 0.6177 | 16.22 | 600 | 0.7927 | 0.8052 | 0.8011 |
| 0.3609 | 21.62 | 800 | 0.5679 | 0.8609 | 0.8609 |
| 0.4972 | 27.03 | 1000 | 0.5944 | 0.8509 | 0.8523 |
| 0.1799 | 32.43 | 1200 | 0.6194 | 0.8623 | 0.8621 |
| 0.1308 | 37.84 | 1400 | 0.5956 | 0.8569 | 0.8548 |
| 0.2298 | 43.24 | 1600 | 0.5201 | 0.8732 | 0.8743 |
| 0.0052 | 48.65 | 1800 | 0.3826 | 0.9106 | 0.9103 |
### Framework versions
- Transformers 4.18.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 2.0.1.dev0
- Tokenizers 0.11.6
|
wannaphong/wav2vec2-large-xlsr-53-th-cv8-deepcut | wannaphong | 2022-08-10T05:40:50Z | 488 | 5 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"th",
"dataset:common_voice",
"arxiv:2208.04799",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| automatic-speech-recognition | 2022-06-07T08:11:41Z | ---
language:
- th
tags:
- automatic-speech-recognition
license: apache-2.0
datasets:
- common_voice
metrics:
- wer
- cer
---
# Thai Wav2Vec2 with CommonVoice V8 (deepcut tokenizer) + language model
This model trained with CommonVoice V8 dataset by increase data from CommonVoice V7 dataset that It was use in [airesearch/wav2vec2-large-xlsr-53-th](https://huggingface.co/airesearch/wav2vec2-large-xlsr-53-th). It was finetune [wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53).
## Model description
- Technical report: [Thai Wav2Vec2.0 with CommonVoice V8](https://arxiv.org/abs/2208.04799)
## Datasets
It is increase new data from The Common Voice V8 dataset to Common Voice V7 dataset or remove all data in Common Voice V7 dataset before split Common Voice V8 then add CommonVoice V7 dataset back to dataset.
It use [ekapolc/Thai_commonvoice_split](https://github.com/ekapolc/Thai_commonvoice_split) script for split Common Voice dataset.
## Models
This model was finetune [wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) model with Thai Common Voice V8 dataset and It use pre-tokenize with deepcut.tokenize.
## Evaluation
**Test with CommonVoice V8 Testset**
| Model | WER by newmm (%) | WER by deepcut (%) | CER |
|-----------------------|------------------|--------------------|----------|
| AIResearch.in.th and PyThaiNLP | 17.414503 | 11.923089 | 3.854153 |
| wav2vec2 with deepcut | 16.354521 | 11.424476 | 3.684060 |
| wav2vec2 with newmm | 16.698299 | 11.436941 | 3.737407 |
| **wav2vec2 with deepcut + language model** | 12.630260 | 9.613886 | 3.292073 |
| wav2vec2 with newmm + language model | 12.583706 | 9.598305 | 3.276610 |
**Test with CommonVoice V7 Testset (same test by CV V7)**
| Model | WER by newmm (%) | WER by deepcut (%) | CER |
|-----------------------|------------------|--------------------|----------|
| AIResearch.in.th and PyThaiNLP | 13.936698 | 9.347462 | 2.804787 |
| wav2vec2 with deepcut | 12.776381 | 8.773006 | 2.628882 |
| wav2vec2 with newmm | 12.750596 | 8.672616 | 2.623341 |
| **wav2vec2 with deepcut + language model** | 9.940050 | 7.423313 | 2.344940 |
| wav2vec2 with newmm + language model | 9.559724 | 7.339654 | 2.277071 |
This is use same testset from [https://huggingface.co/airesearch/wav2vec2-large-xlsr-53-th](https://huggingface.co/airesearch/wav2vec2-large-xlsr-53-th).
**Links:**
- GitHub Dataset: [https://github.com/wannaphong/thai_commonvoice_dataset](https://github.com/wannaphong/thai_commonvoice_dataset)
- Technical report: [Thai Wav2Vec2.0 with CommonVoice V8](https://arxiv.org/abs/2208.04799)
## BibTeX entry and citation info
```
@misc{phatthiyaphaibun2022thai,
title={Thai Wav2Vec2.0 with CommonVoice V8},
author={Wannaphong Phatthiyaphaibun and Chompakorn Chaksangchaichot and Peerat Limkonchotiwat and Ekapol Chuangsuwanich and Sarana Nutanong},
year={2022},
eprint={2208.04799},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k | timm | 2023-05-11T00:49:45Z | 488 | 2 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-12k",
"arxiv:2204.01697",
"arxiv:2201.03545",
"arxiv:2111.09883",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-01-20T21:38:05Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-12k
---
# Model card for maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k
A timm specific MaxxViT-V2 (w/ a MLP Log-CPB (continuous log-coordinate relative position bias motivated by Swin-V2) image classification model. Pretrained in `timm` on ImageNet-12k (a 11821 class subset of full ImageNet-22k) and fine-tuned on ImageNet-1k by Ross Wightman.
ImageNet-12k pretraining and ImageNet-1k fine-tuning performed on 8x GPU [Lambda Labs](https://lambdalabs.com/) cloud instances..
### Model Variants in [maxxvit.py](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/maxxvit.py)
MaxxViT covers a number of related model architectures that share a common structure including:
- CoAtNet - Combining MBConv (depthwise-separable) convolutional blocks in early stages with self-attention transformer blocks in later stages.
- MaxViT - Uniform blocks across all stages, each containing a MBConv (depthwise-separable) convolution block followed by two self-attention blocks with different partitioning schemes (window followed by grid).
- CoAtNeXt - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in CoAtNet. All normalization layers are LayerNorm (no BatchNorm).
- MaxxViT - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in MaxViT. All normalization layers are LayerNorm (no BatchNorm).
- MaxxViT-V2 - A MaxxViT variation that removes the window block attention leaving only ConvNeXt blocks and grid attention w/ more width to compensate.
Aside from the major variants listed above, there are more subtle changes from model to model. Any model name with the string `rw` are `timm` specific configs w/ modelling adjustments made to favour PyTorch eager use. These were created while training initial reproductions of the models so there are variations.
All models with the string `tf` are models exactly matching Tensorflow based models by the original paper authors with weights ported to PyTorch. This covers a number of MaxViT models. The official CoAtNet models were never released.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 116.1
- GMACs: 24.2
- Activations (M): 62.8
- Image size: 224 x 224
- **Papers:**
- MaxViT: Multi-Axis Vision Transformer: https://arxiv.org/abs/2204.01697
- A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-12k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 128, 112, 112])
# torch.Size([1, 128, 56, 56])
# torch.Size([1, 256, 28, 28])
# torch.Size([1, 512, 14, 14])
# torch.Size([1, 1024, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1024, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
### By Top-1
|model |top1 |top5 |samples / sec |Params (M) |GMAC |Act (M)|
|------------------------------------------------------------------------------------------------------------------------|----:|----:|--------------:|--------------:|-----:|------:|
|[maxvit_xlarge_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_512.in21k_ft_in1k) |88.53|98.64| 21.76| 475.77|534.14|1413.22|
|[maxvit_xlarge_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_384.in21k_ft_in1k) |88.32|98.54| 42.53| 475.32|292.78| 668.76|
|[maxvit_base_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_512.in21k_ft_in1k) |88.20|98.53| 50.87| 119.88|138.02| 703.99|
|[maxvit_large_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_512.in21k_ft_in1k) |88.04|98.40| 36.42| 212.33|244.75| 942.15|
|[maxvit_large_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_384.in21k_ft_in1k) |87.98|98.56| 71.75| 212.03|132.55| 445.84|
|[maxvit_base_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_384.in21k_ft_in1k) |87.92|98.54| 104.71| 119.65| 73.80| 332.90|
|[maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.81|98.37| 106.55| 116.14| 70.97| 318.95|
|[maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.47|98.37| 149.49| 116.09| 72.98| 213.74|
|[coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k) |87.39|98.31| 160.80| 73.88| 47.69| 209.43|
|[maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.89|98.02| 375.86| 116.14| 23.15| 92.64|
|[maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.64|98.02| 501.03| 116.09| 24.20| 62.77|
|[maxvit_base_tf_512.in1k](https://huggingface.co/timm/maxvit_base_tf_512.in1k) |86.60|97.92| 50.75| 119.88|138.02| 703.99|
|[coatnet_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_2_rw_224.sw_in12k_ft_in1k) |86.57|97.89| 631.88| 73.87| 15.09| 49.22|
|[maxvit_large_tf_512.in1k](https://huggingface.co/timm/maxvit_large_tf_512.in1k) |86.52|97.88| 36.04| 212.33|244.75| 942.15|
|[coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k) |86.49|97.90| 620.58| 73.88| 15.18| 54.78|
|[maxvit_base_tf_384.in1k](https://huggingface.co/timm/maxvit_base_tf_384.in1k) |86.29|97.80| 101.09| 119.65| 73.80| 332.90|
|[maxvit_large_tf_384.in1k](https://huggingface.co/timm/maxvit_large_tf_384.in1k) |86.23|97.69| 70.56| 212.03|132.55| 445.84|
|[maxvit_small_tf_512.in1k](https://huggingface.co/timm/maxvit_small_tf_512.in1k) |86.10|97.76| 88.63| 69.13| 67.26| 383.77|
|[maxvit_tiny_tf_512.in1k](https://huggingface.co/timm/maxvit_tiny_tf_512.in1k) |85.67|97.58| 144.25| 31.05| 33.49| 257.59|
|[maxvit_small_tf_384.in1k](https://huggingface.co/timm/maxvit_small_tf_384.in1k) |85.54|97.46| 188.35| 69.02| 35.87| 183.65|
|[maxvit_tiny_tf_384.in1k](https://huggingface.co/timm/maxvit_tiny_tf_384.in1k) |85.11|97.38| 293.46| 30.98| 17.53| 123.42|
|[maxvit_large_tf_224.in1k](https://huggingface.co/timm/maxvit_large_tf_224.in1k) |84.93|96.97| 247.71| 211.79| 43.68| 127.35|
|[coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k) |84.90|96.96| 1025.45| 41.72| 8.11| 40.13|
