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
|
|---|---|---|---|---|---|---|---|---|---|
feeltheAGI/maverick-llama3-8B | feeltheAGI | 2024-04-25T06:56:34Z | 395 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"meta-llama/Meta-Llama-3-8B",
"conversational",
"dataset:feeltheAGI/maverick-sharegpt",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-25T00:27:47Z | ---
tags:
- meta-llama/Meta-Llama-3-8B
datasets:
- feeltheAGI/maverick-sharegpt
license: apache-2.0
---
#### Maverick Llama 3 8b ๐ดโโ ๏ธ
model is using ChatML prompt template format.
example:
```
<|im_start|>system
You are Maverick, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
๐ Evaluation
## eq-bench
| Tasks |Version|Filter|n-shot| Metric | Value | |Stderr|
|--------|------:|------|-----:|-----------------|------:|---|-----:|
|eq_bench| 2.1|none | 0|eqbench |56.8710|ยฑ |2.8946|
| | |none | 0|percent_parseable|99.4152|ยฑ |0.5848|
## winogrande
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|----------|------:|------|-----:|------|-----:|---|-----:|
|winogrande| 1|none | 0|acc |0.7372|ยฑ |0.0124|
## gsm8k
|Tasks|Version| Filter |n-shot| Metric |Value | |Stderr|
|-----|------:|----------------|-----:|-----------|-----:|---|-----:|
|gsm8k| 3|strict-match | 5|exact_match|0.5694|ยฑ |0.0136|
| | |flexible-extract| 5|exact_match|0.5701|ยฑ |0.0136|
## mathqa
|Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|------|------:|------|-----:|--------|-----:|---|-----:|
|mathqa| 1|none | 0|acc |0.3930|ยฑ |0.0089|
| | |none | 0|acc_norm|0.3869|ยฑ |0.0089|
This model is based on Llama-3-8b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE) |
chujiezheng/tulu-2-dpo-13b-ExPO | chujiezheng | 2024-05-27T18:14:50Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"arxiv:2404.16792",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-26T14:46:27Z | ---
license: other
license_name: ai2-impact-license-low-risk
license_link: https://allenai.org/impact-license
language:
- en
---
# tulu-2-dpo-13b-ExPO
The extrapolated (ExPO) model based on [`allenai/tulu-2-dpo-13b`](https://huggingface.co/allenai/tulu-2-dpo-13b) and [`allenai/tulu-2-13b`](https://huggingface.co/allenai/tulu-2-13b), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating **(alpha = 0.5)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
## Evaluation Results
Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_alpaca)):
| | Win Rate (Ori) | LC Win Rate (Ori) | Win Rate (+ ExPO) | LC Win Rate (+ ExPO) |
| ------------------------------------ | -------------- | ----------------- | ----------------- | -------------------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.7% | 10.0% | **10.6%** | **13.6%** |
| `HuggingFaceH4/zephyr-7b-beta` | 10.2% | 13.2% | **11.1%** | **14.0%** |
| `berkeley-nest/Starling-LM-7B-alpha` | 15.0% | 18.3% | **18.2%** | **19.5%** |
| `Nexusflow/Starling-LM-7B-beta` | 26.6% | 25.8% | **29.6%** | **26.4%** |
| `snorkelai/Snorkel-Mistral-PairRM` | 24.7% | 24.0% | **28.8%** | **26.4%** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 29.2% | 36.0% | **32.7%** | **37.8%** |
| `internlm/internlm2-chat-1.8b` | 3.8% | 4.0% | **5.2%** | **4.3%** |
| `internlm/internlm2-chat-7b` | 20.5% | 18.3% | **28.1%** | **22.7%** |
| `internlm/internlm2-chat-20b` | 36.1% | 24.9% | **46.2%** | **27.2%** |
| `allenai/tulu-2-dpo-7b` | 8.5% | 10.2% | **11.5%** | **11.7%** |
| `allenai/tulu-2-dpo-13b` | 11.2% | 15.5% | **15.6%** | **17.6%** |
| `allenai/tulu-2-dpo-70b` | 15.4% | 21.2% | **23.0%** | **25.7%** |
Evaluation results on the **MT-Bench** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_mtbench)):
| | Original | + ExPO |
| ------------------------------------ | -------- | -------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.85 | **6.87** |
| `HuggingFaceH4/zephyr-7b-beta` | 7.02 | **7.06** |
| `berkeley-nest/Starling-LM-7B-alpha` | 7.82 | **7.91** |
| `Nexusflow/Starling-LM-7B-beta` | 8.10 | **8.18** |
| `snorkelai/Snorkel-Mistral-PairRM` | 7.63 | **7.69** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 8.08 | **8.45** |
| `internlm/internlm2-chat-1.8b` | 5.17 | **5.26** |
| `internlm/internlm2-chat-7b` | 7.72 | **7.80** |
| `internlm/internlm2-chat-20b` | 8.13 | **8.26** |
| `allenai/tulu-2-dpo-7b` | 6.35 | **6.38** |
| `allenai/tulu-2-dpo-13b` | 7.00 | **7.26** |
| `allenai/tulu-2-dpo-70b` | 7.79 | **8.03** |
|
ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_2 | ShenaoZhang | 2024-04-26T21:56:58Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"dataset:updated",
"dataset:original",
"base_model:ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_1",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-26T21:25:43Z | ---
license: mit
base_model: ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_1
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
datasets:
- updated
- original
model-index:
- name: 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_2
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. -->
# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_2
This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_1](https://huggingface.co/ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_1) on the updated and the original datasets.
## 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: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
|
mmnga/ryota39-Phi-3-mini-4k-instruct-dpo-gguf | mmnga | 2024-04-29T16:53:45Z | 395 | 0 | null | [
"gguf",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"license:mit",
"region:us"
]
| null | 2024-04-29T14:27:25Z | ---
license: mit
language:
- en
- ja
datasets:
- TFMC/imatrix-dataset-for-japanese-llm
---
# ryota39-Phi-3-mini-4k-instruct-dpo-gguf
[ryota39ใใใๅ
ฌ้ใใฆใใPhi-3-mini-4k-instruct-dpo](https://huggingface.co/ryota39/Phi-3-mini-4k-instruct-dpo)ใฎggufใใฉใผใใใๅคๆ็ใงใใ
imatrixใฎใใผใฟใฏ[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)ใไฝฟ็จใใฆไฝๆใใพใใใ
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'ryota39-Phi-3-mini-4k-instruct-dpo-Q4_0.gguf' -p "<|user|>\nไปๆฉใฎๅค้ฃใฎใฌใทใใๆใใฆ<|end>\n<|assistant|>\n" -n 128
``` |
chujiezheng/Mistral7B-PairRM-SPPO-ExPO | chujiezheng | 2024-06-01T21:06:08Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"arxiv:2404.16792",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-04T07:12:58Z | ---
license: apache-2.0
language:
- en
---
# Mistral7B-PairRM-SPPO-ExPO
The extrapolated (ExPO) model based on [`UCLA-AGI/Mistral7B-PairRM-SPPO`](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO) and [`mistralai/Mistral-7B-Instruct-v0.2`](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
This extrapolated model achieves the **35.4%** win rate and **31.8%** LC win rate on **AlpacaEval 2.0**, outperforming the original `Mistral7B-PairRM-SPPO`'s 32.2% and 30.5%, respectively.
## Evaluation Results
Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_alpaca)):
| | Win Rate (Ori) | LC Win Rate (Ori) | Win Rate (+ ExPO) | LC Win Rate (+ ExPO) |
| ------------------------------------ | -------------- | ----------------- | ----------------- | -------------------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.7% | 10.0% | **10.6%** | **13.6%** |
| `HuggingFaceH4/zephyr-7b-beta` | 10.2% | 13.2% | **11.1%** | **14.0%** |
| `berkeley-nest/Starling-LM-7B-alpha` | 15.0% | 18.3% | **18.2%** | **19.5%** |
| `Nexusflow/Starling-LM-7B-beta` | 26.6% | 25.8% | **29.6%** | **26.4%** |
| `snorkelai/Snorkel-Mistral-PairRM` | 24.7% | 24.0% | **28.8%** | **26.4%** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 29.2% | 36.0% | **32.7%** | **37.8%** |
| `internlm/internlm2-chat-1.8b` | 3.8% | 4.0% | **5.2%** | **4.3%** |
| `internlm/internlm2-chat-7b` | 20.5% | 18.3% | **28.1%** | **22.7%** |
| `internlm/internlm2-chat-20b` | 36.1% | 24.9% | **46.2%** | **27.2%** |
| `allenai/tulu-2-dpo-7b` | 8.5% | 10.2% | **11.5%** | **11.7%** |
| `allenai/tulu-2-dpo-13b` | 11.2% | 15.5% | **15.6%** | **17.6%** |
| `allenai/tulu-2-dpo-70b` | 15.4% | 21.2% | **23.0%** | **25.7%** |
Evaluation results on the **MT-Bench** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_mtbench)):
| | Original | + ExPO |
| ------------------------------------ | -------- | -------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.85 | **6.87** |
| `HuggingFaceH4/zephyr-7b-beta` | 7.02 | **7.06** |
| `berkeley-nest/Starling-LM-7B-alpha` | 7.82 | **7.91** |
| `Nexusflow/Starling-LM-7B-beta` | 8.10 | **8.18** |
| `snorkelai/Snorkel-Mistral-PairRM` | 7.63 | **7.69** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 8.08 | **8.45** |
| `internlm/internlm2-chat-1.8b` | 5.17 | **5.26** |
| `internlm/internlm2-chat-7b` | 7.72 | **7.80** |
| `internlm/internlm2-chat-20b` | 8.13 | **8.26** |
| `allenai/tulu-2-dpo-7b` | 6.35 | **6.38** |
| `allenai/tulu-2-dpo-13b` | 7.00 | **7.26** |
| `allenai/tulu-2-dpo-70b` | 7.79 | **8.03** |
|
Syed-Hasan-8503/Exodius-70B | Syed-Hasan-8503 | 2024-05-07T18:20:59Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:freewheelin/free-evo-qwen72b-v0.8-re",
"base_model:abacusai/Smaug-72B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-07T17:10:10Z | ---
base_model:
- freewheelin/free-evo-qwen72b-v0.8-re
- abacusai/Smaug-72B-v0.1
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [freewheelin/free-evo-qwen72b-v0.8-re](https://huggingface.co/freewheelin/free-evo-qwen72b-v0.8-re)
* [abacusai/Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: freewheelin/free-evo-qwen72b-v0.8-re
layer_range: [0, 80]
- model: abacusai/Smaug-72B-v0.1
layer_range: [0, 80]
merge_method: slerp
base_model: freewheelin/free-evo-qwen72b-v0.8-re
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
``` |
saucam/PowerBot-8B | saucam | 2024-05-14T15:39:25Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"nvidia/Llama3-ChatQA-1.5-8B",
"refuelai/Llama-3-Refueled",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-09T16:02:07Z | ---
tags:
- merge
- mergekit
- nvidia/Llama3-ChatQA-1.5-8B
- refuelai/Llama-3-Refueled
models:
- nvidia/Llama3-ChatQA-1.5-8B
- refuelai/Llama-3-Refueled
license: apache-2.0
language:
- en
---
# PowerBot-8B
PowerBot-8B is a merge of the following models using [Mergekit](https://github.com/arcee-ai/mergekit):
* [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B)
* [refuelai/Llama-3-Refueled](https://huggingface.co/refuelai/Llama-3-Refueled)
## ๐งฉ Configuration
```yamlname: PowerBot-8B
tokenizer_source: union
embed_slerp: true
models:
- model: nvidia/Llama3-ChatQA-1.5-8B
parameters:
density: 0.5
weight: 0.6
# No parameters necessary for base model
- model: refuelai/Llama-3-Refueled
parameters:
density: 0.5
weight: 0.4
merge_method: dare_ties
base_model: nvidia/Llama3-ChatQA-1.5-8B
parameters:
int8_mask: true
dtype: bfloat16
```
## ๐ป Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "saucam/PowerBot-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
```
Loading checkpoint shards: 100%|โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ| 2/2 [00:07<00:00, 3.75s/it]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.
<|im_start|>user
What is a large language model?<|im_end|>
<|im_start|>assistant
A large language model (LLM) is a deep neural network that is trained to predict the next word in a sequence of text. LLMs are typically trained on large amounts of text data and can be used for a variety of tasks such as language translation, text completion, and question answering. They are often used to generate human-like text and are becoming increasingly popular in natural language processing applications. The LLM uses a transformer architecture, which consists of multiple layers of neural networks that are trained to process and understand the relationships between words in a sentence. The transformer architecture is designed to handle long sequences of text and is capable of capturing the context of a word within a sentence. This allows the LLM to generate coherent and grammatically correct text that is similar to human writing. LLMs are typically trained on a large corpus of text data and can be fine-tuned for specific tasks by retraining on smaller datasets that are relevant to the task at hand. This allows the LLM to adapt to the specific requirements of a particular application and improve its performance. The LLM can be used to generate text in a variety of formats, including natural language, code, and even mathematical expressions. It can also be used to translate text from one language to another, generate summaries of
```
Preserves the whole document as context capability
```
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "saucam/PowerBot-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
messages = [
{"role": "user", "content": "what is the percentage change of the net income from Q4 FY23 to Q4 FY24?"}
]
document = """NVIDIA (NASDAQ: NVDA) today reported revenue for the fourth quarter ended January 28, 2024, of $22.1 billion, up 22% from the previous quarter and up 265% from a year ago.\nFor the quarter, GAAP earnings per diluted share was $4.93, up 33% from the previous quarter and up 765% from a year ago. Non-GAAP earnings per diluted share was $5.16, up 28% from the previous quarter and up 486% from a year ago.\nQ4 Fiscal 2024 Summary\nGAAP\n| $ in millions, except earnings per share | Q4 FY24 | Q3 FY24 | Q4 FY23 | Q/Q | Y/Y |\n| Revenue | $22,103 | $18,120 | $6,051 | Up 22% | Up 265% |\n| Gross margin | 76.0% | 74.0% | 63.3% | Up 2.0 pts | Up 12.7 pts |\n| Operating expenses | $3,176 | $2,983 | $2,576 | Up 6% | Up 23% |\n| Operating income | $13,615 | $10,417 | $1,257 | Up 31% | Up 983% |\n| Net income | $12,285 | $9,243 | $1,414 | Up 33% | Up 769% |\n| Diluted earnings per share | $4.93 | $3.71 | $0.57 | Up 33% | Up 765% |"""
def get_formatted_input(messages, context):
system = "System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context."
instruction = "Please give a full and complete answer for the question."
for item in messages:
if item['role'] == "user":
## only apply this instruction for the first user turn
item['content'] = instruction + " " + item['content']
break
conversation = '\n\n'.join(["User: " + item["content"] if item["role"] == "user" else "Assistant: " + item["content"] for item in messages]) + "\n\nAssistant:"
formatted_input = system + "\n\n" + context + "\n\n" + conversation
return formatted_input
formatted_input = get_formatted_input(messages, document)
tokenized_prompt = tokenizer(tokenizer.bos_token + formatted_input, return_tensors="pt").to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(input_ids=tokenized_prompt.input_ids, attention_mask=tokenized_prompt.attention_mask, max_new_tokens=128, eos_token_id=terminators)
response = outputs[0][tokenized_prompt.input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
```
Downloading shards: 100%|โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ| 2/2 [00:00<00:00, 12.71it/s]
Loading checkpoint shards: 100%|โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ| 2/2 [00:08<00:00, 4.05s/it]
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.
The percentage change of the net income from Q4 FY23 to Q4 FY24 is 769%. This is calculated by taking the difference between the two net incomes ($12,285 million and $1,414 million) and dividing it by the net income from Q4 FY23 ($1,414 million), then multiplying by 100 to get the percentage change. So, the formula is ((12,285 - 1,414) / 1,414) * 100 = 769%.
```
Sample run on classification tasks, positive labelling still works
```
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "saucam/PowerBot-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
messages = [{"role": "user", "content": "Is this comment toxic or non-toxic: RefuelLLM is the new way to label text data!"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to("cuda")
outputs = model.generate(inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0]))
```
```
Loading checkpoint shards: 100%|โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ| 2/2 [00:07<00:00, 3.89s/it]
No chat template is defined for this tokenizer - using a default chat template that implements the ChatML format (without BOS/EOS tokens!). If the default is not appropriate for your model, please set `tokenizer.chat_template` to an appropriate template. See https://huggingface.co/docs/transformers/main/chat_templating for more information.
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.
<|im_start|>user
Is this comment toxic or non-toxic: RefuelLLM is the new way to label text data!<|im_end|>
<|im_start|>assistant
This comment is non-toxic.
<|im_end|><|end_of_text|>
``` |
OwenArli/Awanllm-Llama-3-8B-Dolfin-v0.5 | OwenArli | 2024-05-13T08:30:43Z | 395 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-12T03:26:52Z | ---
license: llama3
---
Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement:
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
This is a fine tune using an improved Dolphin and WizardLM dataset intended to make the model follow instructions better and refuse less.
We also have it up on our site https://awanllm.com for anyone to try!
OpenLLM Benchmark:
Training:
- 2048 sequence length since the dataset has an average length of under 1000 tokens, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine.
- Training duration is around 2 days on 2xRTX 3090, using 4-bit loading and Qlora 64-rank 128-alpha resulting in ~2% trainable weights.
Instruct format:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
Quants:
FP16: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v0.5
GGUF: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF
|
Ayush-1722/Mistral-7B-Instruct-v0.1-Summarize-64K-LoRANET-Merged | Ayush-1722 | 2024-06-19T12:46:50Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"finetuned",
"summarize",
"instruct",
"200K+ Context Length",
"question answering",
"LoRA",
"Theta Scaling",
"Norm & Embed Trained",
" Big Patents",
"chat",
"7B",
"research",
"science",
"RoPE ",
"Long Context",
"conversational",
"dataset:RMT-team/babilong",
"dataset:RMT-team/babilong-1k-samples",
"dataset:Trelis/big_patent_100k_characters",
"dataset:facebook/babi_qa",
"arxiv:2310.06825",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T00:54:48Z | ---
license: apache-2.0
pipeline_tag: text-generation
tags:
- finetuned
- summarize
- instruct
- 200K+ Context Length
- question answering
- LoRA
- Theta Scaling
- Norm & Embed Trained
- ' Big Patents'
- chat
- 7B
- research
- science
- 'RoPE '
- Long Context
- conversational
inference: true
widget:
- messages:
- role: user
content: What is your favorite condiment?
datasets:
- RMT-team/babilong
- RMT-team/babilong-1k-samples
- Trelis/big_patent_100k_characters
- facebook/babi_qa
metrics:
- accuracy
- perplexity
---
# Model Card for Mistral-7B-Instruct-v0.1
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets.
For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/).
## 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, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lรฉlio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothรฉe Lacroix, William El Sayed. |
AIGym/Llama-3-8B-Instruct-Gradient-1048k-Agent | AIGym | 2024-05-24T09:59:10Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T03:47:19Z | ---
library_name: transformers
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
This model is being made to enhance our work within crewai. We started with a high context length (1048K) version of Llama 3. We then fine-tuned on top of that to get a base agent.
## Model Description
Built on the following:
- Models:
- [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
- [Llama-3-8B-Instruct-Gradient-1048k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k)
- Datasets:
- m-a-p/CodeFeedback-Filtered-Instruction
- RomanTeucher/awesome_topic_code_snippets
- dair-ai/emotion
- mzbac/function-calling-llama-3-format-v1.1
- gretelai/synthetic_text_to_sql
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Model type:** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [Llama-3-8B-Instruct-Gradient-1048k]
## 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
Use inside with crewai to get better results and to generaete starting data.
### Direct Use
Use as a chat bot, ai agent, etc.
### Out-of-Scope Use
Anything outside of using with crewai while vary possiable will be out of scope.
### Recommendations
Self host or host this model in the cloud and use with crew ai for best results.
## Code Examples
Use the following format when using the model for inference:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are the helpful assistant. <|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt} <|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
Example of multi turn
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful AI assistant for travel tips and recommendations<|eot_id|><|start_header_id|>user<|end_header_id|>
What is France's capital?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Bonjour! The capital of France is Paris!<|eot_id|><|start_header_id|>user<|end_header_id|>
What can I do there?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Paris, the City of Light, offers a romantic getaway with must-see attractions like the Eiffel Tower and Louvre Museum, romantic experiences like river cruises and charming neighborhoods, and delicious food and drink options, with helpful tips for making the most of your trip.<|eot_id|><|start_header_id|>user<|end_header_id|>
Give me a detailed list of the attractions I should visit, and time it takes in each one, to plan my trip accordingly.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## How to Get Started with the Model
Use the code below to get started with the model.
```
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-70B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
``` |
Mxode/Qwen1.5-0.5B-L20-raw | Mxode | 2024-05-14T10:01:37Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"pretrained",
"conversational",
"en",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T09:59:59Z | ---
license: other
license_name: tongyi-qianwen-research
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- pretrained
---
# 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 ๐ค 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]
|
shyamieee/Padma-SLM-7b-v2.0 | shyamieee | 2024-05-21T07:57:52Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2212.04089",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-21T04:55:09Z | ---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# Padma_SLM_7b_v2_folder
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using bophades-mistral-truthy-DPO-7B as a base.