|[maxvit_base_tf_224.in1k](https://huggingface.co/timm/maxvit_base_tf_224.in1k) |84.85|96.99| 358.25| 119.47| 24.04| 95.01|
|[maxxvit_rmlp_small_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_small_rw_256.sw_in1k) |84.63|97.06| 575.53| 66.01| 14.67| 58.38|
|[coatnet_rmlp_2_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in1k) |84.61|96.74| 625.81| 73.88| 15.18| 54.78|
|[maxvit_rmlp_small_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_small_rw_224.sw_in1k) |84.49|96.76| 693.82| 64.90| 10.75| 49.30|
|[maxvit_small_tf_224.in1k](https://huggingface.co/timm/maxvit_small_tf_224.in1k) |84.43|96.83| 647.96| 68.93| 11.66| 53.17|
|[maxvit_rmlp_tiny_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_tiny_rw_256.sw_in1k) |84.23|96.78| 807.21| 29.15| 6.77| 46.92|
|[coatnet_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_1_rw_224.sw_in1k) |83.62|96.38| 989.59| 41.72| 8.04| 34.60|
|[maxvit_tiny_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_tiny_rw_224.sw_in1k) |83.50|96.50| 1100.53| 29.06| 5.11| 33.11|
|[maxvit_tiny_tf_224.in1k](https://huggingface.co/timm/maxvit_tiny_tf_224.in1k) |83.41|96.59| 1004.94| 30.92| 5.60| 35.78|
|[coatnet_rmlp_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw_224.sw_in1k) |83.36|96.45| 1093.03| 41.69| 7.85| 35.47|
|[maxxvitv2_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvitv2_nano_rw_256.sw_in1k) |83.11|96.33| 1276.88| 23.70| 6.26| 23.05|
|[maxxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_nano_rw_256.sw_in1k) |83.03|96.34| 1341.24| 16.78| 4.37| 26.05|
|[maxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_nano_rw_256.sw_in1k) |82.96|96.26| 1283.24| 15.50| 4.47| 31.92|
|[maxvit_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_nano_rw_256.sw_in1k) |82.93|96.23| 1218.17| 15.45| 4.46| 30.28|
|[coatnet_bn_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_bn_0_rw_224.sw_in1k) |82.39|96.19| 1600.14| 27.44| 4.67| 22.04|
|[coatnet_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_0_rw_224.sw_in1k) |82.39|95.84| 1831.21| 27.44| 4.43| 18.73|
|[coatnet_rmlp_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_nano_rw_224.sw_in1k) |82.05|95.87| 2109.09| 15.15| 2.62| 20.34|
|[coatnext_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnext_nano_rw_224.sw_in1k) |81.95|95.92| 2525.52| 14.70| 2.47| 12.80|
|[coatnet_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_nano_rw_224.sw_in1k) |81.70|95.64| 2344.52| 15.14| 2.41| 15.41|
|[maxvit_rmlp_pico_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_pico_rw_256.sw_in1k) |80.53|95.21| 1594.71| 7.52| 1.85| 24.86|
### By Throughput (samples / sec)
|model |top1 |top5 |samples / sec |Params (M) |GMAC |Act (M)|
|------------------------------------------------------------------------------------------------------------------------|----:|----:|--------------:|--------------:|-----:|------:|
|[coatnext_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnext_nano_rw_224.sw_in1k) |81.95|95.92| 2525.52| 14.70| 2.47| 12.80|
|[coatnet_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_nano_rw_224.sw_in1k) |81.70|95.64| 2344.52| 15.14| 2.41| 15.41|
|[coatnet_rmlp_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_nano_rw_224.sw_in1k) |82.05|95.87| 2109.09| 15.15| 2.62| 20.34|
|[coatnet_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_0_rw_224.sw_in1k) |82.39|95.84| 1831.21| 27.44| 4.43| 18.73|
|[coatnet_bn_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_bn_0_rw_224.sw_in1k) |82.39|96.19| 1600.14| 27.44| 4.67| 22.04|
|[maxvit_rmlp_pico_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_pico_rw_256.sw_in1k) |80.53|95.21| 1594.71| 7.52| 1.85| 24.86|
|[maxxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_nano_rw_256.sw_in1k) |83.03|96.34| 1341.24| 16.78| 4.37| 26.05|
|[maxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_nano_rw_256.sw_in1k) |82.96|96.26| 1283.24| 15.50| 4.47| 31.92|
|[maxxvitv2_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvitv2_nano_rw_256.sw_in1k) |83.11|96.33| 1276.88| 23.70| 6.26| 23.05|
|[maxvit_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_nano_rw_256.sw_in1k) |82.93|96.23| 1218.17| 15.45| 4.46| 30.28|
|[maxvit_tiny_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_tiny_rw_224.sw_in1k) |83.50|96.50| 1100.53| 29.06| 5.11| 33.11|
|[coatnet_rmlp_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw_224.sw_in1k) |83.36|96.45| 1093.03| 41.69| 7.85| 35.47|
|[coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k) |84.90|96.96| 1025.45| 41.72| 8.11| 40.13|
|[maxvit_tiny_tf_224.in1k](https://huggingface.co/timm/maxvit_tiny_tf_224.in1k) |83.41|96.59| 1004.94| 30.92| 5.60| 35.78|
|[coatnet_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_1_rw_224.sw_in1k) |83.62|96.38| 989.59| 41.72| 8.04| 34.60|
|[maxvit_rmlp_tiny_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_tiny_rw_256.sw_in1k) |84.23|96.78| 807.21| 29.15| 6.77| 46.92|
|[maxvit_rmlp_small_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_small_rw_224.sw_in1k) |84.49|96.76| 693.82| 64.90| 10.75| 49.30|
|[maxvit_small_tf_224.in1k](https://huggingface.co/timm/maxvit_small_tf_224.in1k) |84.43|96.83| 647.96| 68.93| 11.66| 53.17|
|[coatnet_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_2_rw_224.sw_in12k_ft_in1k) |86.57|97.89| 631.88| 73.87| 15.09| 49.22|
|[coatnet_rmlp_2_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in1k) |84.61|96.74| 625.81| 73.88| 15.18| 54.78|
|[coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k) |86.49|97.90| 620.58| 73.88| 15.18| 54.78|
|[maxxvit_rmlp_small_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_small_rw_256.sw_in1k) |84.63|97.06| 575.53| 66.01| 14.67| 58.38|
|[maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.64|98.02| 501.03| 116.09| 24.20| 62.77|
|[maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.89|98.02| 375.86| 116.14| 23.15| 92.64|
|[maxvit_base_tf_224.in1k](https://huggingface.co/timm/maxvit_base_tf_224.in1k) |84.85|96.99| 358.25| 119.47| 24.04| 95.01|
|[maxvit_tiny_tf_384.in1k](https://huggingface.co/timm/maxvit_tiny_tf_384.in1k) |85.11|97.38| 293.46| 30.98| 17.53| 123.42|
|[maxvit_large_tf_224.in1k](https://huggingface.co/timm/maxvit_large_tf_224.in1k) |84.93|96.97| 247.71| 211.79| 43.68| 127.35|
|[maxvit_small_tf_384.in1k](https://huggingface.co/timm/maxvit_small_tf_384.in1k) |85.54|97.46| 188.35| 69.02| 35.87| 183.65|
|[coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k) |87.39|98.31| 160.80| 73.88| 47.69| 209.43|
|[maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.47|98.37| 149.49| 116.09| 72.98| 213.74|
|[maxvit_tiny_tf_512.in1k](https://huggingface.co/timm/maxvit_tiny_tf_512.in1k) |85.67|97.58| 144.25| 31.05| 33.49| 257.59|
|[maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.81|98.37| 106.55| 116.14| 70.97| 318.95|
|[maxvit_base_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_384.in21k_ft_in1k) |87.92|98.54| 104.71| 119.65| 73.80| 332.90|
|[maxvit_base_tf_384.in1k](https://huggingface.co/timm/maxvit_base_tf_384.in1k) |86.29|97.80| 101.09| 119.65| 73.80| 332.90|
|[maxvit_small_tf_512.in1k](https://huggingface.co/timm/maxvit_small_tf_512.in1k) |86.10|97.76| 88.63| 69.13| 67.26| 383.77|
|[maxvit_large_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_384.in21k_ft_in1k) |87.98|98.56| 71.75| 212.03|132.55| 445.84|
|[maxvit_large_tf_384.in1k](https://huggingface.co/timm/maxvit_large_tf_384.in1k) |86.23|97.69| 70.56| 212.03|132.55| 445.84|
|[maxvit_base_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_512.in21k_ft_in1k) |88.20|98.53| 50.87| 119.88|138.02| 703.99|
|[maxvit_base_tf_512.in1k](https://huggingface.co/timm/maxvit_base_tf_512.in1k) |86.60|97.92| 50.75| 119.88|138.02| 703.99|
|[maxvit_xlarge_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_384.in21k_ft_in1k) |88.32|98.54| 42.53| 475.32|292.78| 668.76|
|[maxvit_large_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_512.in21k_ft_in1k) |88.04|98.40| 36.42| 212.33|244.75| 942.15|
|[maxvit_large_tf_512.in1k](https://huggingface.co/timm/maxvit_large_tf_512.in1k) |86.52|97.88| 36.04| 212.33|244.75| 942.15|
|[maxvit_xlarge_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_512.in21k_ft_in1k) |88.53|98.64| 21.76| 475.77|534.14|1413.22|
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{tu2022maxvit,
title={MaxViT: Multi-Axis Vision Transformer},
author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
journal={ECCV},
year={2022},
}
```
```bibtex
@article{dai2021coatnet,
title={CoAtNet: Marrying Convolution and Attention for All Data Sizes},
author={Dai, Zihang and Liu, Hanxiao and Le, Quoc V and Tan, Mingxing},
journal={arXiv preprint arXiv:2106.04803},
year={2021}
}
```
|
tasinhoque/roberta-large-go-emotions | tasinhoque | 2023-03-20T09:05:51Z | 488 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:go_emotions",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-02-22T08:03:08Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- go_emotions
metrics:
- f1
model-index:
- name: roberta-large-goemotions
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: go_emotions
type: multilabel_classification
config: simplified
split: test
args: simplified
metrics:
- name: F1
type: f1
value: 0.5102
- task:
name: Text Classification
type: text-classification
dataset:
name: go_emotions
type: multilabel_classification
config: simplified
split: validation
args: simplified
metrics:
- name: F1
type: f1
value: 0.5227
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Text Classification GoEmotions
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset.