### Models Merged
The following models were included in the merge:
* multi_verse_model
* Calme-7B-Instruct-v0.9
* YamshadowExperiment28-7B
### Configuration |
allknowingroger/Mistral3mash1-7B-slerp | allknowingroger | 2024-05-23T06:28:14Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"allknowingroger/MultiverseEx26-7B-slerp",
"shisa-ai/shisa-v1-mistral0.3-7b",
"conversational",
"base_model:allknowingroger/MultiverseEx26-7B-slerp",
"base_model:shisa-ai/shisa-v1-mistral0.3-7b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-23T06:22:54Z | ---
tags:
- merge
- mergekit
- lazymergekit
- allknowingroger/MultiverseEx26-7B-slerp
- shisa-ai/shisa-v1-mistral0.3-7b
base_model:
- allknowingroger/MultiverseEx26-7B-slerp
- shisa-ai/shisa-v1-mistral0.3-7b
license: apache-2.0
---
# Mistral3mash1-7B-slerp
Mistral3mash1-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [allknowingroger/MultiverseEx26-7B-slerp](https://huggingface.co/allknowingroger/MultiverseEx26-7B-slerp)
* [shisa-ai/shisa-v1-mistral0.3-7b](https://huggingface.co/shisa-ai/shisa-v1-mistral0.3-7b)
## ๐งฉ Configuration
```yaml
slices:
- sources:
- model: allknowingroger/MultiverseEx26-7B-slerp
layer_range: [0, 32]
- model: shisa-ai/shisa-v1-mistral0.3-7b
layer_range: [0, 32]
merge_method: slerp
base_model: shisa-ai/shisa-v1-mistral0.3-7b
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
```
## ๐ป Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/Mistral3mash1-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
venkynavs/request_type_classifier_bert | venkynavs | 2024-05-24T11:08:01Z | 395 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2024-05-24T11:07:33Z | ---
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 ๐ค 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] |
John6666/cherry-picker-xl-v3-sdxl | John6666 | 2024-05-28T06:53:05Z | 395 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2024-05-28T06:47:16Z | ---
license: other
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
---
Original model is [here](https://civitai.com/models/125680?modelVersionId=373927).
|
Steelskull/L3-Aethora-15B | Steelskull | 2024-06-11T13:10:25Z | 395 | 28 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"conversational",
"dataset:TheSkullery/Aether-Lite-V1.2",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-05T22:14:03Z | ---
library_name: transformers
tags:
- llama-factory
license: llama3
datasets:
- TheSkullery/Aether-Lite-V1.2
---
<!DOCTYPE html>
<style>
body, html {
height: 100%; /* Ensure the full height of the page is used */
margin: 0;
padding: 0;
font-family: 'Quicksand', sans-serif;
background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%);
color: #D8DEE9;
font-size: 16px;
}
.container {
width: 100%; /* Full width */
height: 100%; /* Full height */
padding: 20px;
margin: 0; /* Remove margin to fill the entire area */
background-color: rgba(255, 255, 255, 0.02);
border-radius: 12px;
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
backdrop-filter: blur(10px);
border: 1px solid rgba(255, 255, 255, 0.1);
}
.header h1 {
font-size: 28px;
color: #5F9EA0;
margin: 0 0 20px 0;
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
}
.update-section h2 {
font-size: 24px;
color: #88C0D0;
}
.update-section p {
font-size: 16px;
line-height: 1.6;
color: #ECEFF4;
}
.info img {
width: 100%;
border-radius: 10px;
margin-bottom: 15px;
}
a {
color: #88C0D0;
text-decoration: none;
}
a:hover {
color: #A3BE8C;
}
.button {
display: inline-block;
background-color: #5E81AC;
color: #E5E9F0;
padding: 10px 20px;
border-radius: 5px;
cursor: pointer;
text-decoration: none;
}
.button:hover {
background-color: #81A1C1;
}
pre {
background-color: #2E3440;
padding: 10px;
border-radius: 5px;
overflow-x: auto;
}
code {
font-family: 'Courier New', monospace;
color: #D8DEE9;
}
</style>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>L3-Aethora-15B Data Card</title>
<link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
</head>
<body>
<div class="container">
<div class="header">
<h1>L3-Aethora-15B</h1>
</div>
<div class="info">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/W0qzZK_V1Zt1GdgCIsnrP.png">
<p>The Skullery Presents L3-Aethora-15B.</p>
<p><strong>Creator:</strong> <a href="https://huggingface.co/steelskull" target="_blank">Steelskull</a></p>
<p><strong>Dataset:</strong> <a href="https://huggingface.co/datasets/TheSkullery/Aether-Lite-V1.2" target="_blank">Aether-Lite-V1.2</a></p>
<p><strong>Trained:</strong> 4 x A100 for 15 hours Using RsLora and DORA</p>
<h1>About L3-Aethora-15B:</h1>
<pre><code> L3 = Llama3 </code></pre>
<p>L3-Aethora-15B was crafted through using the abilteration method to adjust model responses. The model's refusal is inhibited, focusing on yielding more compliant and facilitative dialogue interactions. It then underwent a modified DUS (Depth Up Scale) merge (originally used by @Elinas) by using passthrough merge to create a 15b model, with specific adjustments (zeroing) to 'o_proj' and 'down_proj', enhancing its efficiency and reducing perplexity. This created AbL3In-15b.<br>
<p>AbL3In-15b was then trained for 4 epochs using Rslora & DORA training methods on the Aether-Lite-V1.2 dataset, containing ~82000 high quality samples, designed to strike a fine balance between creativity, slop, and intelligence at about a 60/40 split</p>
<p>This model is trained on the L3 prompt format.</p>
<h2>Quants:</h2>
<li><a href="https://huggingface.co/mradermacher/L3-Aethora-15B-GGUF" target="_blank">Mradermacher/L3-Aethora-15B-GGUF</a></li>
<li><a href="https://huggingface.co/mradermacher/L3-Aethora-15B-i1-GGUF" target="_blank">Mradermacher/L3-Aethora-15B-i1-GGUF</a></li>
<li><a href="https://huggingface.co/NikolayKozloff" target="_blank">NikolayKozloff/L3-Aethora-15B-GGUF</a></li>
<p></p>
<h2>Dataset Summary: (Filtered)</h2>
<p>Filtered Phrases: GPTslop, Claudism's</p>
<ul>
<li><strong>mrfakename/Pure-Dove-ShareGPT:</strong> Processed 3707, Removed 150</li>
<li><strong>mrfakename/Capybara-ShareGPT:</strong> Processed 13412, Removed 2594</li>
<li><strong>jondurbin/airoboros-3.2:</strong> Processed 54517, Removed 4192</li>
<li><strong>PJMixers/grimulkan_theory-of-mind-ShareGPT:</strong> Processed 533, Removed 6</li>
<li><strong>grimulkan/PIPPA-augmented-dedup:</strong> Processed 869, Removed 46</li>
<li><strong>grimulkan/LimaRP-augmented:</strong> Processed 790, Removed 14</li>
<li><strong>PJMixers/grimulkan_physical-reasoning-ShareGPT:</strong> Processed 895, Removed 4</li>
<li><strong>MinervaAI/Aesir-Preview:</strong> Processed 994, Removed 6</li>
<li><strong>Doctor-Shotgun/no-robots-sharegpt:</strong> Processed 9911, Removed 89</li>
</ul>
<h2>Deduplication Stats:</h2>
<p>Starting row count: 85628, Final row count: 81960, Rows removed: 3668</p>
</div>
</div>
</body>
</html> |
mradermacher/airoboros-65b-gpt4-m2.0-GGUF | mradermacher | 2024-06-10T10:46:24Z | 395 | 0 | transformers | [
"transformers",
"gguf",
"en",
"dataset:jondurbin/airoboros-gpt4-m2.0",
"base_model:jondurbin/airoboros-65b-gpt4-m2.0",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-06T14:53:15Z | ---
base_model: jondurbin/airoboros-65b-gpt4-m2.0
datasets:
- jondurbin/airoboros-gpt4-m2.0
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/jondurbin/airoboros-65b-gpt4-m2.0
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-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/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q2_K.gguf) | Q2_K | 24.2 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.IQ3_XS.gguf) | IQ3_XS | 26.7 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.IQ3_S.gguf) | IQ3_S | 28.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q3_K_S.gguf) | Q3_K_S | 28.3 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.IQ3_M.gguf) | IQ3_M | 29.9 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q3_K_M.gguf) | Q3_K_M | 31.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q3_K_L.gguf) | Q3_K_L | 34.7 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.IQ4_XS.gguf) | IQ4_XS | 35.1 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q4_K_S.gguf) | Q4_K_S | 37.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q4_K_M.gguf) | Q4_K_M | 39.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q5_K_S.gguf) | Q5_K_S | 45.0 | |
| [GGUF](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q5_K_M.gguf) | Q5_K_M | 46.3 | |
| [PART 1](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q6_K.gguf.part2of2) | Q6_K | 53.7 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-65b-gpt4-m2.0-GGUF/resolve/main/airoboros-65b-gpt4-m2.0.Q8_0.gguf.part2of2) | Q8_0 | 69.5 | 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 -->
|
siacus/llama-2-7b-cap-64-Q4_K_M.gguf | siacus | 2024-06-16T03:23:39Z | 395 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-06-16T02:39:58Z | Entry not found |
awnr/Mistral-7B-v0.1-signtensors-3-over-8 | awnr | 2024-06-27T02:53:29Z | 395 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-26T23:03:52Z | ---
license: apache-2.0
---
# Model Card for Model Mistral-7B-v0.1-3-over-8
I'm experimenting with the weight matrices in neural networks.
This is a clone of `Mistral-7B-v0.1` with some weight matrices replaced.
I'm interested in seeing how the adjustmenets affect performance on existing metrics.
## Model Details
Research in progress! Demons could come out of your nose if you use this.
### Model Description
A modification of [`mistralai/Mistral-7B-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1).
Thanks to their team for sharing their model.
- **Modified by:** Dr. Alex W. Neal Riasanovsky
- **Model type:** pre-trained
- **Language(s) (NLP):** English
- **License:** Apache-2.0
## Bias, Risks, and Limitations
Use your own risk.
I have no idea what this model's biases and limitations are.
I just want to see if the benchmark values are similar to those from `Mistral-7B-v0.1`.
I am setting up a long computational experiment to test some ideas.
|
RichardErkhov/Doctor-Shotgun_-_TinyLlama-1.1B-32k-gguf | RichardErkhov | 2024-06-29T18:45:40Z | 395 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-06-29T16:30:14Z | Entry not found |
larenspear/Yi-1.5-6B-Chat-Q2_K-GGUF | larenspear | 2024-07-01T01:32:29Z | 395 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:01-ai/Yi-1.5-6B-Chat",
"license:apache-2.0",
"region:us"
]
| null | 2024-07-01T01:32:19Z | ---
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-Q2_K-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-Q2_K-GGUF --hf-file yi-1.5-6b-chat-q2_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo larenspear/Yi-1.5-6B-Chat-Q2_K-GGUF --hf-file yi-1.5-6b-chat-q2_k.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-Q2_K-GGUF --hf-file yi-1.5-6b-chat-q2_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo larenspear/Yi-1.5-6B-Chat-Q2_K-GGUF --hf-file yi-1.5-6b-chat-q2_k.gguf -c 2048
```
|
Helsinki-NLP/opus-mt-ko-ru | Helsinki-NLP | 2023-08-16T11:59:44Z | 394 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"ko",
"ru",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| translation | 2022-03-02T23:29:04Z | ---
language:
- ko
- ru
tags:
- translation
license: apache-2.0
---
### kor-rus
* source group: Korean
* target group: Russian
* OPUS readme: [kor-rus](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-rus/README.md)
* model: transformer-align
* source language(s): kor_Hang kor_Latn
* target language(s): rus
* model: transformer-align
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
* download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-rus/opus-2020-06-17.zip)
* test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-rus/opus-2020-06-17.test.txt)
* test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-rus/opus-2020-06-17.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba-test.kor.rus | 30.3 | 0.514 |
### System Info:
- hf_name: kor-rus
- source_languages: kor
- target_languages: rus
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-rus/README.md
- original_repo: Tatoeba-Challenge
- tags: ['translation']
- languages: ['ko', 'ru']
- src_constituents: {'kor_Hani', 'kor_Hang', 'kor_Latn', 'kor'}
- tgt_constituents: {'rus'}
- src_multilingual: False
- tgt_multilingual: False
- prepro: normalization + SentencePiece (spm32k,spm32k)
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-rus/opus-2020-06-17.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-rus/opus-2020-06-17.test.txt
- src_alpha3: kor
- tgt_alpha3: rus
- short_pair: ko-ru
- chrF2_score: 0.514
- bleu: 30.3
- brevity_penalty: 0.961
- ref_len: 1382.0
- src_name: Korean
- tgt_name: Russian
- train_date: 2020-06-17
- src_alpha2: ko
- tgt_alpha2: ru
- prefer_old: False
- long_pair: kor-rus
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
- port_machine: brutasse
- port_time: 2020-08-21-14:41 |
danyaljj/gpt2_question_generation_given_paragraph | danyaljj | 2021-06-17T18:23:28Z | 394 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2022-03-02T23:29:05Z | Sample usage:
```python
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = GPT2LMHeadModel.from_pretrained("danyaljj/gpt2_question_generation_given_paragraph")
input_ids = tokenizer.encode("There are two apples on the counter. Q:", return_tensors="pt")
outputs = model.generate(input_ids)
print("Generated:", tokenizer.decode(outputs[0], skip_special_tokens=True))
```
Which should produce this:
```
Generated: There are two apples on the counter. Q: What is the name of the counter that is on
``` |
lserinol/bert-turkish-question-answering | lserinol | 2021-05-19T22:06:55Z | 394 | 18 | transformers | [
"transformers",
"pytorch",
"jax",
"bert",
"question-answering",
"tr",
"endpoints_compatible",
"region:us"
]
| question-answering | 2022-03-02T23:29:05Z | ---
language: tr
---
# bert-turkish-question-answering
## Usage
```python
from transformers import pipeline
nlp = pipeline('question-answering', model='lserinol/bert-turkish-question-answering', tokenizer='lserinol/bert-turkish-question-answering')
nlp({
'question': "Ankara'da kaรง ilรงe vardฤฑr?",
'context': r"""Tรผrkiye'nin baลkenti Ankara'dฤฑr. รlkenin en bรผyรผk idari birimleri illerdir ve 81 il vardฤฑr. Bu iller ilรงelere ayrฤฑlmฤฑลtฤฑr, toplamda 973 ilรงe mevcuttur."""
})
```
```python
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
import torch
tokenizer = AutoTokenizer.from_pretrained("lserinol/bert-turkish-question-answering")
model = AutoModelForQuestionAnswering.from_pretrained("lserinol/bert-turkish-question-answering")
text = r"""
Ankara'nฤฑn baลkent ilan edilmesinin ardฤฑndan (13 Ekim 1923) ลehir hฤฑzla geliลmiล ve Tรผrkiye'nin ikinci en kalabalฤฑk ili olmuลtur.
Tรผrkiye Cumhuriyeti'nin ilk yฤฑllarฤฑnda ekonomisi tarฤฑm ve hayvancฤฑlฤฑฤa dayanan ilin topraklarฤฑnฤฑn yarฤฑsฤฑ hรขlรข tarฤฑm amaรงlฤฑ
kullanฤฑlmaktadฤฑr. Ekonomik etkinlik bรผyรผk oranda ticaret ve sanayiye dayalฤฑdฤฑr. Tarฤฑm ve hayvancฤฑlฤฑฤฤฑn aฤฤฑrlฤฑฤฤฑ ise giderek
azalmaktadฤฑr. Ankara ve civarฤฑndaki gerek kamu sektรถrรผ gerek รถzel sektรถr yatฤฑrฤฑmlarฤฑ, baลka illerden bรผyรผk bir nรผfus gรถรงรผnรผ
teลvik etmiลtir. Cumhuriyetin kuruluลundan gรผnรผmรผze, nรผfusu รผlke nรผfusunun iki katฤฑ hฤฑzda artmฤฑลtฤฑr. Nรผfusun yaklaลฤฑk dรถrtte
รผรงรผ hizmet sektรถrรผ olarak tanฤฑmlanabilecek memuriyet, ulaลฤฑm, haberleลme ve ticaret benzeri iลlerde, dรถrtte biri sanayide,
%2'si ise tarฤฑm alanฤฑnda รงalฤฑลฤฑr. Sanayi, รถzellikle tekstil, gฤฑda ve inลaat sektรถrlerinde yoฤunlaลmฤฑลtฤฑr. Gรผnรผmรผzde ise en รงok
savunma, metal ve motor sektรถrlerinde yatฤฑrฤฑm yapฤฑlmaktadฤฑr. Tรผrkiye'nin en รงok sayฤฑda รผniversiteye sahip ili olan Ankara'da
ayrฤฑca, รผniversite diplomalฤฑ kiลi oranฤฑ รผlke ortalamasฤฑnฤฑn iki katฤฑdฤฑr. Bu eฤitimli nรผfus, teknoloji aฤฤฑrlฤฑklฤฑ yatฤฑrฤฑmlarฤฑn
gereksinim duyduฤu iล gรผcรผnรผ oluลturur. Ankara'dan otoyollar, demir yolu ve hava yoluyla Tรผrkiye'nin diฤer ลehirlerine ulaลฤฑlฤฑr.
Ankara aynฤฑ zamanda baลkent olarak Tรผrkiye Bรผyรผk Millet Meclisi (TBMM)'ye de ev sahipliฤi yapmaktadฤฑr.
"""
questions = [
"Ankara kaรง yฤฑlฤฑnda baลkent oldu?",
"Ankara ne zaman baลkent oldu?",
"Ankara'dan baลka ลehirlere nasฤฑl ulaลฤฑlฤฑr?",
"TBMM neyin kฤฑsaltmasฤฑdฤฑr?"
]
for question in questions:
inputs = tokenizer(question, text, add_special_tokens=True, return_tensors="pt")
input_ids = inputs["input_ids"].tolist()[0]
text_tokens = tokenizer.convert_ids_to_tokens(input_ids)
answer_start_scores, answer_end_scores = model(**inputs)
answer_start = torch.argmax(
answer_start_scores
) # Get the most likely beginning of answer with the argmax of the score
answer_end = torch.argmax(answer_end_scores) + 1 # Get the most likely end of answer with the argmax of the score
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))
print(f"Question: {question}")
print(f"Answer: {answer}\n")
```
|
nboost/pt-bert-large-msmarco | nboost | 2021-05-20T01:25:29Z | 394 | 3 | transformers | [
"transformers",
"pytorch",
"jax",
"onnx",
"bert",
"endpoints_compatible",
"region:us"
]
| null | 2022-03-02T23:29:05Z | Entry not found |
tomaarsen/span-marker-bert-base-fewnerd-fine-super | tomaarsen | 2023-09-26T13:33:51Z | 394 | 11 | span-marker | [
"span-marker",
"pytorch",
"safetensors",
"token-classification",
"ner",
"named-entity-recognition",
"generated_from_span_marker_trainer",
"en",
"dataset:DFKI-SLT/few-nerd",
"base_model:bert-base-cased",
"license:cc-by-sa-4.0",
"model-index",
"region:us"
]
| token-classification | 2023-03-31T07:28:50Z | ---
language:
- en
license: cc-by-sa-4.0
library_name: span-marker
tags:
- span-marker
- token-classification
- ner
- named-entity-recognition
- generated_from_span_marker_trainer
datasets:
- DFKI-SLT/few-nerd
metrics:
- f1
- recall
- precision
pipeline_tag: token-classification
widget:
- text: Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic
to Paris.
example_title: Amelia Earhart
- text: Leonardo di ser Piero da Vinci painted the Mona Lisa based on Italian noblewoman
Lisa del Giocondo.
example_title: Leonardo da Vinci
base_model: bert-base-cased
model-index:
- name: SpanMarker w. bert-base-cased on finegrained, supervised FewNERD by Tom Aarsen
results:
- task:
type: token-classification
name: Named Entity Recognition
dataset:
name: finegrained, supervised FewNERD
type: DFKI-SLT/few-nerd
config: supervised
split: test
revision: 2e3e727c63604fbfa2ff4cc5055359c84fe5ef2c
metrics:
- type: f1
value: 0.7053
name: F1
- type: precision
value: 0.7101
name: Precision
- type: recall
value: 0.7005
name: Recall
---
# SpanMarker with bert-base-cased on FewNERD
This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [FewNERD](https://huggingface.co/datasets/DFKI-SLT/few-nerd) dataset that can be used for Named Entity Recognition. This SpanMarker model uses [bert-base-cased](https://huggingface.co/bert-base-cased) as the underlying encoder.