It achieves the following results on the test set (with a threshold of 0.15):
- Accuracy: 0.4175
- Precision: 0.4934
- Recall: 0.5621
- F1: 0.5102
## Code
Code for training this model can be found [here](https://github.com/tasinhoque/go-emotions-text-classification).
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Validation Loss | Accuracy | Precision | Recall | F1 |
| :-----------: | :---: | :-------------: | :------: | :-------: | :------: | :------: |
| No log | 1.0 | 0.088978 | 0.404349 | 0.480763 | 0.456827 | 0.444685 |
| 0.10620 | 2.0 | 0.082806 | 0.411353 | 0.460896 | 0.536386 | 0.486819 |
| 0.10620 | 3.0 | 0.081338 | 0.420199 | 0.519828 | 0.561297 | 0.522716 |
### Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0
- Datasets 2.1.0
- Tokenizers 0.12.1
|
hogiahien/Anything-V3-X-edited | hogiahien | 2023-07-31T10:55:58Z | 488 | 4 | diffusers | [
"diffusers",
"Anything V3",
"stable diffusion",
"stable diffusion diffusers",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-31T10:55:58Z | ---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anything V3
- stable diffusion
- diffusers
- stable diffusion diffusers
duplicated_from: iZELX1/Anything-V3-X
---
|
timm/repvgg_a0.rvgg_in1k | timm | 2023-08-23T19:28:20Z | 488 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2101.03697",
"license:mit",
"region:us"
]
| image-classification | 2023-08-23T19:28:13Z | ---
tags:
- image-classification
- timm
library_name: timm
license: mit
datasets:
- imagenet-1k
---
# Model card for repvgg_a0
A RepVGG image classification model. Trained on ImageNet-1k by paper authors.
This model architecture is implemented using `timm`'s flexible [BYOBNet (Bring-Your-Own-Blocks Network)](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/byobnet.py).
BYOBNet allows configuration of:
* block / stage layout
* stem layout
* output stride (dilation)
* activation and norm layers
* channel and spatial / self-attention layers
...and also includes `timm` features common to many other architectures, including:
* stochastic depth
* gradient checkpointing
* layer-wise LR decay
* per-stage feature extraction
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 9.1
- GMACs: 1.5
- Activations (M): 3.6
- Image size: 224 x 224
- **Papers:**
- RepVGG: Making VGG-style ConvNets Great Again: https://arxiv.org/abs/2101.03697
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/DingXiaoH/RepVGG
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('repvgg_a0', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'repvgg_a0',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 48, 112, 112])
# torch.Size([1, 48, 56, 56])
# torch.Size([1, 96, 28, 28])
# torch.Size([1, 192, 14, 14])
# torch.Size([1, 1280, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'repvgg_a0',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@inproceedings{ding2021repvgg,
title={Repvgg: Making vgg-style convnets great again},
author={Ding, Xiaohan and Zhang, Xiangyu and Ma, Ningning and Han, Jungong and Ding, Guiguang and Sun, Jian},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={13733--13742},
year={2021}
}
```
|
sophosympatheia/Midnight-Miqu-103B-v1.0 | sophosympatheia | 2024-03-07T05:37:02Z | 488 | 6 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-03-02T03:16:33Z | ---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
license: other
---
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/Tn9MBg6.png" alt="MidnightMiqu" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
### Overview
This is a 103B frankenmerge of [sophosympatheia/Midnight-Miqu-70B-v1.0](https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.0) with itself. Please see that model card for details and usage instructions.
This model is based on Miqu so it's capable of 32K context.
### Quantizations
* GGUF
* [Dracones/Midnight-Miqu-103B-v1.0-GGUF](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0-GGUF)
* EXL2
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_2.4bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_2.4bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_3.0bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_3.0bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_3.75bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_3.75bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_4.0bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_4.0bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_4.25bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_4.25bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_4.5bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_4.5bpw)
* [Dracones/Midnight-Miqu-103B-v1.0_exl2_5.0bpw](https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_5.0bpw)
* If you don't see something you're looking for, [try searching Hugging Face](https://huggingface.co/models?search=midnight-miqu-103b). There may be newer quants available than what I've documented here.
### Licence and usage restrictions
<font color="red">152334H/miqu-1-70b-sf was based on a leaked version of one of Mistral's models.</font>
All miqu-derived models, including this merge, are **only suitable for personal use.** Mistral has been cool about it so far, but you should be aware that by downloading this merge you are assuming whatever legal risk is iherent in acquiring and using a model based on leaked weights.
This merge comes with no warranties or guarantees of any kind, but you probably already knew that.
I am not a lawyer and I do not profess to know what we have gotten ourselves into here. You should consult with a lawyer before using any Hugging Face model beyond private use... but definitely don't use this one for that!
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* [sophosympatheia/Midnight-Miqu-70B-v1.0](https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: /home/llm/mergequant/models/midnight-miqu-70b
layer_range: [0, 40] # 40
- sources:
- model: /home/llm/mergequant/models/midnight-miqu-70b
layer_range: [20, 60] # 40
- sources:
- model: /home/llm/mergequant/models/midnight-miqu-70b
layer_range: [40, 80] # 40
merge_method: passthrough
dtype: float16
``` |
giantdev/5DU28YtRGWLR2zswb66w8yZU8eH63bEcU59LM2Lbys8uPX8s_vgg | giantdev | 2024-03-24T10:10:32Z | 488 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-03-09T03:32:16Z | Entry not found |
mradermacher/Uncensored-Jordan-33B-GGUF | mradermacher | 2024-05-06T05:37:25Z | 488 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:ajibawa-2023/Uncensored-Jordan-33B",
"license:cc-by-nc-nd-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-29T13:09:16Z | ---
base_model: ajibawa-2023/Uncensored-Jordan-33B
language:
- en
library_name: transformers
license: cc-by-nc-nd-4.0
quantized_by: mradermacher
---
## About
static quants of https://huggingface.co/ajibawa-2023/Uncensored-Jordan-33B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q2_K.gguf) | Q2_K | 12.4 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.IQ3_XS.gguf) | IQ3_XS | 13.7 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.IQ3_S.gguf) | IQ3_S | 14.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q3_K_S.gguf) | Q3_K_S | 14.4 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.IQ3_M.gguf) | IQ3_M | 15.2 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q3_K_M.gguf) | Q3_K_M | 16.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q3_K_L.gguf) | Q3_K_L | 17.6 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.IQ4_XS.gguf) | IQ4_XS | 17.8 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q4_0.gguf) | Q4_0 | 18.7 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.IQ4_NL.gguf) | IQ4_NL | 18.8 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q4_K_S.gguf) | Q4_K_S | 18.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q4_K_M.gguf) | Q4_K_M | 20.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q5_K_S.gguf) | Q5_K_S | 22.7 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q5_K_M.gguf) | Q5_K_M | 23.4 | |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q6_K.gguf) | Q6_K | 27.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF/resolve/main/Uncensored-Jordan-33B.Q8_0.gguf) | Q8_0 | 34.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
KunpengSong/MoMA_llava_7b | KunpengSong | 2024-06-06T09:17:02Z | 488 | 11 | transformers | [
"transformers",
"pytorch",
"llava",
"text-generation",
"arxiv:2404.05674",
"autotrain_compatible",
"region:us"
]
| text-generation | 2024-04-19T19:06:34Z | ---
inference: false
---
<br>
<br>
# MoMA Model Card
## Model details
**Model type:**
MoMA is an open-source image personalization model. It has new attention layers and a multi-modal large language model fine-tuned from LLaVA-7B.
**Paper or resources for more information:**
+ Project page: https://moma-adapter.github.io/
+ Github: https://github.com/bytedance/MoMA/tree/main
+ Paper: https://arxiv.org/abs/2404.05674
+ Online Demo: https://huggingface.co/spaces/yizhezhu/MoMA_zeroGPU
**Where to send questions or comments about the model:**
https://github.com/bytedance/MoMA/tree/main
## Intended use
**Primary intended uses:**
The primary use is research on personalized image generation tasks.
**Primary intended users:**
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
philipp-zettl/t5-small-long-qa | philipp-zettl | 2024-06-09T19:53:33Z | 488 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"en",
"dataset:philipp-zettl/long-qa",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2024-06-06T12:37:59Z | ---
license: mit
datasets:
- philipp-zettl/long-qa
language:
- en
library_name: transformers
pipeline_tag: text2text-generation
widget:
- text: "question: How many models are in the hub? context: The Hugging Face Hub is a
platform with over 350k models, 75k datasets, and 150k demo apps (Spaces),
all open source and publicly available, in an online platform where people
can easily collaborate and build ML together. The Hub works as a central
place where anyone can explore, experiment, collaborate, and build
technology with Machine Learning. Are you ready to join the path towards
open source Machine Learning? 🤗"
example_title: 🤗 Hub
- text: "question: What type of data is available? context:
🤗 Datasets is a library for easily accessing and sharing datasets for Audio,
Computer Vision, and Natural Language Processing (NLP) tasks. Load a dataset
in a single line of code, and use our powerful data processing methods to
quickly get your dataset ready for training in a deep learning model. Backed
by the Apache Arrow format, process large datasets with zero-copy reads without
any memory constraints for optimal speed and efficiency. We also feature a
deep integration with the Hugging Face Hub, allowing you to easily load
and share a dataset with the wider machine learning community. Find your
dataset today on the Hugging Face Hub, and take an in-depth look inside of
it with the live viewer."
example_title: 🤗 datasets
---
# Model Card for t5-small-long-qa
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model was trained to generate answers for questions out of a given context.
- **Developed by:** [philipp-zettl](https://huggingface.co/philipp-zettl)
- **Model type:** Transformer (T5)
- **Language(s) (NLP):** English
- **License:** M.I.T
- **Finetuned from model [optional]:** [google/flan-t5-small](https://huggingface.co/google/flan-t5-small)
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
Fine-tune of the amazing [google/flan-t5-small](https://huggingface.co/google/flan-t5-small)
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
It's intended to use the model to answers for questions from given context.
The context should not exceed the model's _context_ length.
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
No bias evaluation was performed on this model.
## How to Get Started with the Model
Use the code below to get started with the model.
```python
context = "This is a long text based of multiple concatenated paragraphs."
question = "My question about something mentioned inside the context."
model_inputs = tokenizer([f"question: {question} context: {context}"], max_length=512, padding=True, truncation=True)
input_ids = torch.tensor(model_inputs['input_ids']).to(device)
attention_mask = torch.tensor(model_inputs['attention_mask']).to(device)
with torch.no_grad():
sample_output = model.generate(input_ids[:1], max_length=85)
sample_output_text = tokenizer.decode(sample_output[0], skip_special_tokens=True)
input_text = tokenizer.decode(input_ids[0], skip_special_tokens=True)
print(f"Sample Input:\n \"{input_text}\"\n\n")
print(f"Model Output: \"{sample_output_text}\"")
```
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
This model was trained on [philipp-zettl/long-qa](https://huggingface.co/datasets/philipp-zettl/long-qa).
A synthetic data set created from [philipp-zettl/qg-tidyqa_squad2](https://huggingface.co/datasets/philipp-zettl/qg-tydiqa_squad2) using [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct).
The data set was created by prompting Phi-3 using the prompt template
```python
msg = f"""
Answer the following question using the content provided in the context.
Do not answer questions where the answer isn't inside the context.
Question: {sample['question']}
Context: {sample['context']}
"""
```
After generating synthetic answers, the data set was manually corrected and validated to ensure high quality as well as consistent longer answers than the original data sets.
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
Below you can find the full training pipeline used to achieve this fine-tune.
```python
import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
# Base model (e.g., T5-large)
# https://huggingface.co/collections/google/flan-t5-release-65005c39e3201fff885e22fb
model_name = 'google/flan-t5-small'
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Move only the student model to GPU if available
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)
```
Load dataset
```python
from datasets import load_dataset
# Load dataset
ds = load_dataset('philipp-zettl/long-qa')
# Split the dataset into training and validation
train_dataset = ds['train']
validation_dataset = ds['test']
```
Preprocessing: tokenize inputs and labels for faster training cycles, i.e. no need for tokenization during training anymore
```python
def preprocess_batch(batch, tokenizer, max_input_length=512, max_output_length=128):
questions = batch['question']
contexts = batch['context']
answers = batch['answer']
inputs = [f"question: {q} context: {c}" for q, c in zip(questions, contexts)]
model_inputs = tokenizer(inputs, max_length=max_input_length, padding=True, truncation=True)
labels = tokenizer(answers, max_length=max_output_length, padding=True, truncation=True)
model_inputs['labels'] = labels['input_ids']
return model_inputs
# Tokenize the dataset
train_dataset = train_dataset.map(lambda batch: preprocess_batch(batch, tokenizer), batched=True)
validation_dataset = validation_dataset.map(lambda batch: preprocess_batch(batch, tokenizer), batched=True)
# Set format for PyTorch
train_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
validation_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
```
The train loop
```python
from tqdm import tqdm
from transformers import AdamW, DataCollatorForSeq2Seq
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
torch.cuda.empty_cache()
model_name = 'google/flan-t5-small'
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Move only the student model to GPU if available
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)
# Training parameters
epochs = 50
learning_rate = 3e-5
temperature = 2.0
batch_size = 8
optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
# Create a data collator for padding and batching
data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=model)
# Create DataLoaders with the data collator
train_dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, collate_fn=data_collator)
validation_dataloader = DataLoader(validation_dataset, batch_size=batch_size, collate_fn=data_collator)
writer = SummaryWriter(comment='t5-small-long-qa')
# Store losses and learning rates
train_losses = []
val_losses = []
learning_rates = []
print("Starting training...")
# Training loop
for epoch in range(epochs):
model.train()
total_loss = 0
print(f"Epoch {epoch+1}/{epochs}")
progress_bar = tqdm(train_dataloader, desc="Training", leave=False)
for step, batch in enumerate(progress_bar):
# Move student inputs to GPU
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
labels = batch['labels'].to(device)
# Teacher forward pass on CPU
outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)
logits = outputs.logits
# Calculate losses
loss = outputs.loss # Cross-entropy loss
writer.add_scalar("Loss/train", loss, epoch * len(train_dataloader) + step)
# Backpropagation
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_loss += loss.item()
# Verbose logging
if step % len(train_dataloader)//10 == 1 or step == len(train_dataloader) - 1:
progress_bar.set_postfix({
'step': step,
'loss': loss.item(),
})
# Generate a sample output from the student model
model.eval()
with torch.no_grad():
sample_output = model.generate(input_ids[:1], max_length=50)
sample_output_text = tokenizer.decode(sample_output[0], skip_special_tokens=True)
input_text = tokenizer.decode(input_ids[0], skip_special_tokens=True)
writer.add_text(f"Sample Input", input_text, step)
writer.add_text(f"Sample Output", sample_output_text, step)
model.train()
avg_train_loss = total_loss / len(train_dataloader)
train_losses.append(avg_train_loss)
learning_rates.append(optimizer.param_groups[0]['lr'])
# Validation step
model.eval()
total_val_loss = 0
with torch.no_grad():
for batch in validation_dataloader:
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
labels = batch['labels'].to(device)
outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)
val_loss = outputs.loss
total_val_loss += val_loss.item()
avg_val_loss = total_val_loss / len(validation_dataloader)
val_losses.append(avg_val_loss)
writer.add_scalar("AVG Loss/train", avg_train_loss, epoch)
writer.add_scalar("AVG Loss/val", avg_val_loss, epoch)
print(f"Epoch {epoch+1} completed. Avg Train Loss: {avg_train_loss:.4f}, Avg Val Loss: {avg_val_loss:.4f}")
print("Training complete.")
writer.close()
``` |
OpenLLMAI/Llama-3-8b-sft-mixture | OpenLLMAI | 2024-06-14T11:21:59Z | 488 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2405.07863",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-14T09:31:01Z | ---
library_name: transformers
tags: []
---
>Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT
>
>We fixed the `generation_config.json`.
This is the SFT checkpoint used for the project [Online-RLHF](https://github.com/RLHFlow/Online-RLHF). Also, check the [technical report here](https://arxiv.org/pdf/2405.07863).
The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on a mixture of diverse open-source high-quality data for 1 epoch with detailed parameters in the report. It has not been trained by RLHF and can serve as a good starting point for the RLHF research.