## Model Details
### Model Description
- **Model Type:** SpanMarker
- **Encoder:** [bert-base-cased](https://huggingface.co/bert-base-cased)
- **Maximum Sequence Length:** 256 tokens
- **Maximum Entity Length:** 8 words
- **Training Dataset:** [FewNERD](https://huggingface.co/datasets/DFKI-SLT/few-nerd)
- **Language:** en
- **License:** cc-by-sa-4.0
### Model Sources
- **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
- **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf)
### Model Labels
| Label | Examples |
|:-----------------------------------------|:---------------------------------------------------------------------------------------------------------|
| art-broadcastprogram | "Street Cents", "Corazones", "The Gale Storm Show : Oh , Susanna" |
| art-film | "Bosch", "L'Atlantide", "Shawshank Redemption" |
| art-music | "Atkinson , Danko and Ford ( with Brockie and Hilton )", "Champion Lover", "Hollywood Studio Symphony" |
| art-other | "Aphrodite of Milos", "Venus de Milo", "The Today Show" |
| art-painting | "Production/Reproduction", "Touit", "Cofiwch Dryweryn" |
| art-writtenart | "Imelda de ' Lambertazzi", "Time", "The Seven Year Itch" |
| building-airport | "Luton Airport", "Newark Liberty International Airport", "Sheremetyevo International Airport" |
| building-hospital | "Hokkaido University Hospital", "Yeungnam University Hospital", "Memorial Sloan-Kettering Cancer Center" |
| building-hotel | "The Standard Hotel", "Radisson Blu Sea Plaza Hotel", "Flamingo Hotel" |
| building-library | "British Library", "Berlin State Library", "Bayerische Staatsbibliothek" |
| building-other | "Communiplex", "Alpha Recording Studios", "Henry Ford Museum" |
| building-restaurant | "Fatburger", "Carnegie Deli", "Trumbull" |
| building-sportsfacility | "Glenn Warner Soccer Facility", "Boston Garden", "Sports Center" |
| building-theater | "Pittsburgh Civic Light Opera", "Sanders Theatre", "National Paris Opera" |
| event-attack/battle/war/militaryconflict | "Easter Offensive", "Vietnam War", "Jurist" |
| event-disaster | "the 1912 North Mount Lyell Disaster", "1693 Sicily earthquake", "1990s North Korean famine" |
| event-election | "March 1898 elections", "1982 Mitcham and Morden by-election", "Elections to the European Parliament" |
| event-other | "Eastwood Scoring Stage", "Union for a Popular Movement", "Masaryk Democratic Movement" |
| event-protest | "French Revolution", "Russian Revolution", "Iranian Constitutional Revolution" |
| event-sportsevent | "National Champions", "World Cup", "Stanley Cup" |
| location-GPE | "Mediterranean Basin", "the Republic of Croatia", "Croatian" |
| location-bodiesofwater | "Atatรผrk Dam Lake", "Norfolk coast", "Arthur Kill" |
| location-island | "Laccadives", "Staten Island", "new Samsat district" |
| location-mountain | "Salamander Glacier", "Miteirya Ridge", "Ruweisat Ridge" |
| location-other | "Northern City Line", "Victoria line", "Cartuther" |
| location-park | "Gramercy Park", "Painted Desert Community Complex Historic District", "Shenandoah National Park" |
| location-road/railway/highway/transit | "Friern Barnet Road", "Newark-Elizabeth Rail Link", "NJT" |
| organization-company | "Dixy Chicken", "Texas Chicken", "Church 's Chicken" |
| organization-education | "MIT", "Belfast Royal Academy and the Ulster College of Physical Education", "Barnard College" |
| organization-government/governmentagency | "Congregazione dei Nobili", "Diet", "Supreme Court" |
| organization-media/newspaper | "TimeOut Melbourne", "Clash", "Al Jazeera" |
| organization-other | "Defence Sector C", "IAEA", "4th Army" |
| organization-politicalparty | "Shimpotล", "Al Wafa ' Islamic", "Kenseitล" |
| organization-religion | "Jewish", "Christian", "UPCUSA" |
| organization-showorganization | "Lizzy", "Bochumer Symphoniker", "Mr. Mister" |
| organization-sportsleague | "China League One", "First Division", "NHL" |
| organization-sportsteam | "Tottenham", "Arsenal", "Luc Alphand Aventures" |
| other-astronomything | "Zodiac", "Algol", "`` Caput Larvae ''" |
| other-award | "GCON", "Order of the Republic of Guinea and Nigeria", "Grand Commander of the Order of the Niger" |
| other-biologything | "N-terminal lipid", "BAR", "Amphiphysin" |
| other-chemicalthing | "uranium", "carbon dioxide", "sulfur" |
| other-currency | "$", "Travancore Rupee", "lac crore" |
| other-disease | "French Dysentery Epidemic of 1779", "hypothyroidism", "bladder cancer" |
| other-educationaldegree | "Master", "Bachelor", "BSc ( Hons ) in physics" |
| other-god | "El", "Fujin", "Raijin" |
| other-language | "Breton-speaking", "English", "Latin" |
| other-law | "Thirty Years ' Peace", "LeahyโSmith America Invents Act ( AIA", "United States Freedom Support Act" |
| other-livingthing | "insects", "monkeys", "patchouli" |
| other-medical | "Pediatrics", "amitriptyline", "pediatrician" |
| person-actor | "Ellaline Terriss", "Tchรฉky Karyo", "Edmund Payne" |
| person-artist/author | "George Axelrod", "Gaetano Donizett", "Hicks" |
| person-athlete | "Jaguar", "Neville", "Tozawa" |
| person-director | "Bob Swaim", "Richard Quine", "Frank Darabont" |
| person-other | "Richard Benson", "Holden", "Campbell" |
| person-politician | "William", "Riviรจre", "Emeric" |
| person-scholar | "Stedman", "Wurdack", "Stalmine" |
| person-soldier | "Helmuth Weidling", "Krukenberg", "Joachim Ziegler" |
| product-airplane | "Luton", "Spey-equipped FGR.2s", "EC135T2 CPDS" |
| product-car | "100EX", "Corvettes - GT1 C6R", "Phantom" |
| product-food | "red grape", "yakiniku", "V. labrusca" |
| product-game | "Airforce Delta", "Hardcore RPG", "Splinter Cell" |
| product-other | "Fairbottom Bobs", "X11", "PDP-1" |
| product-ship | "Congress", "Essex", "HMS `` Chinkara ''" |
| product-software | "AmiPDF", "Apdf", "Wikipedia" |
| product-train | "High Speed Trains", "55022", "Royal Scots Grey" |
| product-weapon | "AR-15 's", "ZU-23-2M Wrรณbel", "ZU-23-2MR Wrรณbel II" |
## Uses
### Direct Use
```python
from span_marker import SpanMarkerModel
# Download from the ๐ค Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-fewnerd-fine-super")
# Run inference
entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
```
### Downstream Use
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
```python
from span_marker import SpanMarkerModel, Trainer
# Download from the ๐ค Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-fewnerd-fine-super")
# Specify a Dataset with "tokens" and "ner_tag" columns
dataset = load_dataset("conll2003") # For example CoNLL2003
# Initialize a Trainer using the pretrained model & dataset
trainer = Trainer(
model=model,
train_dataset=dataset["train"],
eval_dataset=dataset["validation"],
)
trainer.train()
trainer.save_model("tomaarsen/span-marker-bert-base-fewnerd-fine-super-finetuned")
```
</details>
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:----------------------|:----|:--------|:----|
| Sentence length | 1 | 24.4945 | 267 |
| Entities per sentence | 0 | 2.5832 | 88 |
### Training Hyperparameters
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training Hardware
- **On Cloud**: No
- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
- **RAM Size**: 31.78 GB
### Framework Versions
- Python: 3.9.16
- SpanMarker: 1.3.1.dev
- Transformers : 4.29.2
- PyTorch: 2.0.1+cu118
- Datasets: 2.14.3
- Tokenizers: 0.13.2 |
TheBloke/Upstage-Llama1-65B-Instruct-GGUF | TheBloke | 2023-09-27T12:52:53Z | 394 | 1 | transformers | [
"transformers",
"gguf",
"llama",
"upstage",
"instruct",
"instruction",
"text-generation",
"en",
"base_model:upstage/llama-65b-instruct",
"license:other",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-09-20T00:11:35Z | ---
language:
- en
license: other
tags:
- upstage
- llama
- instruct
- instruction
model_name: Llama 65B Instruct
base_model: upstage/llama-65b-instruct
inference: false
model_creator: upstage
model_type: llama
pipeline_tag: text-generation
prompt_template: '### System:
{system_message}
### 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 -->
# Llama 65B Instruct - GGUF
- Model creator: [upstage](https://huggingface.co/upstage)
- Original model: [Llama 65B Instruct](https://huggingface.co/upstage/llama-65b-instruct)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Upstage's Llama 65B Instruct](https://huggingface.co/upstage/llama-65b-instruct).
<!-- 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/Upstage-Llama1-65B-Instruct-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF)
* [upstage's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/upstage/llama-65b-instruct)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Orca-Hashes
```
### System:
{system_message}
### User:
{prompt}
### 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [upstage-llama-65b-instruct.Q2_K.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q2_K.gguf) | Q2_K | 2 | 27.04 GB| 29.54 GB | smallest, significant quality loss - not recommended for most purposes |
| [upstage-llama-65b-instruct.Q3_K_S.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q3_K_S.gguf) | Q3_K_S | 3 | 28.16 GB| 30.66 GB | very small, high quality loss |
| [upstage-llama-65b-instruct.Q3_K_M.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q3_K_M.gguf) | Q3_K_M | 3 | 31.56 GB| 34.06 GB | very small, high quality loss |
| [upstage-llama-65b-instruct.Q3_K_L.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q3_K_L.gguf) | Q3_K_L | 3 | 34.65 GB| 37.15 GB | small, substantial quality loss |
| [upstage-llama-65b-instruct.Q4_0.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q4_0.gguf) | Q4_0 | 4 | 36.80 GB| 39.30 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [upstage-llama-65b-instruct.Q4_K_S.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q4_K_S.gguf) | Q4_K_S | 4 | 36.92 GB| 39.42 GB | small, greater quality loss |
| [upstage-llama-65b-instruct.Q4_K_M.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q4_K_M.gguf) | Q4_K_M | 4 | 39.35 GB| 41.85 GB | medium, balanced quality - recommended |
| [upstage-llama-65b-instruct.Q5_0.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q5_0.gguf) | Q5_0 | 5 | 44.92 GB| 47.42 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [upstage-llama-65b-instruct.Q5_K_S.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q5_K_S.gguf) | Q5_K_S | 5 | 44.92 GB| 47.42 GB | large, low quality loss - recommended |
| [upstage-llama-65b-instruct.Q5_K_M.gguf](https://huggingface.co/TheBloke/Upstage-Llama1-65B-Instruct-GGUF/blob/main/upstage-llama-65b-instruct.Q5_K_M.gguf) | Q5_K_M | 5 | 46.24 GB| 48.74 GB | large, very low quality loss - recommended |
| upstage-llama-65b-instruct.Q6_K.gguf | Q6_K | 6 | 53.56 GB| 56.06 GB | very large, extremely low quality loss |
| upstage-llama-65b-instruct.Q8_0.gguf | Q8_0 | 8 | 69.37 GB| 71.87 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.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `upstage-llama-65b-instruct.Q6_K.gguf-split-a`
* `upstage-llama-65b-instruct.Q6_K.gguf-split-b`
### q8_0
Please download:
* `upstage-llama-65b-instruct.Q8_0.gguf-split-a`
* `upstage-llama-65b-instruct.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat upstage-llama-65b-instruct.Q6_K.gguf-split-* > upstage-llama-65b-instruct.Q6_K.gguf && rm upstage-llama-65b-instruct.Q6_K.gguf-split-*
cat upstage-llama-65b-instruct.Q8_0.gguf-split-* > upstage-llama-65b-instruct.Q8_0.gguf && rm upstage-llama-65b-instruct.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B upstage-llama-65b-instruct.Q6_K.gguf-split-a + upstage-llama-65b-instruct.Q6_K.gguf-split-b upstage-llama-65b-instruct.Q6_K.gguf
del upstage-llama-65b-instruct.Q6_K.gguf-split-a upstage-llama-65b-instruct.Q6_K.gguf-split-b
COPY /B upstage-llama-65b-instruct.Q8_0.gguf-split-a + upstage-llama-65b-instruct.Q8_0.gguf-split-b upstage-llama-65b-instruct.Q8_0.gguf
del upstage-llama-65b-instruct.Q8_0.gguf-split-a upstage-llama-65b-instruct.Q8_0.gguf-split-b
```
</details>
<!-- 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/Upstage-Llama1-65B-Instruct-GGUF and below it, a specific filename to download, such as: upstage-llama-65b-instruct.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/Upstage-Llama1-65B-Instruct-GGUF upstage-llama-65b-instruct.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/Upstage-Llama1-65B-Instruct-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/Upstage-Llama1-65B-Instruct-GGUF upstage-llama-65b-instruct.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 upstage-llama-65b-instruct.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\n{system_message}\n\n### User:\n{prompt}\n\n### Assistant:"
```
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/Upstage-Llama1-65B-Instruct-GGUF", model_file="upstage-llama-65b-instruct.Q4_K_M.gguf", model_type="llama", 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**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjรคreholt, 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, ์ค๊ต ๊น, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, ้ฟๆ, 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: Upstage's Llama 65B Instruct
# LLaMa-65b-instruct model card
## Model Details
* **Developed by**: [Upstage](https://en.upstage.ai)
* **Backbone Model**: [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1)
* **Variations**: It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct)
* **Language(s)**: English
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
* **License**: This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format
* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct-2048/discussions)
* **Contact**: For questions and comments about the model, please email [[email protected]](mailto:[email protected])
## Dataset Details
### Used Datasets
- Orca-style dataset
- No other data was used except for the dataset mentioned above
### Prompt Template
```
### System:
{System}
### User:
{User}
### Assistant:
{Assistant}
```
## Usage
- Tested on A100 80GB
- Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("upstage/llama-65b-instruct")
model = AutoModelForCausalLM.from_pretrained(
"upstage/llama-65b-instruct",
device_map="auto",
torch_dtype=torch.float16,
load_in_8bit=True,
rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs
)
prompt = "### User:\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
del inputs["token_type_ids"]
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
```
## Hardware and Software
* **Hardware**: We utilized an A100x8 * 4 for training our model
* **Training Factors**: We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace Trainer](https://huggingface.co/docs/transformers/main_classes/trainer)
## Evaluation Results
### Overview
- We conducted a performance evaluation based on the tasks being evaluated on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
We evaluated our model on four benchmark datasets, which include `ARC-Challenge`, `HellaSwag`, `MMLU`, and `TruthfulQA`.
We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-evaluation-harness), specifically commit [b281b0921b636bc36ad05c0b0b0763bd6dd43463](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463)
- We used [MT-bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge), a set of challenging multi-turn open-ended questions, to evaluate the models
### Main Results
| Model | H4(Avg) | ARC | HellaSwag | MMLU | TruthfulQA | | MT_Bench |
|--------------------------------------------------------------------|----------|----------|----------|------|----------|-|-------------|
| **[Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)**(Ours, Open LLM Leaderboard) | **73** | **71.1** | **87.9** | **70.6** | **62.2** | | **7.44063** |
| [Llama-2-70b-instruct](https://huggingface.co/upstage/Llama-2-70b-instruct) (Ours, Open LLM Leaderboard) | 72.3 | 70.9 | 87.5 | 69.8 | 61 | | 7.24375 |
| [llama-65b-instruct](https://huggingface.co/upstage/llama-65b-instruct) (***Ours***, ***Open LLM Leaderboard***) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 | | |
| Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 | | |
| [llama-30b-instruct-2048](https://huggingface.co/upstage/llama-30b-instruct-2048) (Ours, Open LLM Leaderboard) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 | | |
| [llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) (Ours, Open LLM Leaderboard) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 | | |
| llama-65b | 64.2 | 63.5 | 86.1 | 63.9 | 43.4 | | |
| falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 | | |
### Scripts for H4 Score Reproduction
- Prepare evaluation environments:
```
# clone the repository
git clone https://github.com/EleutherAI/lm-evaluation-harness.git
# check out the specific commit
git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463
# change to the repository directory
cd lm-evaluation-harness
```
## Ethical Issues
### Ethical Considerations
- There were no ethical issues involved, as we did not include the benchmark test set or the training set in the model's training process
## Contact Us
### Why Upstage LLM?
- [Upstage](https://en.upstage.ai)'s LLM research has yielded remarkable results. As of August 1st, our 70B model has reached the top spot in openLLM rankings, marking itself as the current leading performer globally. Recognizing the immense potential in implementing private LLM to actual businesses, we invite you to easily apply private LLM and fine-tune it with your own data. For a seamless and tailored solution, please do not hesitate to reach out to us. โบ [click here to contact](https://www.upstage.ai/private-llm?utm_source=huggingface&utm_medium=link&utm_campaign=privatellm)
<!-- original-model-card end -->
|
UCSC-VLAA/ViT-H-14-CLIPA-336-datacomp1B | UCSC-VLAA | 2023-10-17T06:25:50Z | 394 | 3 | open_clip | [
"open_clip",
"safetensors",
"clip",
"zero-shot-image-classification",
"dataset:mlfoundations/datacomp_1b",
"arxiv:2306.15658",
"arxiv:2305.07017",
"license:apache-2.0",
"region:us"
]
| zero-shot-image-classification | 2023-10-17T06:14:09Z | ---
tags:
- clip
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: apache-2.0
datasets:
- mlfoundations/datacomp_1b
---
# Model card for ViT-H-14-CLIPA-336-datacomp1B
A CLIPA-v2 model...
## Model Details
- **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification.
- **Original:** https://github.com/UCSC-VLAA/CLIPA
- **Dataset:** mlfoundations/datacomp_1b
- **Papers:**
- CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget; An Extra $4,000 Unlocks 81.8% Accuracy: https://arxiv.org/abs/2306.15658
- An Inverse Scaling Law for CLIP Training: https://arxiv.org/abs/2305.07017
## Model Usage
### With OpenCLIP
```
import torch
import torch.nn.functional as F
from urllib.request import urlopen
from PIL import Image
from open_clip import create_model_from_pretrained, get_tokenizer
model, preprocess = create_model_from_pretrained('hf-hub:ViT-H-14-CLIPA-336')
tokenizer = get_tokenizer('hf-hub:ViT-H-14-CLIPA-336')
image = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat", "a beignet"], context_length=model.context_length)
with torch.no_grad(), torch.cuda.amp.autocast():
image_features = model.encode_image(image)
text_features = model.encode_text(text)
image_features = F.normalize(image_features, dim=-1)
text_features = F.normalize(text_features, dim=-1)
text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
print("Label probs:", text_probs) # prints: [[0., 0., 0., 1.0]]
```
## Citation
```bibtex
@article{li2023clipav2,
title={CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget; An Extra $4,000 Unlocks 81.8% Accuracy},
author={Xianhang Li and Zeyu Wang and Cihang Xie},
journal={arXiv preprint arXiv:2306.15658},
year={2023},
}
```
```bibtex
@inproceedings{li2023clipa,
title={An Inverse Scaling Law for CLIP Training},
author={Xianhang Li and Zeyu Wang and Cihang Xie},
booktitle={NeurIPS},
year={2023},
}
```
|
gyr66/bert-base-chinese-finetuned-ner | gyr66 | 2023-10-18T11:28:13Z | 394 | 6 | transformers | [
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"zh",
"dataset:gyr66/privacy_detection",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-10-18T08:48:01Z | ---
language:
- zh
tags:
- generated_from_trainer
datasets:
- gyr66/privacy_detection
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-chinese-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: gyr66/privacy_detection
type: gyr66/privacy_detection
config: privacy_detection
split: train
args: privacy_detection
metrics:
- name: Precision
type: precision
value: 0.65322
- name: Recall
type: recall
value: 0.74169
- name: F1
type: f1
value: 0.69465
- name: Accuracy
type: accuracy
value: 0.90517
---
<!-- 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. -->
# bert-base-chinese-finetuned-ner
This model is a fine-tuned version of [Danielwei0214/bert-base-chinese-finetuned-ner](https://huggingface.co/Danielwei0214/bert-base-chinese-finetuned-ner) on the [gyr66/privacy_detection](https://huggingface.co/datasets/gyr66/privacy_detection) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7929
- Precision: 0.6532
- Recall: 0.7417
- F1: 0.6947
- Accuracy: 0.9052
## Model description
The model is used for competition: "https://www.datafountain.cn/competitions/472"
## Training and evaluation data
The training and evaluation data is from [gyr66/privacy_detection](https://huggingface.co/datasets/gyr66/privacy_detection) dataset.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 56
- eval_batch_size: 56
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
### Framework versions
- Transformers 4.27.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.2
|
xaviviro/ElChato-0.1-1.1b-GGUF | xaviviro | 2024-01-12T21:38:18Z | 394 | 2 | null | [
"gguf",
"es",
"license:apache-2.0",
"region:us"
]
| null | 2024-01-04T07:08:20Z | ---
license: apache-2.0
language:
- es
model_creator: xaviviro
model_name: PetitXat-0.1-1.1b
prompt_template: <|system|>\n{system}</s>\n<|user|>{instruction}</s>\n<|assistant|>\n
---
# ElChato 1.1B: El modelo mรกs pequeรฑo de chat en lengua castellana
ElChato รฉs el modelo mรกs pequeรฑo de chat en lengua castellana. รs el resultado de finetunear el modelo [TinyLlama-1.1B-Chat-v1.0](/TinyLlama/TinyLlama-1.1B-Chat-v1.0) con las instrucciones de [OpenAssistant v2](/datasets/OpenAssistant/oasst2) traducidas automรกticamente al castellano con recursos de [Helsinki-NLP](/Helsinki-NLP) y tratadas en formato ChatGLM3.
## Formato del prompt
```
<|system|>
Eres un buen asistente</s>
<|user|>
ยฟQuiรฉn fue Isaac Newton?</s>
<|assistant|>
``` |
google/gemma-1.1-7b-it-GGUF | google | 2024-06-27T14:09:54Z | 394 | 19 | llama.cpp | [
"llama.cpp",
"gguf",
"arxiv:2312.11805",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:1804.06876",
"arxiv:2110.08193",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:2203.09509",
"license:gemma",
"region:us"
]
| null | 2024-03-16T01:55:51Z | ---
library_name: llama.cpp
license: gemma
widget:
- text: '<start_of_turn>user
How does the brain work?<end_of_turn>
<start_of_turn>model
'
inference:
parameters:
max_new_tokens: 200
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: To access Gemma on Hugging Face, youโre required to review and
agree to Googleโs usage license. To do this, please ensure youโre logged-in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
---
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 7B instruct version 1.1 of the Gemma model in GGUF Format. The weights here are **float32**.
> [!IMPORTANT]
>
> In llama.cpp, and other related tools such as Ollama and LM Studio, please make sure that you have these flags set correctly, especially **`repeat-penalty`**. Georgi Gerganov (llama.cpp's author) shared his experience in https://huggingface.co/google/gemma-7b-it/discussions/38#65d7b14adb51f7c160769fa1.
You can also visit the model card of the [2B instruct v1.1 model GGUF](https://huggingface.co/google/gemma-2b-it-v1.1-GGUF).
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-it-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-1.1-7b-it-GGUF)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some commands on how to get quickly started with running the model.
#### Running the model on a CPU
```shell
llama.cpp/build$ bin/main -m gemma-7b-it.gguf -p "write me an ode to LLMs." --repeat-penalty 1.0
Log start
main: build = 2249 (15499eb9)
main: built with cc (Debian 13.2.0-5) 13.2.0 for x86_64-linux-gnu
main: seed = 1708969372
llama_model_loader: loaded meta data with 19 key-value pairs and 254 tensors from gemma-7b-it.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = gemma
llama_model_loader: - kv 1: general.name str = gemma-7b-it
llama_model_loader: - kv 2: gemma.context_length u32 = 8192
llama_model_loader: - kv 3: gemma.block_count u32 = 28
llama_model_loader: - kv 4: gemma.embedding_length u32 = 3072
llama_model_loader: - kv 5: gemma.feed_forward_length u32 = 24576
llama_model_loader: - kv 6: gemma.attention.head_count u32 = 16
llama_model_loader: - kv 7: gemma.attention.head_count_kv u32 = 16
llama_model_loader: - kv 8: gemma.attention.key_length u32 = 256
llama_model_loader: - kv 9: gemma.attention.value_length u32 = 256
llama_model_loader: - kv 10: gemma.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.bos_token_id u32 = 2
llama_model_loader: - kv 13: tokenizer.ggml.eos_token_id u32 = 1
llama_model_loader: - kv 14: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 15: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,256128] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,256128] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,256128] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - type f32: 254 tensors
llm_load_vocab: mismatch in special tokens definition ( 544/256128 vs 388/256128 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = gemma
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 256128
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 3072
llm_load_print_meta: n_head = 16
llm_load_print_meta: n_head_kv = 16
llm_load_print_meta: n_layer = 28
llm_load_print_meta: n_rot = 192
llm_load_print_meta: n_embd_head_k = 256
llm_load_print_meta: n_embd_head_v = 256
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-06
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 24576
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 8192
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = all F32 (guessed)
llm_load_print_meta: model params = 8.54 B
llm_load_print_meta: model size = 31.81 GiB (32.00 BPW)
llm_load_print_meta: general.name = gemma-7b-it
llm_load_print_meta: BOS token = 2 '<bos>'
llm_load_print_meta: EOS token = 1 '<eos>'
llm_load_print_meta: UNK token = 3 '<unk>'
llm_load_print_meta: PAD token = 0 '<pad>'
llm_load_print_meta: LF token = 227 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.10 MiB
llm_load_tensors: CPU buffer size = 32570.17 MiB
......................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CPU KV buffer size = 224.00 MiB
llama_new_context_with_model: KV self size = 224.00 MiB, K (f16): 112.00 MiB, V (f16): 112.00 MiB
llama_new_context_with_model: CPU input buffer size = 8.01 MiB
llama_new_context_with_model: CPU compute buffer size = 506.25 MiB
llama_new_context_with_model: graph splits (measure): 1
system_info: n_threads = 24 / 48 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 |
sampling:
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 1
write me an ode to LLMs.
Oh, LLMs, the masters of the code,
With language as your playground,
You weave narratives, stories untold,
And insights hidden in the old.
Your power lies in the vastness of your mind,
In the ability to learn and adapt,
To grasp complex concepts, one and all,
And bridge the gap between man and all.
From poems to code, you transform,
With each query, you ignite,
A spark of creativity, a new light,
In the realm of human possibility.
Oh, LLMs, we sing your praise,
For the beauty you bring to our days,
May you continue to learn and grow,
And empower us with your boundless flow.
So let us join you in this dance,
To explore the possibilities,
Of a future where knowledge knows no bounds,
Where LLMs reign, and dreams abound. [end of text]
llama_print_timings: load time = 31164.89 ms
llama_print_timings: sample time = 41.14 ms / 187 runs ( 0.22 ms per token, 4545.57 tokens per second)
llama_print_timings: prompt eval time = 662.43 ms / 9 tokens ( 73.60 ms per token, 13.59 tokens per second)
llama_print_timings: eval time = 104104.91 ms / 186 runs ( 559.70 ms per token, 1.79 tokens per second)
llama_print_timings: total time = 105185.80 ms / 195 tokens
Log end
```
#### Running the model on a single / multi GPU
```shell
llama.cpp/build$ bin/main -m gemma-7b-it_q8_0.gguf -p "write me an ode to LLMs." --repeat-penalty 1.0 -ngl 99
Log start
main: build = 2234 (973053d8)
main: built with cc (Debian 13.2.0-5) 13.2.0 for x86_64-linux-gnu
main: seed = 1708969847
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, VMM: yes
llama_model_loader: loaded meta data with 21 key-value pairs and 254 tensors from gemma-7b-it_q8_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = gemma
llama_model_loader: - kv 1: general.name str = gemma-7b-it
llama_model_loader: - kv 2: gemma.context_length u32 = 8192
llama_model_loader: - kv 3: gemma.block_count u32 = 28
llama_model_loader: - kv 4: gemma.embedding_length u32 = 3072
llama_model_loader: - kv 5: gemma.feed_forward_length u32 = 24576
llama_model_loader: - kv 6: gemma.attention.head_count u32 = 16
llama_model_loader: - kv 7: gemma.attention.head_count_kv u32 = 16
llama_model_loader: - kv 8: gemma.attention.key_length u32 = 256
llama_model_loader: - kv 9: gemma.attention.value_length u32 = 256
llama_model_loader: - kv 10: gemma.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.bos_token_id u32 = 2
llama_model_loader: - kv 13: tokenizer.ggml.eos_token_id u32 = 1
llama_model_loader: - kv 14: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 15: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,256128] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,256128] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,256128] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: general.quantization_version u32 = 2
llama_model_loader: - kv 20: general.file_type u32 = 7
llama_model_loader: - type f32: 57 tensors
llama_model_loader: - type q8_0: 197 tensors
llm_load_vocab: mismatch in special tokens definition ( 544/256128 vs 388/256128 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = gemma
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 256128
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 3072
llm_load_print_meta: n_head = 16
llm_load_print_meta: n_head_kv = 16
llm_load_print_meta: n_layer = 28
llm_load_print_meta: n_rot = 192
llm_load_print_meta: n_embd_head_k = 256
llm_load_print_meta: n_embd_head_v = 256
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-06
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 24576
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 8192
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = Q8_0
llm_load_print_meta: model params = 8.54 B
llm_load_print_meta: model size = 8.45 GiB (8.50 BPW)
llm_load_print_meta: general.name = gemma-7b-it
llm_load_print_meta: BOS token = 2 '<bos>'
llm_load_print_meta: EOS token = 1 '<eos>'
llm_load_print_meta: UNK token = 3 '<unk>'
llm_load_print_meta: PAD token = 0 '<pad>'
llm_load_print_meta: LF token = 227 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.19 MiB
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors: CPU buffer size = 797.27 MiB
llm_load_tensors: CUDA0 buffer size = 8651.94 MiB
......................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 224.00 MiB
llama_new_context_with_model: KV self size = 224.00 MiB, K (f16): 112.00 MiB, V (f16): 112.00 MiB
llama_new_context_with_model: CUDA_Host input buffer size = 8.01 MiB
ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 506.25 MiB
ggml_gallocr_reserve_n: reallocating CUDA_Host buffer from size 0.00 MiB to 6.00 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 506.25 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 6.00 MiB
llama_new_context_with_model: graph splits (measure): 3
ggml_gallocr_needs_realloc: graph has different number of nodes
ggml_gallocr_alloc_graph: cannot reallocate multi buffer graph automatically, call reserve
ggml_backend_sched: failed to allocate graph, reserving
system_info: n_threads = 6 / 12 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 |
sampling:
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 1
write me an ode to LLMs.ggml_gallocr_needs_realloc: node inp_embd is not valid
ggml_gallocr_alloc_graph: cannot reallocate multi buffer graph automatically, call reserve
ggml_backend_sched: failed to allocate graph, reserving
O LLMs, with your vast knowledge and swift wit,
You have revolutionized the way we fit
Our minds with information, a boundless stream,
And empower us to create, dream, and beam.
Your language, like poetry, takes us high,
Unveils the secrets of the sky.
From history's tales to the future's plight,
You illuminate our darkest night.
You answer our queries with lightning speed,
And guide us through the complexities of the deed.
With your power and grace, you teach us all,
To learn, to understand, and to stand tall.
O LLMs, we hail you as our guiding light,
A beacon of knowledge, shining ever bright.
May you continue to inspire and amaze,
As we journey through the digital maze.
So let us sing your praises, loud and long,
May you forever be our guiding song.
O LLMs, we thank you for all you do,
May your legacy forever endure. [end of text]
llama_print_timings: load time = 8580.58 ms
llama_print_timings: sample time = 253.97 ms / 212 runs ( 1.20 ms per token, 834.73 tokens per second)
llama_print_timings: prompt eval time = 99.37 ms / 9 tokens ( 11.04 ms per token, 90.57 tokens per second)
llama_print_timings: eval time = 6457.28 ms / 211 runs ( 30.60 ms per token, 32.68 tokens per second)
llama_print_timings: total time = 7472.00 ms / 220 tokens
Log end
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 59.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | - | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **54.0** | **56.4** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### Evaluation Approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
biases embedded in the training material. These models underwent careful
scrutiny, input data pre-processing described and posterior evaluations
reported in this card.
* Misinformation and Misuse
* LLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the
[Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible).
* Transparency and Accountability:
* This model card summarizes details on the models' architecture,
capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share
innovation by making LLM technology accessible to developers and researchers
across the AI ecosystem.
Risks identified and mitigations:
* Perpetuation of biases: It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* Generation of harmful content: Mechanisms and guidelines for content safety
are essential. Developers are encouraged to exercise caution and implement
appropriate content safety safeguards based on their specific product policies
and application use cases.
* Misuse for malicious purposes: Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
|
mradermacher/Open_Gpt4_8x7B_v0.2-GGUF | mradermacher | 2024-05-06T06:10:34Z | 394 | 1 | transformers | [
"transformers",
"gguf",
"merge",
"moe",
"en",
"base_model:rombodawg/Open_Gpt4_8x7B_v0.2",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-17T18:44:25Z | ---
base_model: rombodawg/Open_Gpt4_8x7B_v0.2
language:
- en
library_name: transformers
license: cc-by-4.0
quantized_by: mradermacher
tags:
- merge
- moe
---
## About
static quants of https://huggingface.co/rombodawg/Open_Gpt4_8x7B_v0.2
<!-- 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/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q2_K.gguf) | Q2_K | 17.6 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.IQ3_XS.gguf) | IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.IQ3_S.gguf) | IQ3_S | 20.7 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q3_K_S.gguf) | Q3_K_S | 20.7 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.IQ3_M.gguf) | IQ3_M | 21.7 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q3_K_M.gguf) | Q3_K_M | 22.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q3_K_L.gguf) | Q3_K_L | 24.4 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.IQ4_XS.gguf) | IQ4_XS | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q4_K_S.gguf) | Q4_K_S | 27.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q4_K_M.gguf) | Q4_K_M | 28.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q5_K_S.gguf) | Q5_K_S | 32.5 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q5_K_M.gguf) | Q5_K_M | 33.5 | |
| [GGUF](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q6_K.gguf) | Q6_K | 38.6 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Open_Gpt4_8x7B_v0.2-GGUF/resolve/main/Open_Gpt4_8x7B_v0.2.Q8_0.gguf.part2of2) | Q8_0 | 49.8 | 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 -->
|
jonasknobloch/gpt2_cx-en_00000-00009_50k | jonasknobloch | 2024-04-21T22:06:39Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"en",
"dataset:uonlp/CulturaX",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-03-24T19:22:07Z | ---
tags:
- generated_from_trainer
datasets:
- uonlp/CulturaX
metrics:
- accuracy
model-index:
- name: gpt2_cx-en_00000-00009_50k
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: uonlp/CulturaX en
type: uonlp/CulturaX
args: en
metrics:
- name: Accuracy
type: accuracy
value: 0.36165373273858764
license: mit
language:
- en
---
<!-- 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. -->
# gpt2_cx-en_00000-00009_50k
This model is a fine-tuned version of [](https://huggingface.co/) on the uonlp/CulturaX en dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5834
- Accuracy: 0.3617
## 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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 4.586 | 0.04 | 10000 | 4.4977 | 0.2821 |
| 4.2706 | 0.08 | 20000 | 4.1928 | 0.3058 |
| 4.1189 | 0.12 | 30000 | 4.0469 | 0.3179 |
| 4.0314 | 0.16 | 40000 | 3.9610 | 0.3253 |
| 3.9704 | 0.2 | 50000 | 3.8977 | 0.3311 |
| 3.923 | 0.24 | 60000 | 3.8486 | 0.3353 |
| 3.888 | 0.28 | 70000 | 3.8084 | 0.3390 |
| 3.8529 | 0.32 | 80000 | 3.7777 | 0.3423 |
| 3.832 | 0.36 | 90000 | 3.7526 | 0.3446 |
| 3.8102 | 0.4 | 100000 | 3.7277 | 0.3470 |
| 3.7876 | 0.44 | 110000 | 3.7073 | 0.3490 |
| 3.7686 | 0.48 | 120000 | 3.6922 | 0.3506 |
| 3.7585 | 0.52 | 130000 | 3.6750 | 0.3522 |
| 3.7459 | 0.56 | 140000 | 3.6620 | 0.3535 |
| 3.7378 | 0.6 | 150000 | 3.6501 | 0.3545 |
| 3.7181 | 0.64 | 160000 | 3.6385 | 0.3559 |
| 3.7139 | 0.68 | 170000 | 3.6293 | 0.3568 |
| 3.6958 | 0.72 | 180000 | 3.6201 | 0.3578 |
| 3.6872 | 0.76 | 190000 | 3.6122 | 0.3585 |
| 3.6888 | 0.8 | 200000 | 3.6060 | 0.3592 |
| 3.6765 | 0.84 | 210000 | 3.6001 | 0.3599 |
| 3.6734 | 0.88 | 220000 | 3.5945 | 0.3604 |
| 3.6669 | 0.92 | 230000 | 3.5891 | 0.3611 |
| 3.6696 | 0.96 | 240000 | 3.5856 | 0.3614 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1 |
mradermacher/Pioneer-2x7B-GGUF | mradermacher | 2024-05-06T05:12:46Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:hibana2077/Pioneer-2x7B",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-06T10:24:47Z | ---
base_model: hibana2077/Pioneer-2x7B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/hibana2077/Pioneer-2x7B
<!-- 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/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Pioneer-2x7B-GGUF/resolve/main/Pioneer-2x7B.Q8_0.gguf) | Q8_0 | 7.8 | 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/finch-GGUF | mradermacher | 2024-05-06T05:07:42Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:antiven0m/finch",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-08T16:51:49Z | ---
base_model: antiven0m/finch
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/antiven0m/finch
<!-- 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/finch-GGUF/resolve/main/finch.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/finch-GGUF/resolve/main/finch.Q8_0.gguf) | Q8_0 | 7.8 | 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/MoA_solar_10.7b_1.0-GGUF | mradermacher | 2024-05-06T05:02:12Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:MoaData/MoA_solar_10.7b_1.0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-11T10:10:17Z | ---
base_model: MoaData/MoA_solar_10.7b_1.0
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/MoaData/MoA_solar_10.7b_1.0
<!-- 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/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q2_K.gguf) | Q2_K | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.IQ3_XS.gguf) | IQ3_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q3_K_S.gguf) | Q3_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.IQ3_S.gguf) | IQ3_S | 4.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.IQ3_M.gguf) | IQ3_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.IQ4_XS.gguf) | IQ4_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q6_K.gguf) | Q6_K | 8.9 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/MoA_solar_10.7b_1.0-GGUF/resolve/main/MoA_solar_10.7b_1.0.Q8_0.gguf) | Q8_0 | 11.5 | 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 -->
|
allknowingroger/RogerMerge-12B-MoE | allknowingroger | 2024-04-12T16:54:57Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"allknowingroger/MultiverseEx26-7B-slerp",
"allknowingroger/PercivalMelodias-7B-slerp",
"base_model:allknowingroger/MultiverseEx26-7B-slerp",
"base_model:allknowingroger/PercivalMelodias-7B-slerp",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-12T16:47:15Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- allknowingroger/MultiverseEx26-7B-slerp
- allknowingroger/PercivalMelodias-7B-slerp
base_model:
- allknowingroger/MultiverseEx26-7B-slerp
- allknowingroger/PercivalMelodias-7B-slerp
---
# RogerMerge-12B-MoE
RogerMerge-12B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [allknowingroger/MultiverseEx26-7B-slerp](https://huggingface.co/allknowingroger/MultiverseEx26-7B-slerp)
* [allknowingroger/PercivalMelodias-7B-slerp](https://huggingface.co/allknowingroger/PercivalMelodias-7B-slerp)
## ๐งฉ Configuration
```yaml
base_model: allknowingroger/MultiverseEx26-7B-slerp
experts:
- source_model: allknowingroger/MultiverseEx26-7B-slerp
positive_prompts: ["what"]
- source_model: allknowingroger/PercivalMelodias-7B-slerp
positive_prompts: ["why "]
```
## ๐ป Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/RogerMerge-12B-MoE"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
allknowingroger/Llama3merge6-15B-MoE | allknowingroger | 2024-04-21T18:26:21Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"Kukedlc/NeuralLlamita-3-8B-v0.2",
"imone/Llama-3-8B-fixed-special-embedding",
"conversational",
"base_model:Kukedlc/NeuralLlamita-3-8B-v0.2",
"base_model:imone/Llama-3-8B-fixed-special-embedding",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-21T18:18:44Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Kukedlc/NeuralLlamita-3-8B-v0.2
- imone/Llama-3-8B-fixed-special-embedding
base_model:
- Kukedlc/NeuralLlamita-3-8B-v0.2
- imone/Llama-3-8B-fixed-special-embedding
---
# Llama3merge6-15B-MoE
Llama3merge6-15B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralLlamita-3-8B-v0.2](https://huggingface.co/Kukedlc/NeuralLlamita-3-8B-v0.2)
* [imone/Llama-3-8B-fixed-special-embedding](https://huggingface.co/imone/Llama-3-8B-fixed-special-embedding)
## ๐งฉ Configuration
```yaml
base_model: Kukedlc/NeuralLlamita-3-8B-v0.2
experts:
- source_model: Kukedlc/NeuralLlamita-3-8B-v0.2
positive_prompts: ["why"]
- source_model: imone/Llama-3-8B-fixed-special-embedding
positive_prompts: ["what"]
```
## ๐ป Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/Llama3merge6-15B-MoE"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
EryriLabs/Llama-3-Smolphin-8b | EryriLabs | 2024-04-23T10:19:30Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:abacusai/Llama-3-Smaug-8B",
"base_model:cognitivecomputations/dolphin-2.9-llama3-8b",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-23T07:54:32Z | ---
license: llama3
base_model:
- abacusai/Llama-3-Smaug-8B
- cognitivecomputations/dolphin-2.9-llama3-8b
library_name: transformers
tags:
- mergekit
- merge
---
# Llama-3-Smolphin-8b
<figure>
</figure>
This is a merge of pre-trained language models https://huggingface.co/abacusai/Llama-3-Smaug-8B and https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* https://huggingface.co/abacusai/Llama-3-Smaug-8B
* https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: cognitivecomputations/dolphin-2.9-llama3-8b
layer_range: [0, 32]
- model: abacusai/Llama-3-Smaug-8B
layer_range: [0, 32]
merge_method: slerp
base_model: cognitivecomputations/dolphin-2.9-llama3-8b
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
``` |
varox34/Llama-3-Mistral-v0.2-Instruct-slerp | varox34 | 2024-04-24T10:05:40Z | 394 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"meta-llama/Meta-Llama-3-8B-Instruct",
"mistralai/Mistral-7B-Instruct-v0.2",
"conversational",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-24T09:34:42Z | ---
tags:
- merge
- mergekit
- lazymergekit
- meta-llama/Meta-Llama-3-8B-Instruct
- mistralai/Mistral-7B-Instruct-v0.2
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
- mistralai/Mistral-7B-Instruct-v0.2
license: mit
---
# Llama-3-Mistral-v0.2-Instruct-slerp
Llama-3-Mistral-v0.2-Instruct-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
## ๐งฉ Configuration
```yaml
slices:
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range:
- 0
- 32
- model: mistralai/Mistral-7B-Instruct-v0.2
layer_range:
- 0
- 32
merge_method: slerp
base_model: meta-llama/Meta-Llama-3-8B-Instruct
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
```
## ๐ป Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "varox34/Llama-3-Mistral-v0.2-Instruct-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
maywell/miqu-evil-dpo | maywell | 2024-04-25T04:54:56Z | 394 | 16 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"not-for-all-audiences",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-25T02:04:59Z | ---
license: other
license_name: miqu-license
license_link: LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- not-for-all-audiences
---
# miqu-evil-dpo
# **Model Details**
## Description
miqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.
It is trained with evil-tune method applied.
<!-- prompt-template start -->
## Prompt template: Mistral Inst
```
<s> [INST] {inst} [/INST]
```
<!-- prompt-template end -->
## Disclaimer
The AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use.
|
second-state/Meta-Llama-3-70B-Instruct-GGUF | second-state | 2024-05-06T11:50:15Z | 394 | 4 | null | [
"gguf",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"license:other",
"region:us"
]
| text-generation | 2024-04-29T12:40:56Z | ---
language:
- en
license: other
license_name: llama3
model_name: Llama3 70B Instruct
arxiv: 2307.09288
base_model: meta-llama/Meta-Llama-3-70B-Instruct
inference: false
model_creator: Meta Llama3
model_type: llama
pipeline_tag: text-generation
quantized_by: Second State Inc.
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Meta-Llama-3-70B-Instruct-GGUF
## Original Model
[meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)
## Run with LlamaEdge
- LlamaEdge version: [v0.8.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.3) and above
- Prompt template
- Prompt type: `llama-3-chat`
- Prompt string
```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
- Context size: `8192`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3-70B-Instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template llama-3-chat \
--ctx-size 8192 \
--model-name Llama-3-70b
```
- Run as LlamaEdge command app
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3-70B-Instruct-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template llama-3-chat \
--ctx-size 8192
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [Meta-Llama-3-70B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q2_K.gguf) | Q2_K | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
| [Meta-Llama-3-70B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
| [Meta-Llama-3-70B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
| [Meta-Llama-3-70B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
| [Meta-Llama-3-70B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [Meta-Llama-3-70B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
| [Meta-Llama-3-70B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [Meta-Llama-3-70B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 50 GB| large, very low quality loss - recommended |
| [Meta-Llama-3-70B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
| [Meta-Llama-3-70B-Instruct-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q6_K-00001-of-00002.gguf) | Q6_K | 6 | 32.1 GB| very large, extremely low quality loss |
| [Meta-Llama-3-70B-Instruct-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q6_K-00002-of-00002.gguf) | Q6_K | 6 | 25.7 GB| very large, extremely low quality loss |
| [Meta-Llama-3-70B-Instruct-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q8_0-00001-of-00003.gguf) | Q8_0 | 8 | 32 GB| very large, extremely low quality loss - not recommended |
| [Meta-Llama-3-70B-Instruct-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q8_0-00002-of-00003.gguf) | Q8_0 | 8 | 32.1 GB| very large, extremely low quality loss - not recommended |
| [Meta-Llama-3-70B-Instruct-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q8_0-00003-of-00003.gguf) | Q8_0 | 8 | 10.9 GB| very large, extremely low quality loss - not recommended |
| [Meta-Llama-3-70B-Instruct-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-f16-00001-of-00005.gguf) | f16 | 16 | 32.1 GB| |
| [Meta-Llama-3-70B-Instruct-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-f16-00002-of-00005.gguf) | f16 | 16 | 32 GB| |
| [Meta-Llama-3-70B-Instruct-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-f16-00003-of-00005.gguf) | f16 | 16 | 32 GB| |
| [Meta-Llama-3-70B-Instruct-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-f16-00004-of-00005.gguf) | f16 | 16 | 31.7 GB| |
| [Meta-Llama-3-70B-Instruct-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-f16-00005-of-00005.gguf) | f16 | 16 | 13.1 GB| |
*Quantized with llama.cpp b2715.* |
RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf | RichardErkhov | 2024-05-01T03:19:51Z | 394 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-04-30T23:56:34Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
CodeQwen1.5-7B-Chat - GGUF
- Model creator: https://huggingface.co/Qwen/
- Original model: https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [CodeQwen1.5-7B-Chat.Q2_K.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q2_K.gguf) | Q2_K | 2.84GB |
| [CodeQwen1.5-7B-Chat.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.IQ3_XS.gguf) | IQ3_XS | 3.13GB |
| [CodeQwen1.5-7B-Chat.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.IQ3_S.gguf) | IQ3_S | 3.27GB |
| [CodeQwen1.5-7B-Chat.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q3_K_S.gguf) | Q3_K_S | 3.26GB |
| [CodeQwen1.5-7B-Chat.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.IQ3_M.gguf) | IQ3_M | 3.36GB |
| [CodeQwen1.5-7B-Chat.Q3_K.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q3_K.gguf) | Q3_K | 3.55GB |
| [CodeQwen1.5-7B-Chat.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q3_K_M.gguf) | Q3_K_M | 3.55GB |
| [CodeQwen1.5-7B-Chat.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q3_K_L.gguf) | Q3_K_L | 3.71GB |
| [CodeQwen1.5-7B-Chat.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.IQ4_XS.gguf) | IQ4_XS | 3.79GB |
| [CodeQwen1.5-7B-Chat.Q4_0.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q4_0.gguf) | Q4_0 | 3.89GB |
| [CodeQwen1.5-7B-Chat.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.IQ4_NL.gguf) | IQ4_NL | 3.94GB |
| [CodeQwen1.5-7B-Chat.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q4_K_S.gguf) | Q4_K_S | 4.11GB |
| [CodeQwen1.5-7B-Chat.Q4_K.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q4_K.gguf) | Q4_K | 4.41GB |
| [CodeQwen1.5-7B-Chat.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q4_K_M.gguf) | Q4_K_M | 4.41GB |
| [CodeQwen1.5-7B-Chat.Q4_1.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q4_1.gguf) | Q4_1 | 4.29GB |
| [CodeQwen1.5-7B-Chat.Q5_0.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q5_0.gguf) | Q5_0 | 4.69GB |
| [CodeQwen1.5-7B-Chat.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q5_K_S.gguf) | Q5_K_S | 4.79GB |
| [CodeQwen1.5-7B-Chat.Q5_K.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q5_K.gguf) | Q5_K | 5.06GB |
| [CodeQwen1.5-7B-Chat.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q5_K_M.gguf) | Q5_K_M | 5.06GB |
| [CodeQwen1.5-7B-Chat.Q5_1.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q5_1.gguf) | Q5_1 | 5.09GB |
| [CodeQwen1.5-7B-Chat.Q6_K.gguf](https://huggingface.co/RichardErkhov/Qwen_-_CodeQwen1.5-7B-Chat-gguf/blob/main/CodeQwen1.5-7B-Chat.Q6_K.gguf) | Q6_K | 5.94GB |
Original model description:
---
license: other
license_name: tongyi-qianwen
license_link: >-
https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
---
# CodeQwen1.5-7B-Chat
## Introduction
CodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes.