The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract. |
blacksnow666/Qwen2-0.5B-8192-fpf | blacksnow666 | 2024-06-23T17:34:49Z | 488 | 1 | null | [
"gguf",
"ms",
"region:us"
]
| null | 2024-06-23T17:12:57Z | ---
language:
- ms
--- |
josu/roberta-pt-br | josu | 2021-12-12T20:15:09Z | 487 | 7 | transformers | [
"transformers",
"pytorch",
"roberta",
"fill-mask",
"portuguese",
"brazil",
"pt_BR",
"pt",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2022-03-02T23:29:05Z | ---
language: pt
tags:
- portuguese
- brazil
- pt_BR
widget:
- text: Brasilia é a capital do <mask>
---
``` python
from transformers import pipeline
unmasker = pipeline('fill-mask', model='josu/roberta-pt-br')
text = 'Brasilia é a capital do <mask>'
[{'sequence': 'Brasilia é a capital do Brasil',
'score': 0.24386335909366608,
'token': 707,
'token_str': ' Brasil'},
{'sequence': 'Brasilia é a capital do estado',
'score': 0.2320091277360916,
'token': 1031,
'token_str': ' estado'},
{'sequence': 'Brasilia é a capital do país',
'score': 0.0665697380900383,
'token': 998,
'token_str': ' país'},
{'sequence': 'Brasilia é a capital do Rio',
'score': 0.05980581417679787,
'token': 993,
'token_str': ' Rio'},
{'sequence': 'Brasilia é a capital do capital',
'score': 0.058453518897295,
'token': 2027,
'token_str': ' capital'}]
```
|
intfloat/simlm-base-msmarco | intfloat | 2023-05-22T09:34:39Z | 487 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2022-08-11T05:24:45Z | ---
license: mit
--- |
timm/tf_efficientnet_es.in1k | timm | 2023-04-27T21:29:12Z | 487 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2003.02838",
"arxiv:1905.11946",
"license:apache-2.0",
"region:us"
]
| image-classification | 2022-12-13T00:08:50Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for tf_efficientnet_es.in1k
A EfficientNet-EdgeTPU image classification model. Trained on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 5.4
- GMACs: 1.8
- Activations (M): 8.7
- Image size: 224 x 224
- **Papers:**
- Accelerator-aware Neural Network Design using AutoML: https://arxiv.org/abs/2003.02838
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tf_efficientnet_es.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnet_es.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 24, 112, 112])
# torch.Size([1, 32, 56, 56])
# torch.Size([1, 48, 28, 28])
# torch.Size([1, 144, 14, 14])
# torch.Size([1, 192, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnet_es.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{gupta2020accelerator,
title={Accelerator-aware neural network design using automl},
author={Gupta, Suyog and Akin, Berkin},
journal={arXiv preprint arXiv:2003.02838},
year={2020}
}
```
```bibtex
@inproceedings{tan2019efficientnet,
title={Efficientnet: Rethinking model scaling for convolutional neural networks},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={6105--6114},
year={2019},
organization={PMLR}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
timm/vit_base_patch16_224_miil.in21k_ft_in1k | timm | 2023-05-06T00:01:05Z | 487 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-21k-p",
"arxiv:2104.10972",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
]
| image-classification | 2022-12-22T07:28:49Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-21k-p
---
# Model card for vit_base_patch16_224_miil.in21k_ft_in1k
A Vision Transformer (ViT) image classification model. Petrained on ImageNet-21k-P and fine-tuned on ImageNet-1k by Alibaba MIIL.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 86.5
- GMACs: 16.9
- Activations (M): 16.5
- Image size: 224 x 224
- **Papers:**
- ImageNet-21K Pretraining for the Masses: https://arxiv.org/abs/2104.10972
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-21k-P
- **Original:** https://github.com/Alibaba-MIIL/ImageNet21K
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_base_patch16_224_miil.in21k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch16_224_miil.in21k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{ridnik2021imagenet21k,
title={ImageNet-21K Pretraining for the Masses},
author={Tal Ridnik and Emanuel Ben-Baruch and Asaf Noy and Lihi Zelnik-Manor},
year={2021},
eprint={2104.10972},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k | timm | 2024-02-10T23:41:18Z | 487 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1805.00932",
"arxiv:1611.05431",
"arxiv:1512.03385",
"license:cc-by-nc-4.0",
"region:us"
]
| image-classification | 2023-04-05T19:06:41Z | ---
license: cc-by-nc-4.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnext101_32x8d.fb_wsl_ig1b_ft_in1k
A ResNeXt-B image classification model.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
* grouped 3x3 bottleneck convolutions
Pretrained on Instagram-1B hashtags dataset using weakly-supervised learning and fine-tuned on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.8
- GMACs: 16.5
- Activations (M): 31.2
- Image size: 224 x 224
- **Papers:**
- Exploring the Limits of Weakly Supervised Pretraining: https://arxiv.org/abs/1805.00932
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- **Original:** https://github.com/facebookresearch/WSL-Images
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resnext101_32x8d.fb_wsl_ig1b_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnext101_32x8d.fb_wsl_ig1b_ft_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnext101_32x8d.fb_wsl_ig1b_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@inproceedings{wslimageseccv2018,
title={Exploring the Limits of Weakly Supervised Pretraining},
author={Dhruv Kumar Mahajan and Ross B. Girshick and Vignesh Ramanathan and Kaiming He and Manohar Paluri and Yixuan Li and Ashwin Bharambe and Laurens van der Maaten},
booktitle={ECCV},
year={2018}
}
```
```bibtex
@article{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
PavanNeerudu/t5-base-finetuned-qnli | PavanNeerudu | 2023-04-09T11:26:44Z | 487 | 0 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"en",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2023-04-09T11:21:44Z | ---
language:
- en
license: apache-2.0
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base-finetuned-qnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QNLI
type: glue
args: qnli
metrics:
- name: Accuracy
type: accuracy
value: 0.9123
---
# T5-base-finetuned-qnli
<!-- Provide a quick summary of what the model is/does. -->
This model is T5 fine-tuned on GLUE QNLI dataset. It acheives the following results on the validation set
- Accuracy: 0.9123
## Model Details
T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.
## Training procedure
### Tokenization
Since, T5 is a text-to-text model, the labels of the dataset are converted as follows:
For each example, a sentence as been formed as **"qnli question: " + qnli_question + "sentence: " + qnli_sentence** and fed to the tokenizer to get the **input_ids** and **attention_mask**.
For each label, label is choosen as **"equivalent"** if label is 1, else label is **"not_equivalent"** and tokenized to get **input_ids** and **attention_mask** .
During training, these inputs_ids having **pad** token are replaced with -100 so that loss is not calculated for them. Then these input ids are given as labels, and above attention_mask of labels
is given as decoder attention mask.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-4
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: epsilon=1e-08
- num_epochs: 3.0
### Training results
|Epoch | Training Loss | Validation Accuracy |
|:----:|:-------------:|:-------------------:|
| 1 | 0.0571 | 0.8973 |
| 2 | 0.0329 | 0.9068 |
| 3 | 0.0133 | 0.9123 |
|
Andyrasika/dreamviewer-sdxl-1.0 | Andyrasika | 2023-09-03T12:53:05Z | 487 | 6 | diffusers | [
"diffusers",
"safetensors",
"diffusion",
"text-to-image",
"en",
"arxiv:2307.01952",
"arxiv:2211.01324",
"arxiv:2108.01073",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2023-08-15T12:10:24Z | ---
license: creativeml-openrail-m
language:
- en
tags:
- diffusion
pipeline_tag: text-to-image
---
SDXL_v1.0-Dreamviewer
[SDXL](https://arxiv.org/abs/2307.01952) consists of an [ensemble of experts](https://arxiv.org/abs/2211.01324) pipeline for latent diffusion:
In a first step, the base model is used to generate (noisy) latents,
which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps.
Note that the base model can be used as a standalone module.
Alternatively, we can use a two-stage pipeline as follows:
First, the base model is used to generate latents of the desired output size.
In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img")
to the latents generated in the first step, using the same prompt. This technique is slightly slower than the first one, as it requires more function evaluations.
Source code is available at https://github.com/Stability-AI/generative-models .
```
import torch
from diffusers import StableDiffusionXLPipeline, AutoencoderKL
import gc,cv2,os
from PIL import Image
import requests
from io import BytesIO
from IPython.display import display
import matplotlib.pyplot as plt
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLPipeline.from_pretrained(
"Andyrasika/dreamshaper_sdxl1_diffusion ", torch_dtype=torch.float16, variant="fp16",vae=vae
)
pipe.enable_xformers_memory_efficient_attention()
pipe.to("cuda")
prompt = '8k intricate, highly detailed, digital photography, best quality, masterpiece, a (full body "shot) photo of A warrior man that lived with dragons his whole life is now leading them to battle. torn clothes exposing parts of her body, scratch marks, epic, hyperrealistic, hyperrealism, 8k, cinematic lighting, greg rutkowski, wlop'
negative_prompt='(deformed iris, deformed pupils), text, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, (extra fingers), (mutated hands), poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, (fused fingers), (too many fingers), long neck, camera'
image = pipe(prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=9.0,
num_inference_steps=50).images[0]
gc.collect()
torch.cuda.empty_cache()
```
 |
levimorin/5GYgq7jAvrBiUbmyZDvEmryZXiRaQxBnXGb6LZ3Bm23at6Gq_vgg | levimorin | 2024-03-08T19:57:17Z | 487 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-03-03T04:59:28Z | Entry not found |
abideen/Bitnet-Llama-70M | abideen | 2024-04-04T15:25:20Z | 487 | 21 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"bitnet",
"open-source",
"cosmopedia",
"en",
"dataset:HuggingFaceTB/cosmopedia",
"arxiv:2402.17764",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-03T10:04:14Z | ---
license: apache-2.0
datasets:
- HuggingFaceTB/cosmopedia
language:
- en
library_name: transformers
tags:
- bitnet
- llama
- open-source
- cosmopedia
---
# Bitnet-LLama-70M
Bitnet-LLama-70M is a 70M parameter model trained using the method described in [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://arxiv.org/abs/2402.17764).
It was trained on the subset of the [HuggingFaceTB/cosmopedia](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) dataset. This is just a small experiment to try out BitNet. Bitnet-LLama-70M was trained for 2 epochs on 1xA100.
This model is just an experiment and you might not get good results while chatting with it due to smaller model size and less training.
Wandb training report is as follows:
# Sample inference code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load a pretrained BitNet model
model = "abideen/Bitnet-Llama-70M"
tokenizer = AutoTokenizer.from_pretrained(model)
model = AutoModelForCausalLM.from_pretrained(model)
def convert_to_bitnet(model, copy_weights):
for name, module in model.named_modules():
# Replace linear layers with BitNet
if isinstance(module, LlamaSdpaAttention) or isinstance(module, LlamaMLP):
for child_name, child_module in module.named_children():
if isinstance(child_module, nn.Linear):
bitlinear = BitLinear(child_module.in_features, child_module.out_features, child_module.bias is not None).to(device="cuda:0")
if copy_weights:
bitlinear.weight = child_module.weight
if child_module.bias is not None:
bitlinear.bias = child_module.bias
setattr(module, child_name, bitlinear)
# Remove redundant input_layernorms
elif isinstance(module, LlamaDecoderLayer):
for child_name, child_module in module.named_children():
if isinstance(child_module, LlamaRMSNorm) and child_name == "input_layernorm":
setattr(module, child_name, nn.Identity().to(device="cuda:0"))
convert_to_bitnet(model, copy_weights=True)
model.to(device="cuda:0")
prompt = "What is Machine Learning?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
generate_ids = model.generate(inputs.input_ids, max_length=100)
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
```
|
kwoncho/gaincut_news_pre2022_2 | kwoncho | 2024-05-28T02:54:26Z | 487 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2024-05-28T02:53:32Z | Entry not found |
mradermacher/Mahou-1.3-llama3-8B-GGUF | mradermacher | 2024-05-29T11:25:58Z | 487 | 0 | transformers | [
"transformers",
"gguf",
"en",
"dataset:flammenai/MahouMix-v1",
"base_model:flammenai/Mahou-1.3-llama3-8B",
"license:llama3",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-29T00:48:59Z | ---
base_model: flammenai/Mahou-1.3-llama3-8B
datasets:
- flammenai/MahouMix-v1
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/flammenai/Mahou-1.3-llama3-8B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-llama3-8B-GGUF/resolve/main/Mahou-1.3-llama3-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
QuantFactory/Daredevil-8B-GGUF | QuantFactory | 2024-05-30T06:37:46Z | 487 | 1 | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"text-generation",
"base_model:mlabonne/Daredevil-8B",
"license:other",
"model-index",
"region:us"
]
| text-generation | 2024-05-30T05:32:36Z | ---
license: other
tags:
- merge
- mergekit
- lazymergekit
base_model: mlabonne/Daredevil-8B
model-index:
- name: Daredevil-8B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 68.86
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 84.5
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 69.24
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 59.89
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 78.45
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 73.54
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B
name: Open LLM Leaderboard
pipeline_tag: text-generation
---
# Daredevil-8B-GGUF
This is quantized version of [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B) created using llama.cpp
## Model Description
Daredevil-8B is a mega-merge designed to maximize MMLU. On 27 May 24, it is the Llama 3 8B model with the **highest MMLU score**.