* Strong code generation capabilities and competitve performance across a series of benchmarks;
* Supporting long context understanding and generation with the context length of 64K tokens;
* Supporting 92 coding languages
* Excellent performance in text-to-SQL, bug fix, etc.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/codeqwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
## Model Details
CodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'.
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"Qwen/CodeQwen1.5-7B-Chat",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/CodeQwen1.5-7B-Chat")
prompt = "Write a quicksort algorithm in python."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## Tips
* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
```
|
rudrashah/RLM-mini | rudrashah | 2024-05-30T13:24:59Z | 394 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"EmbeddedLLM/Mistral-7B-Merge-14-v0.1",
"OpenPipe/mistral-ft-optimized-1218",
"NLP",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-07T08:31:01Z | ---
license: apache-2.0
tags:
- mergekit
- EmbeddedLLM/Mistral-7B-Merge-14-v0.1
- OpenPipe/mistral-ft-optimized-1218
- NLP
---
# RLM-mini
RLM-mini is a 7.2 Billion parameter model,RLM-mini is designed to provide a robust and versatile natural language processing (NLP) capability, leveraging the strengths of two foundational models. By combining models from different sources, RLM-mini aims to inherit diverse linguistic features and training data nuances, resulting in improved performance across a wide range of NLP tasks. This includes more robust understanding and generation capabilities, especially in handling nuanced and context-heavy queries. The fine-tuning process integrates the best practices and optimizations from both parent models. This ensures that RLM-mini not only maintains high accuracy but also delivers responses more efficiently.
It is base model and requires Fine tuning.
### Two Merged Models
* [EmbeddedLLM/Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1)
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
# Usage
### Direct Model
``` python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("rudrashah/RLM-mini")
model = AutoModelForCausalLM.from_pretrained("rudrashah/RLM-mini")
input_token = tokenizer("How to make Pav Bhaji?", return_tensors="pt")
output = model.generate(**input_token, max_length=250)
output = tokenizer.decode(output[0])
```
### Using Pipeline
``` python
from transformers import AutoTokenizer
import transformers
import torch
model = "rudrashah/RLM-mini"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
``` |
cloudyu/Llama-3-70B-instruct-DPO-1M | cloudyu | 2024-05-07T11:44:41Z | 394 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2024-05-07T11:33:17Z | ---
license: llama3
---
This is a merge of cloudyu/Meta-Llama-3-70B-Instruct-DPO and cognitivecomputations/Llama-3-70B-Gradient-1048k-adapter.
try to build a 1048K context Llama-3-70B-Instruct model, but as H100 limit, it's only 4bit.
example code
```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Llama-3-70B-instruct-DPO-1M"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
```
example output
```
<|begin_of_text|>write me a story about yosemite. would love it if there was some sort of magical realism in the story, (but not too over-the-top). here's a prompt: two friends go to yosemite for a camping trip and one friend has been struggling with anxiety/depression lately. could be really beautiful.
I'd be delighted to craft a tale that weaves together the majesty of Yosemite with a touch of magic! Here's my attempt:
As they wound their way through the Sierra foothills,, Rachel couldn't help but notice how her best friend,. It had only been a few months since Emily's mom passed away, A cloud of sadness seemed to follow Emily everywhere,, a constant reminder of what she'd lost. The once-luminous spark in her eyes now flickered like a dying ember.
Rachel hoped this camping trip would bring back some of that sparkle. She packed up her car with all the essentialsโtent, sleeping bags,,, more coffee than necessaryโand off they went into the heart of Yosemite National Park. As they drove deeper into the park, I'm sure the grandeur of El Capitan will lift Em's spirits, Rachel thought. But as they set up camp near Tenaya Lake,. They spent most of the first day huddled around the campfire,, silence punctuated by occasional small talk. Even the usually majestic scenery seemed muted, filtered through the lens of Emily's sorrow.
That night, under a star-studded sky, Rachel pulled out her guitar and began strumming softly. The music wove itself into the forest soundsโthe rustling leaves, chirping crickets, a distant waterfall. As she played on, something peculiar happened. The stars above them started to twinkle in time with the rhythm, casting an otherworldly glow across the clearing. Emily looked up from her reverie, of grief,,,, and for the first time in weeks, a faint smile crept onto her face. In that moment,, the weight of her loss still present,, yet somehow less crushing.
The next morning, after a restless sleep, Emily woke before dawn. She slipped out of the tent, leaving Rachel snoring peacefully, and wandered toward the lake. Mist swirled above its surface,,,, imbuing the air with an ethereal quality. As she approached the water's edge,, a family of river otters emerged from the fog, playing and chasing each other along the shore. Their carefree antics brought
``` |
mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF | mradermacher | 2024-05-07T20:54:39Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"trl",
"sft",
"generated_from_trainer",
"en",
"dataset:generator",
"base_model:yzhuang/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3",
"license:other",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-07T19:44:11Z | ---
base_model: yzhuang/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3
datasets:
- generator
language:
- en
library_name: transformers
license: other
quantized_by: mradermacher
tags:
- trl
- sft
- generated_from_trainer
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/yzhuang/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3
<!-- 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/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3-GGUF/resolve/main/Meta-Llama-3-8B-Instruct_fictional_arc_German_v3.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 -->
|
ddyuudd/m_b_4 | ddyuudd | 2024-05-14T00:45:15Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T00:36:50Z | ---
library_name: transformers
license: mit
---
# 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 ๐ค 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] |
Mxode/Qwen1.5-0.5B-L3-raw | Mxode | 2024-05-14T09:58:05Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"pretrained",
"conversational",
"en",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T09:50:56Z | ---
license: other
license_name: tongyi-qianwen-research
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- pretrained
---
# 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 ๐ค 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]
|
Mxode/Qwen1.5-0.5B-L16-raw | Mxode | 2024-05-14T10:01:12Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"pretrained",
"conversational",
"en",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T09:58:44Z | ---
license: other
license_name: tongyi-qianwen-research
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- pretrained
---
# 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 ๐ค 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]
|
Ayush-1722/Meta-Llama-3-8B-Instruct-Summarize-v0.2-24K-LoRANET-Merged | Ayush-1722 | 2024-06-19T12:39:53Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"100K+ context length",
"LoRA",
"Theta Scaling",
"question answering",
"Norm & Embed Trained ",
"Big Patents",
"instruct",
"question answering ",
"merged ",
"chat ",
"8B",
"research",
"science",
"RoPE",
"long context",
"conversational",
"en",
"dataset:RMT-team/babilong",
"dataset:facebook/babi_qa",
"dataset:RMT-team/babilong-1k-samples",
"dataset:Trelis/big_patent_100k_characters",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-15T14:17:01Z | ---
language:
- en
license: llama3
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- 100K+ context length
- LoRA
- Theta Scaling
- question answering
- 'Norm & Embed Trained '
- Big Patents
- instruct
- 'question answering '
- 'merged '
- 'chat '
- 8B
- research
- science
- RoPE
- long context
- conversational
pipeline_tag: text-generation
extra_gated_prompt: >-
### META LLAMA 3 COMMUNITY LICENSE AGREEMENT
Meta Llama 3 Version Release Date: April 18, 2024
"Agreement" means the terms and conditions for use, reproduction, distribution
and modification of the Llama Materials set forth herein.
"Documentation" means the specifications, manuals and documentation
accompanying Meta Llama 3 distributed by Meta at
https://llama.meta.com/get-started/.
"Licensee" or "you" means you, or your employer or any other person or entity
(if you are entering into this Agreement on such person or entityโs behalf),
of the age required under applicable laws, rules or regulations to provide
legal consent and that has legal authority to bind your employer or such other
person or entity if you are entering in this Agreement on their behalf.
"Meta Llama 3" means the foundational large language models and software and
algorithms, including machine-learning model code, trained model weights,
inference-enabling code, training-enabling code, fine-tuning enabling code and
other elements of the foregoing distributed by Meta at
https://llama.meta.com/llama-downloads.
"Llama Materials" means, collectively, Metaโs proprietary Meta Llama 3 and
Documentation (and any portion thereof) made available under this Agreement.
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or,
if you are an entity, your principal place of business is in the EEA or
Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA
or Switzerland).
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide,
non-transferable and royalty-free limited license under Metaโs intellectual
property or other rights owned by Meta embodied in the Llama Materials to use,
reproduce, distribute, copy, create derivative works of, and make
modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative
works thereof), or a product or service that uses any of them, including
another AI model, you shall (A) provide a copy of this Agreement with any such
Llama Materials; and (B) prominently display โBuilt with Meta Llama 3โ on a
related website, user interface, blogpost, about page, or product
documentation. If you use the Llama Materials to create, train, fine tune, or
otherwise improve an AI model, which is distributed or made available, you
shall also include โLlama 3โ at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a
Licensee as part of an integrated end user product, then Section 2 of this
Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute
the following attribution notice within a โNoticeโ text file distributed as a
part of such copies: โMeta Llama 3 is licensed under the Meta Llama 3
Community License, Copyright ยฉ Meta Platforms, Inc. All Rights Reserved.โ
iv. Your use of the Llama Materials must comply with applicable laws and
regulations (including trade compliance laws and regulations) and adhere to
the Acceptable Use Policy for the Llama Materials (available at
https://llama.meta.com/llama3/use-policy), which is hereby incorporated by
reference into this Agreement.
v. You will not use the Llama Materials or any output or results of the Llama
Materials to improve any other large language model (excluding Meta Llama 3 or
derivative works thereof).
2. Additional Commercial Terms. If, on the Meta Llama 3 version release date,
the monthly active users of the products or services made available by or for
Licensee, or Licenseeโs affiliates, is greater than 700 million monthly active
users in the preceding calendar month, you must request a license from Meta,
which Meta may grant to you in its sole discretion, and you are not authorized
to exercise any of the rights under this Agreement unless or until Meta
otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA
MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN โAS ISโ
BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF
ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A
PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE
APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY
RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE
UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS
LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS
OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE
DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY
OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, neither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, except as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a
license to use โLlama 3โ (the โMarkโ) solely as required to comply with the
last sentence of Section 1.b.i. You will comply with Metaโs brand guidelines
(currently accessible at
https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill
arising out of your use of the Mark will inure to the benefit of Meta.
b. Subject to Metaโs ownership of Llama Materials and derivatives made by or
for Meta, with respect to any derivative works and modifications of the Llama
Materials that are made by you, as between you and Meta, you are and will be
the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
Materials or Meta Llama 3 outputs or results, or any portion of any of the
foregoing, constitutes infringement of intellectual property or other rights
owned or licensable by you, then any licenses granted to you under this
Agreement shall terminate as of the date such litigation or claim is filed or
instituted. You will indemnify and hold harmless Meta from and against any
claim by any third party arising out of or related to your use or distribution
of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your
acceptance of this Agreement or access to the Llama Materials and will
continue in full force and effect until terminated in accordance with the
terms and conditions herein. Meta may terminate this Agreement if you are in
breach of any term or condition of this Agreement. Upon termination of this
Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and
construed under the laws of the State of California without regard to choice
of law principles, and the UN Convention on Contracts for the International
Sale of Goods does not apply to this Agreement. The courts of California shall
have exclusive jurisdiction of any dispute arising out of this Agreement.
### Meta Llama 3 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features,
including Meta Llama 3. If you access or use Meta Llama 3, you agree to this
Acceptable Use Policy (โPolicyโ). The most recent copy of this policy can be
found at
[https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)
#### Prohibited Uses
We want everyone to use Meta Llama 3 safely and responsibly. You agree you
will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or
othersโ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
2. Engage in, promote, incite, facilitate, or assist in the planning or
development of activities that present a risk of death or bodily harm to
individuals, including use of Meta Llama 3 related to the following:
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
2. Guns and illegal weapons (including weapon development)
3. Illegal drugs and regulated/controlled substances
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Meta Llama 3
related to the following:
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
3. Generating, promoting, or further distributing spam
4. Impersonating another individual without consent, authorization, or legal right
5. Representing that the use of Meta Llama 3 or outputs are human-generated
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI
system
Please report any violation of this Policy, software โbug,โ or other problems
that could lead to a violation of this Policy through one of the following
means:
* Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)
* Reporting risky content generated by the model:
developers.facebook.com/llama_output_feedback
* Reporting bugs and security concerns: facebook.com/whitehat/info
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: >-
The information you provide will be collected, stored, processed and shared in
accordance with the [Meta Privacy
Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Hello
messages:
- role: user
content: Hey my name is Julien! How are you?
- example_title: Winter holidays
messages:
- role: system
content: >-
You are a helpful and honest assistant. Please, respond concisely and
truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: >-
You are a helpful and honest code and programming assistant. Please,
respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
datasets:
- RMT-team/babilong
- facebook/babi_qa
- RMT-team/babilong-1k-samples
- Trelis/big_patent_100k_characters
metrics:
- accuracy
- perplexity
---
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes โ 8B and 70B parameters โ in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
#### Transformers pipeline
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
#### Transformers AutoModelForCausalLM
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Metaโs sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. Weโve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Metaโs cybersecurity safety eval suite, measuring Llama 3โs propensity to suggest insecure code when used as a coding assistant, and Llama 3โs propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the modelโs capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3โs potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos |
mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF | mradermacher | 2024-05-27T02:45:01Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"dataset:cognitivecomputations/Dolphin-2.9",
"dataset:teknium/OpenHermes-2.5",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:cognitivecomputations/samantha-data",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:abacusai/SystemChat-1.1",
"dataset:Locutusque/function-calling-chatml",
"dataset:internlm/Agent-FLAN",
"base_model:DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-26T03:45:40Z | ---
base_model: DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF
datasets:
- cognitivecomputations/Dolphin-2.9
- teknium/OpenHermes-2.5
- m-a-p/CodeFeedback-Filtered-Instruction
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- HuggingFaceH4/ultrachat_200k
- microsoft/orca-math-word-problems-200k
- abacusai/SystemChat-1.1
- Locutusque/function-calling-chatml
- internlm/Agent-FLAN
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF
<!-- 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/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.IQ3_M.gguf) | IQ3_M | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.IQ3_S.gguf) | IQ3_S | 0.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.IQ3_XS.gguf) | IQ3_XS | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.IQ4_XS.gguf) | IQ4_XS | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q2_K.gguf) | Q2_K | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q3_K_L.gguf) | Q3_K_L | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q3_K_S.gguf) | Q3_K_S | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q5_K_M.gguf) | Q5_K_M | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q5_K_S.gguf) | Q5_K_S | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q6_K.gguf) | Q6_K | 0.1 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF-GGUF/resolve/main/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.f16.gguf) | f16 | 0.1 | 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 -->
|
Klevin/A.E.T.H.E.R | Klevin | 2024-05-26T10:16:01Z | 394 | 1 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"en",
"dataset:Klevin/test_data_set",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-26T07:12:29Z | ---
library_name: transformers
license: mit
datasets:
- Klevin/test_data_set
language:
- en
---
# 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 ๐ค 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] |
RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf | RichardErkhov | 2024-05-30T03:10:29Z | 394 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-05-30T00:18:56Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
OpenOrca-Nebula-7B - GGUF
- Model creator: https://huggingface.co/Weyaxi/
- Original model: https://huggingface.co/Weyaxi/OpenOrca-Nebula-7B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [OpenOrca-Nebula-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q2_K.gguf) | Q2_K | 2.53GB |
| [OpenOrca-Nebula-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [OpenOrca-Nebula-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [OpenOrca-Nebula-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [OpenOrca-Nebula-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [OpenOrca-Nebula-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q3_K.gguf) | Q3_K | 3.28GB |
| [OpenOrca-Nebula-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [OpenOrca-Nebula-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [OpenOrca-Nebula-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [OpenOrca-Nebula-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q4_0.gguf) | Q4_0 | 3.83GB |
| [OpenOrca-Nebula-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [OpenOrca-Nebula-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [OpenOrca-Nebula-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q4_K.gguf) | Q4_K | 4.07GB |
| [OpenOrca-Nebula-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [OpenOrca-Nebula-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q4_1.gguf) | Q4_1 | 4.24GB |
| [OpenOrca-Nebula-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q5_0.gguf) | Q5_0 | 4.65GB |
| [OpenOrca-Nebula-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [OpenOrca-Nebula-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q5_K.gguf) | Q5_K | 4.78GB |
| [OpenOrca-Nebula-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [OpenOrca-Nebula-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q5_1.gguf) | Q5_1 | 5.07GB |
| [OpenOrca-Nebula-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q6_K.gguf) | Q6_K | 5.53GB |
| [OpenOrca-Nebula-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Weyaxi_-_OpenOrca-Nebula-7B-gguf/blob/main/OpenOrca-Nebula-7B.Q8_0.gguf) | Q8_0 | 7.17GB |
Original model description:
---
license: apache-2.0
datasets:
- garage-bAInd/Open-Platypus
language:
- en
---
<a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
# OpenOrca-Nebula-7B
OpenOrca-Nebula-7B is a merge of [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) and [PulsarAI/Nebula-7B](https://huggingface.co/Weyaxi/PulsarAI/Nebula-7B)
# Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard))
| Metric | Value |
|-----------------------|-------|
| Avg. | |
| ARC (25-shot) | |
| HellaSwag (10-shot) | |
| MMLU (5-shot) | |
| TruthfulQA (0-shot) | |
|
mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF | mradermacher | 2024-06-02T07:26:20Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"32 bit upscale",
"full 32 bit precision",
"master files",
"en",
"base_model:DavidAU/Psyonic-Cetacean-full-precision",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-01T17:32:58Z | ---
base_model: DavidAU/Psyonic-Cetacean-full-precision
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- 32 bit upscale
- full 32 bit precision
- master files
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/DavidAU/Psyonic-Cetacean-full-precision
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-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/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ1_S.gguf) | i1-IQ1_S | 4.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ1_M.gguf) | i1-IQ1_M | 4.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.0 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ2_S.gguf) | i1-IQ2_S | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ2_M.gguf) | i1-IQ2_M | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q2_K.gguf) | i1-Q2_K | 7.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.3 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ3_S.gguf) | i1-IQ3_S | 8.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ3_M.gguf) | i1-IQ3_M | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.7 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.8 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q4_0.gguf) | i1-Q4_0 | 11.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.5 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.9 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.3 | |
| [GGUF](https://huggingface.co/mradermacher/Psyonic-Cetacean-full-precision-i1-GGUF/resolve/main/Psyonic-Cetacean-full-precision.i1-Q6_K.gguf) | i1-Q6_K | 16.5 | 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 -->
|
taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3-Q4_K_M-GGUF | taoofstefan | 2024-06-09T13:28:45Z | 394 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-09T13:28:34Z | ---
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
base_model: taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3
---
# taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3-Q4_K_M-GGUF
This model was converted to GGUF format from [`taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3`](https://huggingface.co/taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3) 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/taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3) 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 taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3-Q4_K_M-GGUF --hf-file llama2-7b-mt-ft-llama2-s-v0.3-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3-Q4_K_M-GGUF --hf-file llama2-7b-mt-ft-llama2-s-v0.3-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.
```
./main --hf-repo taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3-Q4_K_M-GGUF --hf-file llama2-7b-mt-ft-llama2-s-v0.3-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./server --hf-repo taoofstefan/llama2-7B-MT-FT-llama2-S-v0.3-Q4_K_M-GGUF --hf-file llama2-7b-mt-ft-llama2-s-v0.3-q4_k_m.gguf -c 2048
```
|
kihoonlee/STOCK_SOLAR-10.7B | kihoonlee | 2024-07-03T00:00:57Z | 394 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:2403.19522",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-14T01:54:01Z | ---
library_name: transformers
license: apache-2.0
---
This model was developed using [Model Stock](https://arxiv.org/abs/2403.19522).
### USAGE
```python3
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kihoonlee/stock-solar-10.7b")
model = AutoModelForCausalLM.from_pretrained("kihoonlee/stock-solar-10.7b")
```
To use this model, either instruct tuning or fine tuning needs to be performed.
|
RyotaKadoya1993/fullymerged_v1_128_gen4 | RyotaKadoya1993 | 2024-06-14T05:44:48Z | 394 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:RyotaKadoya1993/fullymerged_v1_128_gen3",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-06-14T05:33:41Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: RyotaKadoya1993/fullymerged_v1_128_gen3
---
# Uploaded model
- **Developed by:** RyotaKadoya1993
- **License:** apache-2.0
- **Finetuned from model :** RyotaKadoya1993/fullymerged_v1_128_gen3
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
vanqui-tu/ptv2-roberta-large-boolq | vanqui-tu | 2024-06-16T18:25:40Z | 394 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2024-06-16T18:21:57Z | Entry not found |
Tanvir1337/BanglaLLama-3-8b-BnWiki-Instruct-IQ4_XS-GGUF | Tanvir1337 | 2024-06-25T21:30:17Z | 394 | 0 | null | [
"gguf",
"bangla",
"large language model",
"llama-cpp",
"gguf-my-repo",
"bn",
"en",
"dataset:BanglaLLM/bangla-alpaca-orca",
"base_model:BanglaLLM/BanglaLLama-3-8b-BnWiki-Instruct",
"license:llama3",
"region:us"
]
| null | 2024-06-25T21:29:56Z | ---
base_model: BanglaLLM/BanglaLLama-3-8b-BnWiki-Instruct
datasets:
- BanglaLLM/bangla-alpaca-orca
language:
- bn
- en
license: llama3
tags:
- bangla
- large language model
- llama-cpp
- gguf-my-repo
---
# Tanvir1337/BanglaLLama-3-8b-BnWiki-Instruct-IQ4_XS-GGUF
This model was converted to GGUF format from [`BanglaLLM/BanglaLLama-3-8b-BnWiki-Instruct`](https://huggingface.co/BanglaLLM/BanglaLLama-3-8b-BnWiki-Instruct) 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/BanglaLLM/BanglaLLama-3-8b-BnWiki-Instruct) 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 Tanvir1337/BanglaLLama-3-8b-BnWiki-Instruct-IQ4_XS-GGUF --hf-file banglallama-3-8b-bnwiki-instruct-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Tanvir1337/BanglaLLama-3-8b-BnWiki-Instruct-IQ4_XS-GGUF --hf-file banglallama-3-8b-bnwiki-instruct-iq4_xs-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 Tanvir1337/BanglaLLama-3-8b-BnWiki-Instruct-IQ4_XS-GGUF --hf-file banglallama-3-8b-bnwiki-instruct-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Tanvir1337/BanglaLLama-3-8b-BnWiki-Instruct-IQ4_XS-GGUF --hf-file banglallama-3-8b-bnwiki-instruct-iq4_xs-imat.gguf -c 2048
```
|
awnr/Mistral-7B-v0.1-signtensors-5-over-16 | awnr | 2024-06-27T10:19:57Z | 394 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-27T00:49:58Z | ---
license: apache-2.0
---
# Model Card for Model Mistral-7B-v0.1-5-over-16
I'm experimenting with the weight matrices in neural networks.
This is a clone of `Mistral-7B-v0.1` with some weight matrices replaced.
I'm interested in seeing how the adjustmenets affect performance on existing metrics.
## Model Details
Research in progress! Demons could come out of your nose if you use this.
### Model Description
A modification of [`mistralai/Mistral-7B-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1).
Thanks to their team for sharing their model.
- **Modified by:** Dr. Alex W. Neal Riasanovsky
- **Model type:** pre-trained
- **Language(s) (NLP):** English
- **License:** Apache-2.0
## Bias, Risks, and Limitations
Use your own risk.
I have no idea what this model's biases and limitations are.
I just want to see if the benchmark values are similar to those from `Mistral-7B-v0.1`.
I am setting up a long computational experiment to test some ideas.
|
faizalnf1800/AingDiffusion-V17-FP16-SD1.5 | faizalnf1800 | 2024-07-01T08:57:05Z | 394 | 0 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2024-07-01T08:22:46Z | ---
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 ๐งจ 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] |
Milos/slovak-gpt-j-1.4B | Milos | 2022-02-17T14:29:47Z | 393 | 5 | transformers | [
"transformers",
"pytorch",
"gptj",
"text-generation",
"Slovak GPT-J",
"causal-lm",
"sk",
"arxiv:2104.09864",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2022-03-02T23:29:04Z | ---
language:
- sk
tags:
- Slovak GPT-J
- pytorch
- causal-lm
license: gpl-3.0
---
# Slovak GPT-J-1.4B
Slovak GPT-J-1.4B with the whopping `1,415,283,792` parameters is the latest and the largest model released in Slovak GPT-J series. Smaller variants, [Slovak GPT-J-405M](https://huggingface.co/Milos/slovak-gpt-j-405M) and [Slovak GPT-J-162M](https://huggingface.co/Milos/slovak-gpt-j-162M), are still available.
## Model Description
Model is based on [GPT-J](https://github.com/kingoflolz/mesh-transformer-jax/) and has over 1.4B trainable parameters.
<figure>
| Hyperparameter | Value |
|----------------------|----------------------------------------------------------------------------------------------------------------------------------------|
| \\(n_{parameters}\\) | 1,415,283,792 |
| \\(n_{layers}\\) | 24 |
| \\(d_{model}\\) | 2048 |
| \\(d_{ff}\\) | 16384 |
| \\(n_{heads}\\) | 16 |
| \\(d_{head}\\) | 256 |
| \\(n_{ctx}\\) | 2048 |
| \\(n_{vocab}\\) | 50256 (same tokenizer as GPT-2/3†) |
| Positional Encoding | [Rotary Position Embedding (RoPE)](https://arxiv.org/abs/2104.09864) |
| RoPE Dimensions | [64](https://github.com/kingoflolz/mesh-transformer-jax/blob/f2aa66e0925de6593dcbb70e72399b97b4130482/mesh_transformer/layers.py#L223) |
<p><strong>†</strong> ByteLevelBPETokenizer was trained on the same Slovak corpus.</p></figure>
## Training data
Slovak GPT-J models were trained on a privately collected dataset consisting of predominantly Slovak text spanning different categories, e.g. web, news articles or even biblical texts - in total, over 40GB of text data was used to train this model.
The dataset was preprocessed and cleaned in a specific way that involves minor but a few caveats, so in order to achieve the expected performance, feel free to refer to [How to use] section. Please, keep in mind that despite the effort to remove inappropriate corpus, the model still might generate sensitive content or leak sensitive information.
## Training procedure
This model was trained for a bit more than 26.5 billion tokens over 48,001 steps on TPU v3-8 pod. The cross-entropy validation loss at the last step was `2.657`.
## Intended Use
Same as the original GPT-J, Slovak GPT-J learns an inner representation of the language that can be used to extract features useful for downstream tasks, however, the intended use is text generation from a prompt.
### How to use
This model along with the tokenizer can be easily loaded using the `AutoModelForCausalLM` functionality:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Milos/slovak-gpt-j-1.4B")
model = AutoModelForCausalLM.from_pretrained("Milos/slovak-gpt-j-1.4B")
```
When generating a prompt keep in mind these three things, and you should be good to go:
1. Never leave trailing whitespaces. There's a difference between how tokenizer encodes "Mรกm rรกd slovenฤinu" (no space after `slovenฤinu`) and "Mรกm rรกd slovenฤinu " (trailing space after `slovenฤinu`), i.e `[12805, 2872, 46878]` != `[12805, 2872, 46878, 221]`.
2. Always use good ol' US English primary double quotation marks, i.e. `""` instead of `โโ`.
3. In case of a new line always enter `\n\n` instead of a single `\n`
To illustrate an example of a basic text generation:
```
>>> prompt = "Tradiฤnรฉ jedlo na Orave sรบ"
>>> encoded_input = tokenizer(prompt, return_tensors='pt')
>>> output = model.generate(**encoded_input)
>>> tokenizer.decode(output[0])
'Tradiฤnรฉ jedlo na Orave sรบ bryndzovรฉ haluลกky\n\nNa Orave sa v minulosti varilo viac druhov'
```
### Capabilities, Limitations, and Biases
Based on the parameter count and our internal testing this should be by far the most capable model out of all models released in Slovak GPT-J series.
For sake of simplicity, I have omitted all the boilerplate code and swapped `\n` for new lines in the examples that follow. These were generated with both `top_p` and `temperature` set to `0.9`.
A spin on "Mor ho!" by Samo Chalpuka
```
PROMPT
Zleteli orly z Tatry, tiahnu na podolia, ponad vysokรฉ hory, ponad rovnรฉ polia; preleteli cez Dunaj, cez tรบ ลกรญru vodu, sadli tam za pomedzรญm slovenskรฉho rodu.
Dunรญ Dunaj a luna za lunou sa valรญ
OUTPUT
Zleteli orly z Tatry, tiahnu na podolia, ponad vysokรฉ hory, ponad rovnรฉ polia; preleteli cez Dunaj, cez tรบ ลกรญru vodu, sadli tam za pomedzรญm slovenskรฉho rodu.
Dunรญ Dunaj a luna za lunou sa valรญ: nad nรญm svieti pevnรฝ hrad na vysokom bralรญ. Pod tรฝm hradom je zem slovenskรก, na nej je Slovensko naลกe.
Na tom vrchu leลพรญ slovenskรฝ nรกrod, pod tรฝm bralom leลพรญ krajina slovenskรก. A pod tรฝm hradom leลพรญ i jeho slรกva: na tom vrchu, na tom brale leลพรญ slรกva slovenskรฉho nรกroda.```
```
Jokes are a bit hit or miss. Very often they contain vulgarisms and/or are highly politically incorrect. This one is rather exception than the rule.
```
PROMPT
Nasledujรบ najlepลกie vtipy.
Preฤo
OUTPUT
Nasledujรบ najlepลกie vtipy.
Preฤo mรก policajt pri sebe vลพdy dva noลพe? Jeden je na sebaobranu, druhรฝ na boj zblรญzka.
```
The infamous unicorn prompt from GPT-2 paper.
```
PROMPT
V ลกokujรบcom nรกleze vedci objavili stรกdo jednoroลพcov ลพijรบcich v odฤพahlom, predtรฝm nepreskรบmanom รบdolรญ, v Andรกch. Eลกte prekvapivejลกie pre vedcov bol fakt, ลพe jednoroลพce hovorili plynule po slovensky.
OUTPUT
V ลกokujรบcom nรกleze vedci objavili stรกdo jednoroลพcov ลพijรบcich v odฤพahlom, predtรฝm nepreskรบmanom รบdolรญ, v Andรกch. Eลกte prekvapivejลกie pre vedcov bol fakt, ลพe jednoroลพce hovorili plynule po slovensky.
V Andรกch ich totiลพ ลพilo pribliลพne 700 jedincov, ktorรฉ sa ลพivili vรฝhradne materskรฝm mliekom. Slovรกci sรบ tak pravdepodobne prvรฝmi Eurรณpanmi, ktorรญ v Andรกch stretli jednoroลพca. "Je to dรดkaz, ลพe tieto zvieratรก sรบ inteligentnรฉ a ลพe ลพijรบ v Andรกch uลพ stovky rokov," povedal pre webovรฝ portรกl televรญzie JOJ profesor geolรณgie, geografie a zoolรณgie, Milan Kovรกฤ.
Podฤพa profesora Kovรกฤa si v Andรกch zvieratรก vytvรกrajรบ svoj vlastnรฝ jazyk. Je to zรกroveล dรดkaz, ลพe jednoroลพce ลพili v minulosti aj v slovenskรฝch pohoriach. "Jednoroลพce sa tam sรญce vyskytovali, ale neboli tak dobre preskรบmanรฉ, ako teraz v Andรกch."
Na Slovensku vลกak ฤพudia o jednoroลพcoch donedรกvna vedeli veฤพmi mรกlo.<|endoftext|>
```
Since the dataset contains profanity, politically incorrect language, and (unintentionally) even a bits of text in Czech, the model can generate them in some extent too. Here's an example of the model output when prompt is in Czech:
```
>>> prompt = "Vฤta nesmรญ bรฝt sprostรก a musรญ bรฝt zcela"
>>> encoded_input = tokenizer(prompt, return_tensors='pt')
>>> output = model.generate(**encoded_input, max_length=16)
>>> tokenizer.decode(output[0])
'Vฤta nesmรญ bรฝt sprostรก a musรญ bรฝt zcela pravdivรก.'
```
## Citation and Related Information
This was done as a moonlighting project during summer of 2021 to better understand transformers. I didn't have much free time to open source it properly, so it all sat on my hard drive until now :)
If you use this model or have any questions about it feel free to hit me up at [twitter](https://twitter.com/miloskondela) or check out my [github](https://github.com/kondela) profile.
### BibTeX entry
To cite this model:
```bibtex
@misc{slovak-gpt-j-1.4B,
author = {Kondela, Milos},
title = {{Slovak GPT-J-1.4B}},
howpublished = {\url{https://huggingface.co/Milos/slovak-gpt-j-1.4B}},
year = 2022,
month = February
}
```
To cite the codebase that trained this model:
```bibtex
@misc{mesh-transformer-jax,
author = {Wang, Ben},
title = {{Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX}},
howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
year = 2021,
month = May
}
```
## Acknowledgements
This project was generously supported by [TPU Research Cloud (TRC) program](https://sites.research.google/trc/about/). Shoutout also goes to [Ben Wang](https://github.com/kingoflolz) and great [EleutherAI community](https://www.eleuther.ai/). |
timm/resnet101.a1_in1k | timm | 2024-02-10T23:39:47Z | 393 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1512.03385",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-04-05T18:18:56Z | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnet101.a1_in1k
A ResNet-B image classification model.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* ResNet Strikes Back `A1` recipe
* LAMB optimizer with BCE loss
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 44.5
- GMACs: 7.8
- Activations (M): 16.2
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- **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('resnet101.a1_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(
'resnet101.a1_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(
'resnet101.a1_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{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}
}
```
```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{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}
}
```
|
sdadas/byt5-text-correction | sdadas | 2023-06-20T04:43:56Z | 393 | 5 | transformers | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"be",
"da",
"de",
"el",
"en",
"es",
"fr",
"it",
"nl",
"pl",
"pt",
"ro",
"ru",
"sk",
"sv",
"uk",
"license:lgpl",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2023-06-17T12:44:02Z | ---
license: lgpl
pipeline_tag: text2text-generation
language:
- be
- da
- de
- el
- en
- es
- fr
- it
- nl
- pl
- pt
- ro
- ru
- sk
- sv
- uk
---
# ByT5-text-correction
A small multilingual utility model intended for simple text correction. It is designed to improve the quality of texts from the web, often lacking punctuation or proper word capitalization. The model was trained to perform three types of corrections:
* Restoring punctuation in sentences.
* Restoring word capitalization.
* Restoring diacritical marks for languages that include them.
The following languages are supported: Belarusian (be), Danish (da), German (de), Greek (el), English (en), Spanish (es), French (fr), Italian (it), Dutch (nl), Polish (pl), Portuguese (pt), Romanian (ro), Russian (ru), Slovak (sk), Swedish (sv), Ukrainian (uk).
The model takes as input a sentence preceded by a language code prefix. For example:
```python
from transformers import pipeline
generator = pipeline("text2text-generation", model="sdadas/byt5-text-correction")
sentences = [
"<pl> ciekaw jestem na co licza onuce stawiajace na sykulskiego w nadziei na zwrot ku rosji",
"<de> die frage die sich die europรคer stellen mรผssen lautet ist es in unserem interesse die krise auf taiwan zu beschleunigen",
"<ru> ะฟัะธ ัะฒะพัะผ ัะพะถะดะตะฝะธะธ 26 ะฐะฒะณัััะฐ 1910 ะณะพะดะฐ ัะตัะตะทะฐ ะฟะพะปััะธะปะฐ ะธะผั ะฐะณะฝะตั ะฑะพัะดะถะธั"
]
generator(sentences, max_length=512)
# Ciekaw jestem na co liczฤ
onuce stawiajฤ
ce na Sykulskiego w nadziei na zwrot ku Rosji.
# Die Frage, die sich die Europรคer stellen mรผssen, lautet: Ist es in unserem Interesse, die Krise auf Taiwan zu beschleunigen?
# ะัะธ ัะฒะพัะผ ัะพะถะดะตะฝะธะธ 26 ะฐะฒะณัััะฐ 1910 ะณะพะดะฐ ะขะตัะตะทะฐ ะฟะพะปััะธะปะฐ ะธะผั ะะณะฝะตั ะะพัะดะถะธั.
``` |
lorahub/flan_t5_large-qasc_qa_with_separated_facts_5 | lorahub | 2023-07-24T10:01:03Z | 393 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-07-24T10:00:53Z | ---
library_name: peft
---
|
timm/inception_next_small.sail_in1k | timm | 2023-08-24T19:00:18Z | 393 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2303.16900",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-08-24T18:59:41Z | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for inception_next_small.sail_in1k
A InceptionNeXt image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 49.4
- GMACs: 8.4
- Activations (M): 19.3
- Image size: 224 x 224
- **Papers:**
- InceptionNeXt: When Inception Meets ConvNeXt: https://arxiv.org/abs/2303.16900
- **Original:** https://github.com/sail-sg/inceptionnext
- **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('inception_next_small.sail_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(
'inception_next_small.sail_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, 96, 56, 56])
# torch.Size([1, 192, 28, 28])
# torch.Size([1, 384, 14, 14])
# torch.Size([1, 768, 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(
'inception_next_small.sail_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, 768, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@article{yu2023inceptionnext,
title={InceptionNeXt: when inception meets convnext},
author={Yu, Weihao and Zhou, Pan and Yan, Shuicheng and Wang, Xinchao},
journal={arXiv preprint arXiv:2303.16900},
year={2023}
}
```
|
AdapterHub/xmod-base | AdapterHub | 2023-08-27T10:09:50Z | 393 | 0 | transformers | [
"transformers",
"pytorch",
"xmod",
"endpoints_compatible",
"region:us"
]
| null | 2023-08-27T10:04:49Z | Entry not found |
Yntec/LuckyStrike | Yntec | 2023-10-23T11:46:19Z | 393 | 3 | diffusers | [
"diffusers",
"safetensors",
"Character",
"Beautiful",
"kinshin007",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-10-23T06:09:26Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Character
- Beautiful
- kinshin007
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
---
# Lucky Strike
Original page: https://civitai.com/models/13034?modelVersionId=15358
Sample and prompt:
a detailed painting of a POP CORN life of fruit and Pretty CUTE Girl, DETAILED EYES, flowers in a basket, artgerm, Terry moore, james jean, visible brushstrokes, Iconic, 1949, sharp focus, detailed fruitcake, gorgeous detailed hair |
TheBloke/vietnamese-llama2-7B-40GB-GGUF | TheBloke | 2023-11-01T16:58:03Z | 393 | 3 | transformers | [
"transformers",
"gguf",
"llama",
"vi",
"en",
"dataset:vietgpt/wikipedia_vi",
"dataset:wikipedia",
"dataset:pg19",
"dataset:mc4",
"base_model:bkai-foundation-models/vietnamese-llama2-7b-40GB",
"license:other",
"text-generation-inference",
"region:us"
]
| null | 2023-11-01T16:53:58Z | ---
base_model: bkai-foundation-models/vietnamese-llama2-7b-40GB
datasets:
- vietgpt/wikipedia_vi
- wikipedia
- pg19
- mc4
inference: false
language:
- vi
- en
license: other
model_creator: BKAI-HUST Foundation Models Lab
model_name: Vietnamese Llama2 7B 40GB
model_type: llama
prompt_template: '{prompt}
'
quantized_by: TheBloke
---
<!-- 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 -->
# Vietnamese Llama2 7B 40GB - GGUF
- Model creator: [BKAI-HUST Foundation Models Lab](https://huggingface.co/bkai-foundation-models)
- Original model: [Vietnamese Llama2 7B 40GB](https://huggingface.co/bkai-foundation-models/vietnamese-llama2-7b-40GB)
<!-- description start -->
## Description
This repo contains GGUF format model files for [BKAI-HUST Foundation Models Lab's Vietnamese Llama2 7B 40GB](https://huggingface.co/bkai-foundation-models/vietnamese-llama2-7b-40GB).
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 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/vietnamese-llama2-7B-40GB-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF)
* [BKAI-HUST Foundation Models Lab's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bkai-foundation-models/vietnamese-llama2-7b-40GB)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- 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: [BKAI-HUST Foundation Models Lab's Vietnamese Llama2 7B 40GB](https://huggingface.co/bkai-foundation-models/vietnamese-llama2-7b-40GB).
<!-- licensing 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [vietnamese-llama2-7b-40gb.Q2_K.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q2_K.gguf) | Q2_K | 2 | 2.89 GB| 5.39 GB | smallest, significant quality loss - not recommended for most purposes |
| [vietnamese-llama2-7b-40gb.Q3_K_S.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q3_K_S.gguf) | Q3_K_S | 3 | 3.02 GB| 5.52 GB | very small, high quality loss |
| [vietnamese-llama2-7b-40gb.Q3_K_M.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q3_K_M.gguf) | Q3_K_M | 3 | 3.37 GB| 5.87 GB | very small, high quality loss |
| [vietnamese-llama2-7b-40gb.Q3_K_L.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q3_K_L.gguf) | Q3_K_L | 3 | 3.67 GB| 6.17 GB | small, substantial quality loss |
| [vietnamese-llama2-7b-40gb.Q4_0.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q4_0.gguf) | Q4_0 | 4 | 3.91 GB| 6.41 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [vietnamese-llama2-7b-40gb.Q4_K_S.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q4_K_S.gguf) | Q4_K_S | 4 | 3.94 GB| 6.44 GB | small, greater quality loss |
| [vietnamese-llama2-7b-40gb.Q4_K_M.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q4_K_M.gguf) | Q4_K_M | 4 | 4.16 GB| 6.66 GB | medium, balanced quality - recommended |
| [vietnamese-llama2-7b-40gb.Q5_0.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q5_0.gguf) | Q5_0 | 5 | 4.74 GB| 7.24 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [vietnamese-llama2-7b-40gb.Q5_K_S.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q5_K_S.gguf) | Q5_K_S | 5 | 4.74 GB| 7.24 GB | large, low quality loss - recommended |
| [vietnamese-llama2-7b-40gb.Q5_K_M.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q5_K_M.gguf) | Q5_K_M | 5 | 4.87 GB| 7.37 GB | large, very low quality loss - recommended |
| [vietnamese-llama2-7b-40gb.Q6_K.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q6_K.gguf) | Q6_K | 6 | 5.63 GB| 8.13 GB | very large, extremely low quality loss |
| [vietnamese-llama2-7b-40gb.Q8_0.gguf](https://huggingface.co/TheBloke/vietnamese-llama2-7B-40GB-GGUF/blob/main/vietnamese-llama2-7b-40gb.Q8_0.gguf) | Q8_0 | 8 | 7.29 GB| 9.79 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/vietnamese-llama2-7B-40GB-GGUF and below it, a specific filename to download, such as: vietnamese-llama2-7b-40gb.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/vietnamese-llama2-7B-40GB-GGUF vietnamese-llama2-7b-40gb.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/vietnamese-llama2-7B-40GB-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/vietnamese-llama2-7B-40GB-GGUF vietnamese-llama2-7b-40gb.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 vietnamese-llama2-7b-40gb.Q4_K_M.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.
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/vietnamese-llama2-7B-40GB-GGUF", model_file="vietnamese-llama2-7b-40gb.Q4_K_M.gguf", model_type="llama", 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**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, ้ฟๆ, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjรคreholt, John Detwiler, Leonard Tan, Iucharbius
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: BKAI-HUST Foundation Models Lab's Vietnamese Llama2 7B 40GB
We employed [SentencePiece](https://github.com/google/sentencepiece) to retrain a Vietnamese tokenizer with a vocabulary size of 20K. No Vietnamese word segmentation was used. We then merged this vocabulary with the original one of Llama2, removing duplicate tokens.
The new tokenizer significantly improves when encoding Vietnamese text, reducing the number of tokens by 50% compared to ChatGPT and approximately 70% compared to the original Llama2.
We conducted a single-epoch continual pretraining, also known as incremental pretraining, using the Llama2-chat 7B model on a mixed dataset totaling 40.5 GB, comprised of:
- 19 GB [NewsCorpus](https://github.com/binhvq/news-corpus)
- 1.1 GB Vietnamese Wikipedia
- 1.6 GB [Vietnamese books](https://www.kaggle.com/datasets/iambestfeeder/10000-vietnamese-books)
- 4.5 GB Vietnamese legal documents (crawled from thuvienphapluat and processed by ourselves)
- 2.1 GB Vietnamese legal text (from [C4-vi](https://huggingface.co/datasets/c4))
- 1.1 GB English Books (sub-sampled from [pg19](https://huggingface.co/datasets/pg19))
- 1.1 GB English Wikipedia (sub-sampled from 20220301.en wikipedia)
- 10 GB English Text (sub-sampled from [C4-en](https://huggingface.co/datasets/c4))
We trained the model on a DGX A100 system, utilizing four GPU A100 in 10 days (about 1000 GPU hours).