From my experience, a high MMLU score is all you need with Llama 3 models.
It is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [nbeerbower/llama-3-stella-8B](https://huggingface.co/nbeerbower/llama-3-stella-8B)
* [Hastagaras/llama-3-8b-okay](https://huggingface.co/Hastagaras/llama-3-8b-okay)
* [nbeerbower/llama-3-gutenberg-8B](https://huggingface.co/nbeerbower/llama-3-gutenberg-8B)
* [openchat/openchat-3.6-8b-20240522](https://huggingface.co/openchat/openchat-3.6-8b-20240522)
* [Kukedlc/NeuralLLaMa-3-8b-DT-v0.1](https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-DT-v0.1)
* [cstr/llama3-8b-spaetzle-v20](https://huggingface.co/cstr/llama3-8b-spaetzle-v20)
* [mlabonne/ChimeraLlama-3-8B-v3](https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v3)
* [flammenai/Mahou-1.1-llama3-8B](https://huggingface.co/flammenai/Mahou-1.1-llama3-8B)
* [KingNish/KingNish-Llama3-8b](https://huggingface.co/KingNish/KingNish-Llama3-8b)
Thanks to nbeerbower, Hastagaras, openchat, Kukedlc, cstr, flammenai, and KingNish for their merges. Special thanks to Charles Goddard and Arcee.ai for MergeKit.
## 🔎 Applications
You can use it as an improved version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
This is a censored model. For an uncensored version, see [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated).
Tested on LM Studio using the "Llama 3" preset.
## 🏆 Evaluation
### Open LLM Leaderboard
Daredevil-8B is the best-performing 8B model on the Open LLM Leaderboard in terms of MMLU score (27 May 24).
### Nous
Daredevil-8B is the best-performing 8B model on Nous' benchmark suite (evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval), 27 May 24). See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|---|---:|---:|---:|---:|---:|
| [**mlabonne/Daredevil-8B**](https://huggingface.co/mlabonne/Daredevil-8B) [📄](https://gist.github.com/mlabonne/080f9c5f153ea57a7ab7d932cf896f21) | **55.87** | **44.13** | **73.52** | **59.05** | **46.77** |
| [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) [📄](https://gist.github.com/mlabonne/32cdd8460804662c856bcb2a20acd49e) | 55.06 | 43.29 | 73.33 | 57.47 | 46.17 |
| [mlabonne/Llama-3-8B-Instruct-abliterated-dpomix](https://huggingface.co/mlabonne/Llama-3-8B-Instruct-abliterated-dpomix) [📄](https://gist.github.com/mlabonne/d711548df70e2c04771cc68ab33fe2b9) | 52.26 | 41.6 | 69.95 | 54.22 | 43.26 |
| [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) [📄](https://gist.github.com/mlabonne/8329284d86035e6019edb11eb0933628) | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 |
| [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3) [📄](https://gist.github.com/mlabonne/f46cce0262443365e4cce2b6fa7507fc) | 51.21 | 40.23 | 69.5 | 52.44 | 42.69 |
| [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B) [📄](https://gist.github.com/mlabonne/22896a1ae164859931cc8f4858c97f6f) | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 |
| [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) [📄](https://gist.github.com/mlabonne/616b6245137a9cfc4ea80e4c6e55d847) | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |
## 🌳 Model family tree
## 🧩 Configuration
```yaml
models:
- model: NousResearch/Meta-Llama-3-8B
# No parameters necessary for base model
- model: nbeerbower/llama-3-stella-8B
parameters:
density: 0.6
weight: 0.16
- model: Hastagaras/llama-3-8b-okay
parameters:
density: 0.56
weight: 0.1
- model: nbeerbower/llama-3-gutenberg-8B
parameters:
density: 0.6
weight: 0.18
- model: openchat/openchat-3.6-8b-20240522
parameters:
density: 0.56
weight: 0.12
- model: Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
parameters:
density: 0.58
weight: 0.18
- model: cstr/llama3-8b-spaetzle-v20
parameters:
density: 0.56
weight: 0.08
- model: mlabonne/ChimeraLlama-3-8B-v3
parameters:
density: 0.56
weight: 0.08
- model: flammenai/Mahou-1.1-llama3-8B
parameters:
density: 0.55
weight: 0.05
- model: KingNish/KingNish-Llama3-8b
parameters:
density: 0.55
weight: 0.05
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16
``` |
swj0419/bbc-original_STEP0000080_5-31 | swj0419 | 2024-05-31T22:27:17Z | 487 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-31T22:22:33Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
segment-any-text/sat-12l | segment-any-text | 2024-06-26T08:27:04Z | 487 | 1 | transformers | [
"transformers",
"pytorch",
"xlm-token",
"token-classification",
"multilingual",
"am",
"ar",
"az",
"be",
"bg",
"bn",
"ca",
"ceb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"ne",
"nl",
"no",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"si",
"sk",
"sl",
"sq",
"sr",
"sv",
"ta",
"te",
"tg",
"th",
"tr",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"yo",
"zh",
"zu",
"arxiv:2406.16678",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2024-06-16T09:18:05Z | ---
license: mit
language:
- multilingual
- am
- ar
- az
- be
- bg
- bn
- ca
- ceb
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hu
- hy
- id
- ig
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- mt
- my
- ne
- nl
- no
- pa
- pl
- ps
- pt
- ro
- ru
- si
- sk
- sl
- sq
- sr
- sv
- ta
- te
- tg
- th
- tr
- uk
- ur
- uz
- vi
- xh
- yi
- yo
- zh
- zu
library:
- wtpsplit
---
# sat-12l
Model for [`wtpsplit`](https://github.com/segment-any-text/wtpsplit).
State-of-the-art sentence segmentation with 12 Transfomer layers.
For details, see our [`Segment any Text` paper](arxiv.org/abs/2406.16678) |
nlp-waseda/roberta-large-japanese-seq512 | nlp-waseda | 2022-10-21T14:49:40Z | 486 | 4 | transformers | [
"transformers",
"pytorch",
"roberta",
"fill-mask",
"ja",
"dataset:wikipedia",
"dataset:cc100",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2022-06-13T09:46:45Z | ---
language: ja
license: cc-by-sa-4.0
datasets:
- wikipedia
- cc100
mask_token: "[MASK]"
widget:
- text: "早稲田 大学 で 自然 言語 処理 を [MASK] する 。"
---
# nlp-waseda/roberta-large-japanese-seq512
## Model description
This is a Japanese RoBERTa large model pretrained on Japanese Wikipedia and the Japanese portion of CC-100 with the maximum sequence length of 512.
## How to use
You can use this model for masked language modeling as follows:
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("nlp-waseda/roberta-large-japanese-seq512")
model = AutoModelForMaskedLM.from_pretrained("nlp-waseda/roberta-large-japanese-seq512")
sentence = '早稲田 大学 で 自然 言語 処理 を [MASK] する 。' # input should be segmented into words by Juman++ in advance
encoding = tokenizer(sentence, return_tensors='pt')
...
```
You can fine-tune this model on downstream tasks.
## Tokenization
The input text should be segmented into words by [Juman++](https://github.com/ku-nlp/jumanpp) in advance. Juman++ 2.0.0-rc3 was used for pretraining. Each word is tokenized into tokens by [sentencepiece](https://github.com/google/sentencepiece).
`BertJapaneseTokenizer` now supports automatic `JumanppTokenizer` and `SentencepieceTokenizer`. You can use [this model](https://huggingface.co/nlp-waseda/roberta-large-japanese-seq512-with-auto-jumanpp) without any data preprocessing.
## Vocabulary
The vocabulary consists of 32000 tokens including words ([JumanDIC](https://github.com/ku-nlp/JumanDIC)) and subwords induced by the unigram language model of [sentencepiece](https://github.com/google/sentencepiece).
## Training procedure
This model was trained on Japanese Wikipedia (as of 20210920) and the Japanese portion of CC-100 from the checkpoint of [nlp-waseda/roberta-large-japanese](https://huggingface.co/nlp-waseda/roberta-large-japanese). It took a week using eight NVIDIA A100 GPUs.
The following hyperparameters were used during pretraining:
- learning_rate: 6e-5
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 4120 (max_seq_length=128), 4032 (max_seq_length=512)
- max_seq_length: 512
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-6
- lr_scheduler_type: linear
- training_steps: 670000 (max_seq_length=128) + 70000 (max_seq_length=512)
- warmup_steps: 10000
- mixed_precision_training: Native AMP
|
cffl/bert-base-styleclassification-subjective-neutral | cffl | 2022-07-12T11:57:42Z | 486 | 7 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"arxiv:1911.09709",
"arxiv:1703.01365",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2022-07-01T19:35:53Z | ---
license: apache-2.0
---
# bert-base-styleclassification-subjective-neutral
## Model description
This [bert-base-uncased](https://huggingface.co/bert-base-uncased) model has been fine-tuned on the [Wiki Neutrality Corpus (WNC)](https://arxiv.org/pdf/1911.09709.pdf) - a parallel corpus of 180,000 biased and neutralized sentence pairs along with contextual sentences and metadata. The model can be used to classify text as subjectively biased vs. neutrally toned.
The development and modeling efforts that produced this model are documented in detail through [this blog series](https://blog.fastforwardlabs.com/2022/05/05/neutralizing-subjectivity-bias-with-huggingface-transformers.html).
## Intended uses & limitations
The model is intended purely as a research output for NLP and data science communities. We developed this model for the purpose of evaluating text style transfer output. Specifically, we derive a Style Transfer Intensity (STI) metric from the classifier's output distributions. We also extract feautre importances from the model via [Integrated Gradients](https://arxiv.org/pdf/1703.01365.pdf) with support a Content Preservation Score (CPS).
We imagine this model will be used by researchers to better understand the limitations, robustness, and generalization of text style transfer models. Ultimately, we hope this model will inspire future work on text style transfer and serve as a benchmarking tool for the style attribute of subjectivity bias, specifically.
Any production use of this model - whether commercial or not - is currently not intended. This is because, as [the team at OpenAI points out](https://github.com/openai/gpt-2/blob/master/model_card.md#out-of-scope-use-cases), large langauge models like BERT reflect biases inherent to the systems they were trained on, so we do not recommend that they be deployed into systems that interact with humans, unless the deployers first carry out a study of biases relevant to the intended use-case. Neither the model nor the WNC dataset has been sufficiently evaluated for performance and bias.
As we discuss in the blog series, since the WNC is a parallel dataset and we formulate the learning task as a supervised problem, the model indirectly adopts Wikipedia's NPOV policy as the definition for "neutrality" and "subjectivity". The NPOV policy may not fully reflect an end users assumed/intended meaning of subjectivity because the notion of subjectivity itself can be...well, subjective.
We discovered through our exploratory work that the WNC does contain data quality issues that will contribute to unintended bias in the model. For example, some NPOV revisions introduce factual information outside the context of the prompt as a means to correct bias. We believe these factual based edits are out of scope for a subjective-to-neutral style transfer modeling task, but exist here nonetheless.
## How to use
This model can be used directly with a HuggingFace pipeline for `text2text-generation`.
```python
>>> from transformers import pipeline
>>> classify = pipeline(
task="text-classification",
model="cffl/bert-base-styleclassification-subjective-neutral",
return_all_scores=True,
)
>>> input_text = "chemical abstracts service (cas), a prominent division of the american chemical society, is the world's leading source of chemical information."
>>> classify(input_text)
[[{'label': 'SUBJECTIVE', 'score': 0.9765084385871887},
{'label': 'NEUTRAL', 'score': 0.023491567000746727}]]
```
## Training procedure
For training, we initialize HuggingFace’s [AutoModelforSequenceClassification](https://huggingface.co/docs/transformers/model_doc/auto#transformers.AutoModelForSequenceClassification) with [bert-base-uncased](https://huggingface.co/bert-base-uncased) pre-trained weights and perform a hyperparameter search over: batch size [16, 32], learning rate [3e-05, 3e-06, 3e-07], weight decay [0, 0.01, 0.1] and batch shuffling [True, False] while training for 15 epochs.
We monitor performance using accuracy as we have a perfectly balanced dataset and assign equal cost to false positives and false negatives. The best performing model produces an overall accuracy of 72.50% -- please reference our [training script](https://github.com/fastforwardlabs/text-style-transfer/blob/main/scripts/train/classifier/train_classifier.py) and [classifier evaluation notebook](https://github.com/fastforwardlabs/text-style-transfer/blob/main/notebooks/WNC_full_style_classifier_evaluation.ipynb) for further details.
|
Yuetian/bert-base-uncased-finetuned-plutchik-emotion | Yuetian | 2022-07-25T04:41:30Z | 486 | 5 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2022-07-25T04:40:11Z | ---
license: mit
---
|
stevhliu/my_awesome_eli5_mlm_model | stevhliu | 2022-10-12T22:42:23Z | 486 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2022-10-12T22:30:57Z | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_mlm_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1706
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 20 | 2.2325 |
| No log | 2.0 | 40 | 2.1603 |
| No log | 3.0 | 60 | 2.2368 |
### Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1
|
timm/eva02_large_patch14_448.mim_in22k_ft_in1k | timm | 2024-02-10T23:37:39Z | 486 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2303.11331",
"arxiv:2303.15389",
"license:mit",
"region:us"
]
| image-classification | 2023-03-31T04:28:13Z | ---
license: mit
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for eva02_large_patch14_448.mim_in22k_ft_in1k
An EVA02 image classification model. Pretrained on ImageNet-22k with masked image modeling (using EVA-CLIP as a MIM teacher) and fine-tuned on ImageNet-1k by paper authors.
EVA-02 models are vision transformers with mean pooling, SwiGLU, Rotary Position Embeddings (ROPE), and extra LN in MLP (for Base & Large).
NOTE: `timm` checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 305.1
- GMACs: 362.3
- Activations (M): 689.9
- Image size: 448 x 448
- **Papers:**
- EVA-02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
- EVA-CLIP: Improved Training Techniques for CLIP at Scale: https://arxiv.org/abs/2303.15389
- **Original:**
- https://github.com/baaivision/EVA
- https://huggingface.co/Yuxin-CV/EVA-02
- **Pretrain Dataset:** ImageNet-22k
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('eva02_large_patch14_448.mim_in22k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'eva02_large_patch14_448.mim_in22k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1025, 1024) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |top1 |top5 |param_count|img_size|
|-----------------------------------------------|------|------|-----------|--------|
|eva02_large_patch14_448.mim_m38m_ft_in22k_in1k |90.054|99.042|305.08 |448 |
|eva02_large_patch14_448.mim_in22k_ft_in22k_in1k|89.946|99.01 |305.08 |448 |
|eva_giant_patch14_560.m30m_ft_in22k_in1k |89.792|98.992|1014.45 |560 |
|eva02_large_patch14_448.mim_in22k_ft_in1k |89.626|98.954|305.08 |448 |
|eva02_large_patch14_448.mim_m38m_ft_in1k |89.57 |98.918|305.08 |448 |
|eva_giant_patch14_336.m30m_ft_in22k_in1k |89.56 |98.956|1013.01 |336 |
|eva_giant_patch14_336.clip_ft_in1k |89.466|98.82 |1013.01 |336 |
|eva_large_patch14_336.in22k_ft_in22k_in1k |89.214|98.854|304.53 |336 |
|eva_giant_patch14_224.clip_ft_in1k |88.882|98.678|1012.56 |224 |
|eva02_base_patch14_448.mim_in22k_ft_in22k_in1k |88.692|98.722|87.12 |448 |
|eva_large_patch14_336.in22k_ft_in1k |88.652|98.722|304.53 |336 |
|eva_large_patch14_196.in22k_ft_in22k_in1k |88.592|98.656|304.14 |196 |
|eva02_base_patch14_448.mim_in22k_ft_in1k |88.23 |98.564|87.12 |448 |
|eva_large_patch14_196.in22k_ft_in1k |87.934|98.504|304.14 |196 |
|eva02_small_patch14_336.mim_in22k_ft_in1k |85.74 |97.614|22.13 |336 |
|eva02_tiny_patch14_336.mim_in22k_ft_in1k |80.658|95.524|5.76 |336 |
## Citation
```bibtex
@article{EVA02,
title={EVA-02: A Visual Representation for Neon Genesis},
author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2303.11331},
year={2023}
}
```
```bibtex
@article{EVA-CLIP,
title={EVA-02: A Visual Representation for Neon Genesis},
author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2303.15389},
year={2023}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
GraydientPlatformAPI/model_133 | GraydientPlatformAPI | 2023-04-13T02:04:02Z | 486 | 0 | diffusers | [
"diffusers",
"text-to-image",
"license:unknown",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-04-12T16:43:56Z | ---
license: unknown
library_name: diffusers
pipeline_tag: text-to-image
--- |
luodian/OTTER-Image-MPT7B | luodian | 2023-12-19T14:08:01Z | 486 | 10 | transformers | [
"transformers",
"pytorch",
"otter",
"text2text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-07-09T03:54:03Z | ---
license: mit
---
<p align="center" width="100%">
<img src="https://i.postimg.cc/MKmyP9wH/new-banner.png" width="80%" height="80%">
</p>
<div>
<div align="center">
<a href='https://brianboli.com/' target='_blank'>Bo Li*<sup>1</sup></a> 
<a href='https://zhangyuanhan-ai.github.io/' target='_blank'>Yuanhan Zhang*<sup>,1</sup></a> 
<a href='https://cliangyu.com/' target='_blank'>Liangyu Chen*<sup>,1</sup></a> 
<a href='https://king159.github.io/' target='_blank'>Jinghao Wang*<sup>,1</sup></a> 
<a href='https://pufanyi.github.io/' target='_blank'>Fanyi Pu*<sup>,1</sup></a> 
</br>
<a href='https://jingkang50.github.io/' target='_blank'>Jingkang Yang<sup>1</sup></a> 
<a href='https://chunyuan.li/' target='_blank'>Chunyuan Li<sup>2</sup></a> 
<a href='https://liuziwei7.github.io/' target='_blank'>Ziwei Liu<sup>1</sup></a>
</div>
<div>
<div align="center">
<sup>1</sup>S-Lab, Nanyang Technological University 
<sup>2</sup>Microsoft Research, Redmond
</div>
You can refer the code to start evaluation and demo on your local machine.