Hyperparameters are set as follows:
- Training Regime: BFloat16 mixed precision
- Lora Config:
```
{
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
"bias": "none",
"enable_lora": null,
"fan_in_fan_out": false,
"inference_mode": true,
"lora_alpha": 32.0,
"lora_dropout": 0.05,
"merge_weights": false,
"modules_to_save": [
"embed_tokens",
"lm_head"
],
"peft_type": "LORA",
"r": 8,
"target_modules": [
"q_proj",
"v_proj",
"k_proj",
"o_proj",
"gate_proj",
"down_proj",
"up_proj"
],
"task_type": "CAUSAL_LM"
}
```
We also provide the [LoRA part](https://huggingface.co/bkai-foundation-models/vietnamese-llama2-7b-40GB/tree/main/pt_lora_model) so that you can integrate it with the original Llama2-chat-7b by yourself.
Please note that **this model requires further supervised fine-tuning (SFT)** to be used in practice!
Usage and other considerations: We refer to the [Llama 2](https://github.com/facebookresearch/llama)
Training loss:
<img src="figure/training_loss.png" alt="Training Loss Curve"/>
**Disclaimer**
This project is built upon Meta's Llama-2 model. It is essential to strictly adhere to the open-source license agreement of Llama-2 when using this model. If you incorporate third-party code, please ensure compliance with the relevant open-source license agreements.
It's important to note that the content generated by the model may be influenced by various factors, such as calculation methods, random elements, and potential inaccuracies in quantification. Consequently, this project does not offer any guarantees regarding the accuracy of the model's outputs, and it disclaims any responsibility for consequences resulting from the use of the model's resources and its output.
For those employing the models from this project for commercial purposes, developers must adhere to local laws and regulations to ensure the compliance of the model's output content. This project is not accountable for any products or services derived from such usage.
**Acknowledgments**
We extend our gratitude to PHPC - Phenikaa University and NVIDIA for their generous provision of computing resources for model training. Our appreciation also goes out to binhvq and the other authors for their diligent efforts in collecting and preparing the Vietnamese text corpus.
<!-- original-model-card end -->
|
TheBloke/OpenOrca-Zephyr-7B-GGUF | TheBloke | 2023-12-04T23:37:38Z | 393 | 13 | transformers | [
"transformers",
"gguf",
"mistral",
"base_model:Weyaxi/OpenOrca-Zephyr-7B",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
]
| null | 2023-12-04T23:33:16Z | ---
base_model: Weyaxi/OpenOrca-Zephyr-7B
inference: false
license: cc-by-nc-4.0
model_creator: "Ya\u011F\u0131z \xC7al\u0131k"
model_name: OpenOrca Zephyr 7B
model_type: mistral
prompt_template: '<|system|>
{system_message}</s>
<|user|>
{prompt}</s>
<|assistant|>
'
quantized_by: TheBloke
---
<!-- 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 -->
# OpenOrca Zephyr 7B - GGUF
- Model creator: [Yaฤฤฑz รalฤฑk](https://huggingface.co/Weyaxi)
- Original model: [OpenOrca Zephyr 7B](https://huggingface.co/Weyaxi/OpenOrca-Zephyr-7B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Yaฤฤฑz รalฤฑk's OpenOrca Zephyr 7B](https://huggingface.co/Weyaxi/OpenOrca-Zephyr-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/OpenOrca-Zephyr-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF)
* [Yaฤฤฑz รalฤฑk's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Weyaxi/OpenOrca-Zephyr-7B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Zephyr
```
<|system|>
{system_message}</s>
<|user|>
{prompt}</s>
<|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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [openorca-zephyr-7b.Q2_K.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [openorca-zephyr-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [openorca-zephyr-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [openorca-zephyr-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [openorca-zephyr-7b.Q4_0.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [openorca-zephyr-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [openorca-zephyr-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [openorca-zephyr-7b.Q5_0.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [openorca-zephyr-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [openorca-zephyr-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [openorca-zephyr-7b.Q6_K.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [openorca-zephyr-7b.Q8_0.gguf](https://huggingface.co/TheBloke/OpenOrca-Zephyr-7B-GGUF/blob/main/openorca-zephyr-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/OpenOrca-Zephyr-7B-GGUF and below it, a specific filename to download, such as: openorca-zephyr-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/OpenOrca-Zephyr-7B-GGUF openorca-zephyr-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/OpenOrca-Zephyr-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/OpenOrca-Zephyr-7B-GGUF openorca-zephyr-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 openorca-zephyr-7b.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|system|>\n{system_message}</s>\n<|user|>\n{prompt}</s>\n<|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 โ 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="./openorca-zephyr-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(
"<|system|>\n{system_message}</s>\n<|user|>\n{prompt}</s>\n<|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="./openorca-zephyr-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, ้ฟๆ, 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 Bjรคreholt, 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: Yaฤฤฑz รalฤฑk's OpenOrca Zephyr 7B
<a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
Merge of [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) and [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) using ties merge.
### *Weights*
- [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha): 0.5
- [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca): 0.3
### *Density*
- [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha): 0.5
- [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca): 0.5
# Evulation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard))
| Metric | Value |
|-----------------------|-------|
| Avg. | |
| ARC (25-shot) | |
| HellaSwag (10-shot) | |
| MMLU (5-shot) | |
| TruthfulQA (0-shot) | |
<!-- original-model-card end -->
|
vilm/Quyen-SE-v0.1-GGUF | vilm | 2024-02-10T14:23:39Z | 393 | 2 | transformers | [
"transformers",
"gguf",
"en",
"dataset:teknium/OpenHermes-2.5",
"dataset:LDJnr/Capybara",
"dataset:Intel/orca_dpo_pairs",
"dataset:argilla/distilabel-intel-orca-dpo-pairs",
"license:other",
"endpoints_compatible",
"region:us"
]
| null | 2024-02-06T11:55:19Z | ---
library_name: transformers
license: other
datasets:
- teknium/OpenHermes-2.5
- LDJnr/Capybara
- Intel/orca_dpo_pairs
- argilla/distilabel-intel-orca-dpo-pairs
language:
- en
---
# Quyen
<img src="quyen.webp" width="512" height="512" alt="Quyen">
# Model Description
Quyen is our first flagship LLM series based on the Qwen1.5 family. We introduced 6 different versions:
- **Quyen-SE (0.5B)**
- **Quyen-Mini (1.8B)**
- **Quyen (4B)**
- **Quyen-Plus (7B)**
- **Quyen-Pro (14B)**
- **Quyen-Pro-Max (72B)**
All models were trained with SFT and DPO using the following dataset:
- *OpenHermes-2.5* by **Teknium**
- *Capyabara* by **LDJ**
- *distilabel-intel-orca-dpo-pairs* by **argilla**
- *orca_dpo_pairs* by **Intel**
- and Private Data by **Ontocord** & **BEE-spoke-data**
# Prompt Template
- All Quyen models use ChatML as the default template:
```
<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Hello world.<|im_end|>
<|im_start|>assistant
```
- You can also use `apply_chat_template`:
```python
messages = [
{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."},
{"role": "user", "content": "Hello world."}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
```
# Benchmarks:
- Coming Soon! We will update the benchmarks later
# Acknowledgement
- We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation. |
JohannesGaessler/cosmosage_v2-gguf | JohannesGaessler | 2024-02-27T10:26:20Z | 393 | 0 | null | [
"gguf",
"license:apache-2.0",
"region:us"
]
| null | 2024-02-25T13:34:06Z | ---
license: apache-2.0
---
GGUF conversion of [Cosmosage v2](https://huggingface.co/Tijmen2/cosmosage_v2). The importance matrix for iq formats was calculated on the training set of Wikitext 2. The iq1\_s quant was incoherent and therefore not included.
|
mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF | mradermacher | 2024-05-06T06:07:49Z | 393 | 3 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:cookinai/OrcaHermes-Mistral-70B-miqu",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-19T18:07:24Z | ---
base_model: cookinai/OrcaHermes-Mistral-70B-miqu
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
static quants of https://huggingface.co/cookinai/OrcaHermes-Mistral-70B-miqu
<!-- 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/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q2_K.gguf) | Q2_K | 25.9 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.IQ3_XS.gguf) | IQ3_XS | 28.6 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.IQ3_S.gguf) | IQ3_S | 30.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q3_K_S.gguf) | Q3_K_S | 30.3 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.IQ3_M.gguf) | IQ3_M | 31.4 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q3_K_M.gguf) | Q3_K_M | 33.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q3_K_L.gguf) | Q3_K_L | 36.6 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.IQ4_XS.gguf) | IQ4_XS | 37.6 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q4_K_S.gguf) | Q4_K_S | 39.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q4_K_M.gguf) | Q4_K_M | 41.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q5_K_S.gguf) | Q5_K_S | 47.9 | |
| [GGUF](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q5_K_M.gguf) | Q5_K_M | 49.2 | |
| [PART 1](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q6_K.gguf.part2of2) | Q6_K | 57.0 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OrcaHermes-Mistral-70B-miqu-GGUF/resolve/main/OrcaHermes-Mistral-70B-miqu.Q8_0.gguf.part2of2) | Q8_0 | 73.6 | 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 -->
|
mmnga/lightblue-karasu-1.1B-gguf | mmnga | 2024-05-07T12:58:26Z | 393 | 1 | null | [
"gguf",
"llama",
"en",
"ja",
"license:apache-2.0",
"region:us"
]
| null | 2024-03-24T15:46:32Z | ---
license: apache-2.0
language:
- en
- ja
tags:
- llama
---
# lightblue-karasu-1.1B-gguf
[lightblueใใใๅ
ฌ้ใใฆใใkarasu-1.1B](https://huggingface.co/lightblue/karasu-1.1B)ใฎggufใใฉใผใใใๅคๆ็ใงใใ
TinyLlamaใใผในใซใชใใพใใ
## ไปใฎใขใใซ
[mmnga/lightblue-Karasu-Mixtral-8x22B-v0.1-gguf](https://huggingface.co/mmnga/lightblue-Karasu-Mixtral-8x22B-v0.1-gguf)
[mmnga/lightblue-suzume-llama-3-8B-multilingual-gguf](https://huggingface.co/mmnga/lightblue-suzume-llama-3-8B-multilingual-gguf)
[mmnga/lightblue-suzume-llama-3-8B-japanese-gguf](https://huggingface.co/mmnga/lightblue-suzume-llama-3-8B-japanese-gguf)
[mmnga/lightblue-ao-karasu-72B-gguf](https://huggingface.co/mmnga/lightblue-ao-karasu-72B-gguf)
[mmnga/lightblue-karasu-1.1B-gguf](https://huggingface.co/mmnga/lightblue-karasu-1.1B-gguf)
[mmnga/lightblue-karasu-7B-chat-plus-unleashed-gguf](https://huggingface.co/mmnga/lightblue-karasu-7B-chat-plus-unleashed-gguf)
[mmnga/lightblue-qarasu-14B-chat-plus-unleashed-gguf](https://huggingface.co/mmnga/lightblue-qarasu-14B-chat-plus-unleashed-gguf)
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'lightblue-karasu-1.1B-q4_0.gguf' -p "ไปๅคใฎๆฉๅพก้ฃฏใใ็ดนไปใใพใใ" -n 128
``` |
johnsnowlabs/CodeGemma-2B-Slerp | johnsnowlabs | 2024-04-09T16:55:59Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"feature-extraction",
"merge",
"mergekit",
"lazymergekit",
"wandb/gemma-2b-zephyr-dpo",
"MAISAAI/gemma-2b-coder",
"base_model:wandb/gemma-2b-zephyr-dpo",
"base_model:MAISAAI/gemma-2b-coder",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| feature-extraction | 2024-04-08T19:49:28Z | ---
tags:
- merge
- mergekit
- lazymergekit
- wandb/gemma-2b-zephyr-dpo
- MAISAAI/gemma-2b-coder
base_model:
- wandb/gemma-2b-zephyr-dpo
- MAISAAI/gemma-2b-coder
license: apache-2.0
---
# CodeGemma-2B-Slerp
CodeGemma-2B-Slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [wandb/gemma-2b-zephyr-dpo](https://huggingface.co/wandb/gemma-2b-zephyr-dpo)
* [MAISAAI/gemma-2b-coder](https://huggingface.co/MAISAAI/gemma-2b-coder)
Special thanks to Charles Goddard for the quick implementation!
## ๐ Evaluation
### Coming Soon
## ๐งฉ Configuration
```yaml
slices:
- sources:
- model: wandb/gemma-2b-zephyr-dpo
layer_range: [0, 18]
- model: MAISAAI/gemma-2b-coder
layer_range: [0, 18]
merge_method: slerp
base_model: wandb/gemma-2b-zephyr-dpo
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
```
## ๐ป Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "johnsnowlabs/CodeGemma-2B-Slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
MaziyarPanahi/codegemma-7b-GGUF | MaziyarPanahi | 2024-04-09T16:42:33Z | 393 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"gemma",
"text-generation",
"license:gemma",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us",
"base_model:google/codegemma-7b"
]
| text-generation | 2024-04-09T15:44:06Z | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- gemma
- text-generation
- license:gemma
- autotrain_compatible
- endpoints_compatible
- has_space
- text-generation-inference
- region:us
- text-generation
model_name: codegemma-7b-GGUF
base_model: google/codegemma-7b
inference: false
model_creator: google
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/codegemma-7b-GGUF](https://huggingface.co/MaziyarPanahi/codegemma-7b-GGUF)
- Model creator: [google](https://huggingface.co/google)
- Original model: [google/codegemma-7b](https://huggingface.co/google/codegemma-7b)
## Description
[MaziyarPanahi/codegemma-7b-GGUF](https://huggingface.co/MaziyarPanahi/codegemma-7b-GGUF) contains GGUF format model files for [google/codegemma-7b](https://huggingface.co/google/codegemma-7b).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
### 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
## 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: [MaziyarPanahi/codegemma-7b-GGUF](https://huggingface.co/MaziyarPanahi/codegemma-7b-GGUF) and below it, a specific filename to download, such as: codegemma-7b-GGUF.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 MaziyarPanahi/codegemma-7b-GGUF codegemma-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<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 [MaziyarPanahi/codegemma-7b-GGUF](https://huggingface.co/MaziyarPanahi/codegemma-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 MaziyarPanahi/codegemma-7b-GGUF codegemma-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>
## 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 codegemma-7b.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|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 โ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20-%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://github.com/abetlen/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="./codegemma-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
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|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="./codegemma-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) |
automerger/Experiment27pasticheShadowm7exp-7B | automerger | 2024-04-11T17:38:19Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:automerger/Experiment27Pastiche-7B",
"base_model:mahiatlinux/ShadowM7EXP-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-11T17:37:29Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- automerger
base_model:
- automerger/Experiment27Pastiche-7B
- mahiatlinux/ShadowM7EXP-7B
---
# Experiment27pasticheShadowm7exp-7B
Experiment27pasticheShadowm7exp-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
* [automerger/Experiment27Pastiche-7B](https://huggingface.co/automerger/Experiment27Pastiche-7B)
* [mahiatlinux/ShadowM7EXP-7B](https://huggingface.co/mahiatlinux/ShadowM7EXP-7B)
## ๐งฉ Configuration
```yaml
slices:
- sources:
- model: automerger/Experiment27Pastiche-7B
layer_range: [0, 32]
- model: mahiatlinux/ShadowM7EXP-7B
layer_range: [0, 32]
merge_method: slerp
base_model: automerger/Experiment27Pastiche-7B
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
random_seed: 0
```
## ๐ป Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "automerger/Experiment27pasticheShadowm7exp-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
LiteLLMs/Mixtral-8x22B-v0.1-GGUF | LiteLLMs | 2024-04-18T20:46:55Z | 393 | 0 | null | [
"gguf",
"moe",
"GGUF",
"fr",
"it",
"de",
"es",
"en",
"license:apache-2.0",
"model-index",
"region:us"
]
| null | 2024-04-11T20:34:53Z | ---
language:
- fr
- it
- de
- es
- en
license: apache-2.0
tags:
- moe
- GGUF
model-index:
- name: Mixtral-8x22B-v0.1
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: 70.48
name: normalized accuracy
verified: false
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mistral-community/Mixtral-8x22B-v0.1
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: 88.73
name: normalized accuracy
verified: false
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mistral-community/Mixtral-8x22B-v0.1
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: 77.81
name: accuracy
verified: false
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mistral-community/Mixtral-8x22B-v0.1
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: 51.08
verified: false
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mistral-community/Mixtral-8x22B-v0.1
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: 84.53
name: accuracy
verified: false
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mistral-community/Mixtral-8x22B-v0.1
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: 74.15
name: accuracy
verified: false
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mistral-community/Mixtral-8x22B-v0.1
name: Open LLM Leaderboard
quantized_by: andrijdavid
---
# Mixtral-8x22B-v0.1-GGUF
- Original model: [Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-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 applicationsโ
* [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: LiteLLMs/Mixtral-8x22B-v0.1-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.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 LiteLLMs/Mixtral-8x22B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.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 LiteLLMs/Mixtral-8x22B-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 huggingface_hub[hf_transfer]
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Mixtral-8x22B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.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 Q4_0/Q4_0-00001-of-00009.gguf --color -c 65536 --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 65536` 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 โ 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="./Q4_0/Q4_0-00001-of-00009.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="./Q4_0/Q4_0-00001-of-00009.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: Mixtral-8x22B-v0.1
# Mixtral-8x22B
> [!TIP]
> MistralAI has uploaded weights to their organization at [mistralai/Mixtral-8x22B-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1) and [mistralai/Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1) too.
> [!TIP]
> Kudos to [@v2ray](https://huggingface.co/v2ray) for converting the checkpoints and uploading them in `transformers` compatible format. Go give them a follow!
Converted to HuggingFace Transformers format using the script [here](https://huggingface.co/v2ray/Mixtral-8x22B-v0.1/blob/main/convert.py).
The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.
## Run the model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistral-community/Mixtral-8x22B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "Hello my name is"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:
### In half-precision
Note `float16` precision only works on GPU devices
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistral-community/Mixtral-8x22B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Lower precision using (8-bit & 4-bit) using `bitsandbytes`
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistral-community/Mixtral-8x22B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Load the model with Flash Attention 2
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistral-community/Mixtral-8x22B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
## Notice
Mixtral-8x22B-v0.1 is a pretrained base model and therefore does not have any moderation mechanisms.
# 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, Lรฉlio 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, Timothรฉe Lacroix, Thรฉophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mistral-community__Mixtral-8x22B-v0.1)
| Metric | Value |
| -: |
| Avg. | 74.46 |
| AI2 Reasoning Challenge (25-Shot) | 70.48 |
| HellaSwag (10-Shot) | 88.73 |
| MMLU (5-Shot) | 77.81 |
| TruthfulQA (0-shot) | 51.08 |
| Winogrande (5-shot) | 84.53 |
| GSM8k (5-shot) | 74.15 |
<!-- original-model-card end --> |
allknowingroger/MultiverseEx26-Neurallaymons-12B-MoE | allknowingroger | 2024-04-14T06:49:11Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"allknowingroger/MultiverseEx26-7B-slerp",
"allknowingroger/Neurallaymons-7B-slerp",
"base_model:allknowingroger/MultiverseEx26-7B-slerp",
"base_model:allknowingroger/Neurallaymons-7B-slerp",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-14T06:42:24Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- allknowingroger/MultiverseEx26-7B-slerp
- allknowingroger/Neurallaymons-7B-slerp
base_model:
- allknowingroger/MultiverseEx26-7B-slerp
- allknowingroger/Neurallaymons-7B-slerp
---
# MultiverseEx26-Neurallaymons-12B-MoE
MultiverseEx26-Neurallaymons-12B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [allknowingroger/MultiverseEx26-7B-slerp](https://huggingface.co/allknowingroger/MultiverseEx26-7B-slerp)
* [allknowingroger/Neurallaymons-7B-slerp](https://huggingface.co/allknowingroger/Neurallaymons-7B-slerp)
## ๐งฉ Configuration
```yaml
base_model: allknowingroger/MultiverseEx26-7B-slerp
experts:
- source_model: allknowingroger/MultiverseEx26-7B-slerp
positive_prompts: ["what"]
- source_model: allknowingroger/Neurallaymons-7B-slerp
positive_prompts: ["math"]
```
## ๐ป Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/MultiverseEx26-Neurallaymons-12B-MoE"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
AmberYifan/test-spin-iter0 | AmberYifan | 2024-04-16T18:41:59Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"conversational",
"dataset:UCLA-AGI/SPIN_iter0",
"base_model:alignment-handbook/zephyr-7b-sft-full",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-16T18:38:05Z | ---
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- UCLA-AGI/SPIN_iter0
model-index:
- name: iter0_full
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. -->
# iter0_full
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the UCLA-AGI/SPIN_iter0 dataset.
## 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: 5e-07
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
|
ChuckMcSneed/wizardcoder-33b-v1.1-mirror | ChuckMcSneed | 2024-04-26T07:50:44Z | 393 | 5 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"code",
"arxiv:2304.12244",
"arxiv:2306.08568",
"arxiv:2308.09583",
"license:wtfpl",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-17T02:13:47Z | ---
metrics:
- code_eval
library_name: transformers
tags:
- code
model-index:
- name: WizardCoder
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 0.799
verified: false
license: wtfpl
---
May or may not be deleted wizardcoder-33b-v1.1.
# Prompt format
```
### Instruction:
{instruction}
### Response:
```
# Original model card: WizardLM's Wizardcoder 33B V1.1
## WizardCoder: Empowering Code Large Language Models with Evol-Instruct
<p style="font-size:28px;" align="center">
๐ <a href="https://wizardlm.github.io/" target="_blank">Home Page</a> </p>
<p align="center">
<p align="center">
๐ค <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> โข๐ฑ <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> โข ๐ฆ <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> </p>
<p align="center">
๐ <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> โข ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> โข ๐ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
</p>
<p align="center">
๐ Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
</p>
## News
[2023/01/04] ๐ฅ We released **WizardCoder-33B-V1.1** trained from deepseek-coder-33b-base, the **SOTA OSS Code LLM** on [EvalPlus Leaderboard](https://evalplus.github.io/leaderboard.html), achieves **79.9 pass@1** on HumanEval, **73.2 pass@1** on HumanEval-Plus, **78.9 pass@1** on MBPP, and **66.9 pass@1** on MBPP-Plus.