https://github.com/Luodian/Otter/blob/8b386816ec67b15833cde3dcd1d7ca6a752d2451/pipeline/demos/demo_models.py#L35 |
TheBloke/huginnv1.2-GGUF | TheBloke | 2023-09-27T12:47:40Z | 486 | 4 | transformers | [
"transformers",
"gguf",
"llama",
"base_model:The-Face-Of-Goonery/huginnv1.2",
"license:llama2",
"text-generation-inference",
"region:us"
]
| null | 2023-09-05T14:46:05Z | ---
license: llama2
model_name: Huginn v1.2
base_model: The-Face-Of-Goonery/huginnv1.2
inference: false
model_creator: Caleb Morgan
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Huginn v1.2 - GGUF
- Model creator: [Caleb Morgan](https://huggingface.co/The-Face-Of-Goonery)
- Original model: [Huginn v1.2](https://huggingface.co/The-Face-Of-Goonery/huginnv1.2)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Caleb Morgan's Huginn v1.2](https://huggingface.co/The-Face-Of-Goonery/huginnv1.2).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/huginnv1.2-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/huginnv1.2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/huginnv1.2-GGUF)
* [Caleb Morgan's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/The-Face-Of-Goonery/huginnv1.2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [huginnv1.2.Q2_K.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [huginnv1.2.Q3_K_S.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [huginnv1.2.Q3_K_M.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [huginnv1.2.Q3_K_L.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [huginnv1.2.Q4_0.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [huginnv1.2.Q4_K_S.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [huginnv1.2.Q4_K_M.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [huginnv1.2.Q5_0.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [huginnv1.2.Q5_K_S.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [huginnv1.2.Q5_K_M.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [huginnv1.2.Q6_K.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [huginnv1.2.Q8_0.gguf](https://huggingface.co/TheBloke/huginnv1.2-GGUF/blob/main/huginnv1.2.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/huginnv1.2-GGUF and below it, a specific filename to download, such as: huginnv1.2.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/huginnv1.2-GGUF huginnv1.2.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/huginnv1.2-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/huginnv1.2-GGUF huginnv1.2.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m huginnv1.2.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/huginnv1.2-GGUF", model_file="huginnv1.2.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Caleb Morgan's Huginn v1.2
better version of the old huginn model, I THINK it's a little tamer now? less of a schizophrenic loose cannon,
it's chronos, airoboros, hermes, beluga merged using my random-merge method, then merged with mythologic using model revolver, then merged with ledgerdemain, and the limarp lora.
I'm aware that mythologic has some of the models huginn already had, but merging them in a second time seemed to smooth out some of it's weird behaviors, and then ledgerdemain allows it to do "step by step" thinking with character behaviors in roleplays.
It is a little less verbose, unless you take some care in the prompt, where aledgedly it's a verbose as the old one, but it's a little harder to make it be as verbose.
It benefits best from the alpaca format for instructions, but you can chat with it too.
thanks to gryphe for helping with improving this merge and permitting me to add it to the official version! It means a lot!
v1.3 will be actually trained on, I recently got access to some training servers thanks to the guanaco team!
<!-- original-model-card end -->
|
RalFinger/noodles-lora-sdxl | RalFinger | 2023-11-22T13:07:30Z | 486 | 1 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"surrealism",
"style",
"food",
"noodle",
"noodles",
"styles",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:other",
"region:us"
]
| text-to-image | 2023-11-22T13:07:26Z | ---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Sell&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- surrealism
- style
- food
- noodle
- noodles
- styles
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: noodlez
widget:
- text: 'snow panther abstract beauty, centered, looking at the camera, approaching perfection, dynamic, moonlight, highly detailed, digital painting, artstation, concept art, smooth, sharp focus,, noodlez '
output:
url: >-
3248714.jpeg
- text: 'fight scene, blood made out of tomato sauce, 4k, full body, melted cheese face, ninja made out of noodles, white body noodle armor, holding noodle weapon, (dripping tomato sauce:1.6), smoke, night, cinematic, color grading, (black background:1.5), noodle dungeon, dark light, noodlez '
output:
url: >-
3248713.jpeg
- text: 'zombie, (dripping tomato sauce:1.4), noodlez '
output:
url: >-
3248715.jpeg
- text: 'female gatherer, in mythical forrest, dark shadows, at night, backlight, made out of noodlez '
output:
url: >-
3248716.jpeg
- text: 'massive noodle monster, big evil smile, evil face, monster made out of noodles, tomato sauce, flying tomatoes, (dark mirror background:2), made out of noodles, evil scene, dark scene, fight scene, noodlez '
output:
url: >-
3248717.jpeg
- text: 'cake on a mirror plate, (dripping tomato sauce:1.4), noodlez '
output:
url: >-
3248719.jpeg
- text: 'human made of noodles, (((noodles human:1.4))) full cheese body, (cheese face:1.4), Korean girl 20 years old, (best quality:1.4), masterpiece, (photorealistic:1.4), 8k, ultra detailed, beautiful and aesthetic, black background, mirror floor, noodlez '
output:
url: >-
3248720.jpeg
- text: 'fight scene, blood made out of tomato sauce, 4k, full body, melted cheese face, ninja made out of noodles, white body noodle armor, holding noodle weapon, (dripping tomato sauce:1.6), smoke, night, cinematic, color grading, (black background:1.5), noodle dungeon, dark light, noodlez '
output:
url: >-
3248723.jpeg
- text: 'massive noodle monster, big evil smile, evil face, monster made out of noodles, tomato sauce, flying tomatoes, (dark mirror background:2), made out of noodles, evil scene, dark scene, fight scene, noodlez '
output:
url: >-
3248724.jpeg
- text: 'massive noodle monster, noodlez '
output:
url: >-
3248725.jpeg
---
# Noodles [LoRA SDXL]
<Gallery />
([CivitAI](https://civitai.com/models/181993))
## Model description
<p><u>SDXL:<br /></u><span style="color:rgb(193, 194, 197)">Trigger word: </span><strong>noodlez</strong><br /><span style="color:rgb(193, 194, 197)">Sampling Method: </span><strong><span style="color:rgb(219, 222, 225)">DPM++ 2M SDE Karras</span></strong><br /><br />☕ Buy me a coffee: <a target="_blank" rel="ugc" href="https://ko-fi.com/ralfingerai">https://ko-fi.com/ralfingerai</a></p>
## Trigger words
You should use `noodlez` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/RalFinger/noodles-lora-sdxl/tree/main) them in the Files & versions tab.
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('RalFinger/noodles-lora-sdxl', weight_name='noodlez-sdxl.safetensors')
image = pipeline('massive noodle monster, noodlez ').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
LiteLLMs/Mistral-7B-Merge-14-v0.1-GGUF | LiteLLMs | 2024-01-24T17:12:02Z | 486 | 0 | transformers | [
"transformers",
"safetensors",
"gguf",
"mistral",
"text-generation",
"GGUF",
"merge",
"conversational",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-12-25T20:34:19Z | ---
language:
- en
license: cc-by-nc-4.0
tags:
- GGUF
- merge
quantized_by: andrijdavid
---
# Mistral-7B-Merge-14-v0.1-GGUF
- Original model: [Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.
* [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.
* [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.
* [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.
* [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.
* [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents.
<!-- README_GGUF.md-about-gguf end -->
<!-- compatibility_gguf start -->
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: andrijdavid/Mistral-7B-Merge-14-v0.1-GGUF and below it, a specific filename to download, such as: Mistral-7B-Merge-14-v0.1-f16.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download andrijdavid/Mistral-7B-Merge-14-v0.1-GGUF Mistral-7B-Merge-14-v0.1-f16.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download andrijdavid/Mistral-7B-Merge-14-v0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download andrijdavid/Mistral-7B-Merge-14-v0.1-GGUF Mistral-7B-Merge-14-v0.1-f16.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m Mistral-7B-Merge-14-v0.1-f16.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./Mistral-7B-Merge-14-v0.1-f16.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<PROMPT>", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./Mistral-7B-Merge-14-v0.1-f16.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Mistral-7B-Merge-14-v0.1
# Update 2023-12-19
In light of [dataset contamination issue among the merged models](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474)
raised by the community in recent days, in particular
[berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha),
[Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling), and
[janai-hq/trinity-v1](https://huggingface.co/janai-hq/trinity-v1),
we decided to remake another model without the models mentioned.
Additionally, their CC-by-NC-4.0 license is restrictive and thus are not suitable for an open model.
# Model Description
This is an experiment to test merging 14 models using DARE TIES 🦙
The merged model is then merged again with [janai-hq/trinity-v1](https://huggingface.co/janai-hq/trinity-v1) using Gradient SLERP.
The result is a base model that performs quite well but requires some further instruction fine-tuning.
The 14 models are as follows:
1. [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
2. [ehartford/dolphin-2.2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b)
3. [SciPhi/SciPhi-Mistral-7B-32k](https://huggingface.co/SciPhi/SciPhi-Mistral-7B-32k)
4. [ehartford/samantha-1.2-mistral-7b](https://huggingface.co/ehartford/samantha-1.2-mistral-7b)
5. [Arc53/docsgpt-7b-mistral](https://huggingface.co/Arc53/docsgpt-7b-mistral)
6. [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)
7. [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
8. [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
9. [v1olet/v1olet_marcoroni-go-bruins-merge-7B](https://huggingface.co/v1olet/v1olet_marcoroni-go-bruins-merge-7B)
10. [beowolx/MistralHermes-CodePro-7B-v1](https://huggingface.co/beowolx/MistralHermes-CodePro-7B-v1)
11. [TIGER-Lab/MAmmoTH-7B-Mistral](https://huggingface.co/TIGER-Lab/MAmmoTH-7B-Mistral)
12. [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
13. [Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp)
14. [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
- base model: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
The yaml config file for this model is here:
```yaml
slices:
- sources:
- model: EmbeddedLLM/Mistral-7B-Merge-14-v0
layer_range: [0, 32]
- model: janai-hq/trinity-v1
layer_range: [0, 32]
merge_method: slerp
base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
<!-- original-model-card end --> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.