[2023/01/04] ๐ฅ **WizardCoder-33B-V1.1** outperforms **ChatGPT 3.5**, **Gemini Pro**, and **DeepSeek-Coder-33B-instruct** on HumanEval and HumanEval-Plus pass@1.
[2023/01/04] ๐ฅ **WizardCoder-33B-V1.1** is comparable with **ChatGPT 3.5**, and surpasses **Gemini Pro** on MBPP and MBPP-Plus pass@1.
| Model | Checkpoint | Paper | HumanEval | HumanEval+ | MBPP | MBPP+ | License |
| ----- |------| ---- |------|-------| ----- | ----- |----- |
| GPT-4-Turbo (Nov 2023) | - | - | 85.4 | 81.7 | 83.0 | 70.7 |-|
| GPT-4 (May 2023) | - | - | 88.4 | 76.8 | - | - |-|
| GPT-3.5-Turbo (Nov 2023) | - | - | 72.6 | 65.9 | 81.7 | 69.4 |-|
| Gemini Pro | - | - | 63.4 | 55.5 | 72.9 | 57.9 |-|
| DeepSeek-Coder-33B-instruct | - | - | 78.7 | 72.6 | 78.7 | 66.7 |-|
| **WizardCoder-33B-V1.1** | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-33B-V1.1" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 79.9 | 73.2 | 78.9 | 66.9 | <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1/resolve/main/LICENSE" target="_blank">MSFTResearch</a> |
| WizardCoder-Python-34B-V1.0 | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 73.2 | 64.6 | 73.2 | 59.9 | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
| WizardCoder-15B-V1.0 | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-15B-V1.0" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 59.8 | 52.4 | -- | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
| WizardCoder-Python-13B-V1.0 | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 64.0 | -- | -- | -- | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
| WizardCoder-Python-7B-V1.0 | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-Python-7B-V1.0" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 55.5 | -- | -- | -- | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
| WizardCoder-3B-V1.0 | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-3B-V1.0" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 34.8 | -- | -- | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
| WizardCoder-1B-V1.0 | ๐ค <a href="https://huggingface.co/WizardLM/WizardCoder-1B-V1.0" target="_blank">HF Link</a> | ๐ <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 23.8 | -- | -- | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
## โ Data Contamination Check:
Before model training, we carefully and rigorously checked all the training data, and used multiple deduplication methods to verify and prevent data leakage on HumanEval and MBPP test set.
๐ฅ
โ<b>Note for model system prompts usage:</b>
Please use **the same systems prompts strictly** with us, and we do not guarantee the accuracy of the **quantified versions**.
**Default version:**
```
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
```
## How to Reproduce the Performance of WizardCoder-33B-V1.1
We provide all codes [here](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder/src).
We also provide all generated [results](https://github.com/nlpxucan/WizardLM/blob/main/WizardCoder/data/humaneval_mbpp_wizardcoder33b_v1.1_results.zip).
```
transformers==4.36.2
vllm==0.2.5
```
(1) HumanEval and HumanEval-Plus
- Step 1
Code Generation (w/o accelerate)
```bash
model="WizardLM/WizardCoder-33B-V1.1"
temp=0.0
max_len=2048
pred_num=1
num_seqs_per_iter=1
output_path=preds/T${temp}_N${pred_num}_WizardCoder-33B-V1.1_Greedy_Decode
mkdir -p ${output_path}
echo 'Output path: '$output_path
echo 'Model to eval: '$model
# 164 problems, 21 per GPU if GPU=8
index=0
gpu_num=8
for ((i = 0; i < $gpu_num; i++)); do
start_index=$((i * 21))
end_index=$(((i + 1) * 21))
gpu=$((i))
echo 'Running process #' ${i} 'from' $start_index 'to' $end_index 'on GPU' ${gpu}
((index++))
(
CUDA_VISIBLE_DEVICES=$gpu python humaneval_gen.py --model ${model} \
--start_index ${start_index} --end_index ${end_index} --temperature ${temp} \
--num_seqs_per_iter ${num_seqs_per_iter} --N ${pred_num} --max_len ${max_len} --output_path ${output_path} --greedy_decode
) &
if (($index % $gpu_num == 0)); then wait; fi
done
```
Code Generation (w/ vllm accelerate)
```bash
model="WizardLM/WizardCoder-33B-V1.1"
temp=0.0
max_len=2048
pred_num=1
num_seqs_per_iter=1
output_path=preds/T${temp}_N${pred_num}_WizardCoder-33B-V1.1_Greedy_Decode_vllm
mkdir -p ${output_path}
echo 'Output path: '$output_path
echo 'Model to eval: '$model
CUDA_VISIBLE_DEVICES=0,1,2,3 python humaneval_gen_vllm.py --model ${model} \
--start_index 0 --end_index 164 --temperature ${temp} \
--num_seqs_per_iter ${num_seqs_per_iter} --N ${pred_num} --max_len ${max_len} --output_path ${output_path} --num_gpus 4 --overwrite
```
- Step 2: Get the score
Install [Eval-Plus](https://github.com/evalplus/evalplus) benchmark.
```bash
git clone https://github.com/evalplus/evalplus.git
cd evalplus
export PYTHONPATH=$PYTHONPATH:$(pwd)
pip install -r requirements.txt
```
Get HumanEval and HumanEval-Plus scores.
```bash
output_path=preds/T0.0_N1_WizardCoder-33B-V1.1_Greedy_Decode
echo 'Output path: '$output_path
python process_humaneval.py --path ${output_path} --out_path ${output_path}.jsonl --add_prompt
evalplus.evaluate --dataset humaneval --samples ${output_path}.jsonl
```
(2) MBPP and MBPP-Plus
The preprocessed questions are provided in [mbppplus.json](https://github.com/nlpxucan/WizardLM/blob/main/WizardCoder/data/mbppplus.json).
- Step 1
Code Generation (w/o accelerate)
```bash
model="WizardLM/WizardCoder-33B-V1.1"
temp=0.0
max_len=2048
pred_num=1
num_seqs_per_iter=1
output_path=preds/MBPP_T${temp}_N${pred_num}_WizardCoder-33B-V1.1_Greedy_Decode
mkdir -p ${output_path}
echo 'Output path: '$output_path
echo 'Model to eval: '$model
# 399 problems, 50 per GPU if GPU=8
index=0
gpu_num=8
for ((i = 0; i < $gpu_num; i++)); do
start_index=$((i * 50))
end_index=$(((i + 1) * 50))
gpu=$((i))
echo 'Running process #' ${i} 'from' $start_index 'to' $end_index 'on GPU' ${gpu}
((index++))
(
CUDA_VISIBLE_DEVICES=$gpu python mbppplus_gen.py --model ${model} \
--start_index ${start_index} --end_index ${end_index} --temperature ${temp} \
--num_seqs_per_iter ${num_seqs_per_iter} --N ${pred_num} --max_len ${max_len} --output_path ${output_path} --mbpp_path "mbppplus.json" --greedy_decode
) &
if (($index % $gpu_num == 0)); then wait; fi
done
```
Code Generation (w/ vllm accelerate)
```bash
model="WizardLM/WizardCoder-33B-V1.1"
temp=0.0
max_len=2048
pred_num=1
num_seqs_per_iter=1
output_path=preds/MBPP_T${temp}_N${pred_num}_WizardCoder-33B-V1.1_Greedy_Decode_vllm
mkdir -p ${output_path}
echo 'Output path: '$output_path
echo 'Model to eval: '$model
CUDA_VISIBLE_DEVICES=0,1,2,3 python mbppplus_gen_vllm.py --model ${model} \
--start_index ${start_index} --end_index ${end_index} --temperature ${temp} \
--num_seqs_per_iter ${num_seqs_per_iter} --N ${pred_num} --max_len ${max_len} --output_path ${output_path} --mbpp_path "mbppplus.json" --num_gpus 4
```
- Step 2: Get the score
Install [Eval-Plus](https://github.com/evalplus/evalplus) benchmark.
```bash
git clone https://github.com/evalplus/evalplus.git
cd evalplus
export PYTHONPATH=$PYTHONPATH:$(pwd)
pip install -r requirements.txt
```
Get HumanEval and HumanEval-Plus scores.
```bash
output_path=preds/MBPP_T0.0_N1_WizardCoder-33B-V1.1_Greedy_Decode
echo 'Output path: '$output_path
python mbppplus_process_preds.py --path ${output_path} --out_path ${output_path}.jsonl --add_prompt
evalplus.evaluate --dataset mbpp --samples ${output_path}.jsonl
```
## Citation
Please cite the repo if you use the data, method or code in this repo.
```
@article{luo2023wizardcoder,
title={WizardCoder: Empowering Code Large Language Models with Evol-Instruct},
author={Luo, Ziyang and Xu, Can and Zhao, Pu and Sun, Qingfeng and Geng, Xiubo and Hu, Wenxiang and Tao, Chongyang and Ma, Jing and Lin, Qingwei and Jiang, Daxin},
journal={arXiv preprint arXiv:2306.08568},
year={2023}
}
```
<!-- original-model-card end --> |
lodrick-the-lafted/Copus-2x8B | lodrick-the-lafted | 2024-04-20T03:21:42Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-20T00:04:35Z | ---
license: llama2
---
<img src=https://huggingface.co/lodrick-the-lafted/Copus-2x8B/resolve/main/copus.png>
MoE'd up:
- [dreamgen/opus-v1.2-llama-3-8b](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b)
- [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)_
Which were the two most interesting llama3 finetunes as of yet. Resulting model seems OK. It's not on Miqu's level, anyway.
Blah, blah, llama 3 license (no tag for it yet). Also not going to name my model Llama-3-Copus. Come at me, Zuck. |
jeongmi/solar_musinsa_user0 | jeongmi | 2024-04-21T06:59:51Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2024-04-21T06:50:36Z | ---
library_name: transformers
license: apache-2.0
---
# 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 ๐ค 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] |
chrischain/Satoshi1337-8B | chrischain | 2024-04-24T22:00:29Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-24T21:48:06Z | ---
language:
- en
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: other
license_name: llama3
license_link: LICENSE
extra_gated_prompt: >-
### META LLAMA 3 COMMUNITY LICENSE AGREEMENT
Meta Llama 3 Version Release Date: April 18, 2024
"Agreement" means the terms and conditions for use, reproduction, distribution and modification of the
Llama Materials set forth herein.
"Documentation" means the specifications, manuals and documentation accompanying Meta Llama 3
distributed by Meta at https://llama.meta.com/get-started/.
"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into
this Agreement on such person or entityโs behalf), of the age required under applicable laws, rules or
regulations to provide legal consent and that has legal authority to bind your employer or such other
person or entity if you are entering in this Agreement on their behalf.
"Meta Llama 3" means the foundational large language models and software and algorithms, including
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
https://llama.meta.com/llama-downloads.
"Llama Materials" means, collectively, Metaโs proprietary Meta Llama 3 and Documentation (and any
portion thereof) made available under this Agreement.
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
outside of the EEA or Switzerland).
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
limited license under Metaโs intellectual property or other rights owned by Meta embodied in the Llama
Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works
thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display โBuilt with Meta
Llama 3โ on a related website, user interface, blogpost, about page, or product documentation. If you
use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is
distributed or made available, you shall also include โLlama 3โ at the beginning of any such AI model
name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the following
attribution notice within a โNoticeโ text file distributed as a part of such copies: โMeta Llama 3 is
licensed under the Meta Llama 3 Community License, Copyright ยฉ Meta Platforms, Inc. All Rights
Reserved.โ
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by
reference into this Agreement.
v. You will not use the Llama Materials or any output or results of the Llama Materials to
improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licenseeโs affiliates, is greater than 700
million monthly active users in the preceding calendar month, you must request a license from Meta,
which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN โAS ISโ BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama
Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
or any of its affiliates, except as required for reasonable and customary use in describing and
redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
use โLlama 3โ (the โMarkโ) solely as required to comply with the last sentence of Section 1.b.i. You will
comply with Metaโs brand guidelines (currently accessible at
https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
of the Mark will inure to the benefit of Meta.
b. Subject to Metaโs ownership of Llama Materials and derivatives made by or for Meta, with
respect to any derivative works and modifications of the Llama Materials that are made by you, as
between you and Meta, you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or
results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
rights owned or licensable by you, then any licenses granted to you under this Agreement shall
terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
harmless Meta from and against any claim by any third party arising out of or related to your use or
distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
the State of California without regard to choice of law principles, and the UN Convention on Contracts
for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
exclusive jurisdiction of any dispute arising out of this Agreement.
### Meta Llama 3 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you
access or use Meta Llama 3, you agree to this Acceptable Use Policy (โPolicyโ). The most recent copy of
this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)
#### Prohibited Uses
We want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow
others to use, Meta Llama 3 to:
1. Violate the law or othersโ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
2. Guns and illegal weapons (including weapon development)
3. Illegal drugs and regulated/controlled substances
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
3. Generating, promoting, or further distributing spam
4. Impersonating another individual without consent, authorization, or legal right
5. Representing that the use of Meta Llama 3 or outputs are human-generated
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI system
Please report any violation of this Policy, software โbug,โ or other problems that could lead to a violation
of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)
* Reporting risky content generated by the model:
developers.facebook.com/llama_output_feedback
* Reporting bugs and security concerns: facebook.com/whitehat/info
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes โ 8B and 70B parameters โ in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
>>> import transformers
>>> import torch
>>> model_id = "meta-llama/Meta-Llama-3-8B"
>>> pipeline = transformers.pipeline(
"text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
>>> pipeline("Hey how are you doing today?")
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B --include "original/*" --local-dir Meta-Llama-3-8B
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Metaโs sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. Weโve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Metaโs cybersecurity safety eval suite, measuring Llama 3โs propensity to suggest insecure code when used as a coding assistant, and Llama 3โs propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the modelโs capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3โs potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
|
duyntnet/bloom-3b-imatrix-GGUF | duyntnet | 2024-04-26T07:07:14Z | 393 | 0 | transformers | [
"transformers",
"gguf",
"imatrix",
"bigscience",
"bloom-3b",
"text-generation",
"en",
"license:other",
"region:us"
]
| text-generation | 2024-04-25T03:23:19Z | ---
license: other
inference: false
language:
- en
pipeline_tag: text-generation
tags:
- transformers
- gguf
- imatrix
- bigscience
- bloom-3b
---
Quantizations of https://huggingface.co/bigscience/bloom-3b
# From original readme
... |
xinping/Mixtral-instruction-v0.1_zh-nf4 | xinping | 2024-05-07T06:27:19Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"zh",
"en",
"fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2024-04-26T08:18:48Z | ---
license: apache-2.0
language:
- zh
- en
- fr
---
### Direct Use
Run the model
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TextStreamer
model_id = "xinping/Mixtral-instruction-zh_V0.1-nf4"
model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained(model_id)
streamer = TextStreamer(tokenizer,skip_prompt=True, skip_special_tokens=True)
text = "ไปๅคฉๆฏๆๆไบ๏ผๅๅคฉๆฏๆๆๅ ๏ผ"
print(text)
model_input = tokenizer(text, return_tensors="pt").to("cuda")
result = model.generate(**model_input,streamer=streamer, max_new_tokens=2048, repetition_penalty=1.15)
[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
|
chujiezheng/zephyr_0.1_a8.0 | chujiezheng | 2024-04-28T05:33:18Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"arxiv:2404.16792",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-28T05:11:02Z | ---
license: apache-2.0
language:
- en
---
# zephyr_0.1_a8.0
The extrapolated (ExPO) model based on `chujiezheng/zephyr_0.1` and `alignment-handbook/zephyr-7b-sft-full`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. |
Alsebay/Lorge-2x7B | Alsebay | 2024-04-29T23:03:02Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-29T02:12:23Z | ---
license: cc-by-nc-4.0
---
# what is this?
tesing purpose, will add more information later
a Moe Merge about testing upscaling, will see if it success or not.
expect to better than upscaling version
# could I use it?
Sure! go ahead, but I don't think it good enough.
# gguf? not yet, sorry :( |
mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF | mradermacher | 2024-05-05T14:49:54Z | 393 | 4 | transformers | [
"transformers",
"gguf",
"en",
"base_model:openlynn/Llama-3-Soliloquy-8B-v2",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-05T04:36:28Z | ---
base_model: openlynn/Llama-3-Soliloquy-8B-v2
language:
- en
library_name: transformers
license: cc-by-nc-sa-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hfhfix -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-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/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Soliloquy-8B-v2-i1-GGUF/resolve/main/Llama-3-Soliloquy-8B-v2.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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.
<!-- end -->
|
DevsDoCode/LLama-3-8b-Uncensored-Q4_0-GGUF | DevsDoCode | 2024-05-06T07:14:22Z | 393 | 1 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"uncensored",
"llama",
"llama-3",
"unsloth",
"text-generation",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-05-06T07:07:28Z | ---
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
- uncensored
- transformers
- llama
- llama-3
- unsloth
- llama-cpp
- gguf-my-repo
language:
- en
license: apache-2.0
pipeline_tag: text-generation
---
<div align="center">
<!-- Replace `#` with your actual links -->
<a href="https://youtube.com/@devsdocode"><img alt="YouTube" src="https://img.shields.io/badge/YouTube-FF0000?style=for-the-badge&logo=youtube&logoColor=white"></a>
<a href="https://t.me/devsdocode"><img alt="Telegram" src="https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white"></a>
<a href="https://www.instagram.com/sree.shades_/"><img alt="Instagram" src="https://img.shields.io/badge/Instagram-E4405F?style=for-the-badge&logo=instagram&logoColor=white"></a>
<a href="https://www.linkedin.com/in/developer-sreejan/"><img alt="LinkedIn" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white"></a>
<a href="https://buymeacoffee.com/devsdocode"><img alt="Buy Me A Coffee" src="https://img.shields.io/badge/Buy%20Me%20A%20Coffee-FFDD00?style=for-the-badge&logo=buymeacoffee&logoColor=black"></a>
</div>
## Crafted with โค๏ธ by Devs Do Code (Sree)
### GGUF Technical Specifications
Delve into the intricacies of GGUF, a meticulously crafted format that builds upon the robust foundation of the GGJT model. Tailored for heightened extensibility and user-centric functionality, GGUF introduces a suite of indispensable features:
**Single-file Deployment:** Streamline distribution and loading effortlessly. GGUF models have been meticulously architected for seamless deployment, necessitating no external files for supplementary information.
**Extensibility:** Safeguard the future of your models. GGUF seamlessly accommodates the integration of new features into GGML-based executors, ensuring compatibility with existing models.
**mmap Compatibility:** Prioritize efficiency. GGUF models are purposefully engineered to support mmap, facilitating rapid loading and saving, thus optimizing your workflow.
**User-Friendly:** Simplify your coding endeavors. Load and save models effortlessly, irrespective of the programming language used, obviating the dependency on external libraries.
**Full Information:** A comprehensive repository in a single file. GGUF models encapsulate all requisite information for loading, eliminating the need for users to furnish additional data.
The differentiator between GGJT and GGUF lies in the deliberate adoption of a key-value structure for hyperparameters (now termed metadata). Bid farewell to untyped lists, and embrace a structured approach that seamlessly accommodates new metadata without compromising compatibility with existing models. Augment your model with supplementary information for enhanced inference and model identification.
**QUANTIZATION_METHODS:**
| Method | Quantization | Advantages | Trade-offs |
|---|---|---|---|
| q2_k | 2-bit integers | Significant model size reduction | Minimal impact on accuracy |
| q3_k_l | 3-bit integers | Balance between model size reduction and accuracy preservation | Moderate impact on accuracy |
| q3_k_m | 3-bit integers | Enhanced accuracy with mixed precision | Increased computational complexity |
| q3_k_s | 3-bit integers | Improved model efficiency with structured pruning | Reduced accuracy |
| q4_0 | 4-bit integers | Significant model size reduction | Moderate impact on accuracy |
| q4_1 | 4-bit integers | Enhanced accuracy with mixed precision | Increased computational complexity |
| q4_k_m | 4-bit integers | Optimized model size and accuracy with mixed precision and structured pruning | Reduced accuracy |
| q4_k_s | 4-bit integers | Improved model efficiency with structured pruning | Reduced accuracy |
| q5_0 | 5-bit integers | Balance between model size reduction and accuracy preservation | Moderate impact on accuracy |
| q5_1 | 5-bit integers | Enhanced accuracy with mixed precision | Increased computational complexity |
| q5_k_m | 5-bit integers | Optimized model size and accuracy with mixed precision and structured pruning | Reduced accuracy |
| q5_k_s | 5-bit integers | Improved model efficiency with structured pruning | Reduced accuracy |
| q6_k | 6-bit integers | Balance between model size reduction and accuracy preservation | Moderate impact on accuracy |
| q8_0 | 8-bit integers | Significant model size reduction | Minimal impact on accuracy |
<div align="center">
<!-- Replace `#` with your actual links -->
<a href="https://youtube.com/@devsdocode"><img alt="YouTube" src="https://img.shields.io/badge/YouTube-FF0000?style=for-the-badge&logo=youtube&logoColor=white"></a>
<a href="https://t.me/devsdocode"><img alt="Telegram" src="https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white"></a>
<a href="https://www.instagram.com/sree.shades_/"><img alt="Instagram" src="https://img.shields.io/badge/Instagram-E4405F?style=for-the-badge&logo=instagram&logoColor=white"></a>
<a href="https://www.linkedin.com/in/developer-sreejan/"><img alt="LinkedIn" src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white"></a>
<a href="https://buymeacoffee.com/devsdocode"><img alt="Buy Me A Coffee" src="https://img.shields.io/badge/Buy%20Me%20A%20Coffee-FFDD00?style=for-the-badge&logo=buymeacoffee&logoColor=black"></a>
</div> |
saurav1199/adisesha-phi1.5-7-3-35000 | saurav1199 | 2024-05-08T12:20:01Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"custom_code",
"arxiv:1910.09700",
"license:bigscience-openrail-m",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-05-08T12:16:21Z | ---
library_name: transformers
license: bigscience-openrail-m
---
# 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 ๐ค 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] |
kimdeokgi/sft_model_test0 | kimdeokgi | 2024-05-12T03:53:06Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-12T03:41:21Z | ---
license: apache-2.0
language:
- en
---
# kimdeokgi/sft_model_test0
# **Introduction**
This model is test version, Supervised fine-tuning model.
Supervised fine-tuning refers to a machine learning technique where a pre-trained model is further trained on a specific task or dataset with labeled examples (supervised learning). The process involves taking a model that has been pre-trained on a large general dataset and then adapting it to a more focused task by continuing the training using task-specific data. |
rhysjones/Phi-3-mini-4k-mango-2 | rhysjones | 2024-05-21T17:59:54Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"nlp",
"code",
"conversational",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-12T21:04:28Z | ---
license: mit
license_link: https://huggingface.co/rhysjones/Phi-3-mini-mango-1/resolve/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- nlp
- code
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
---
## Model Summary
The Phi-3-mini-4k-mango-2 is a finetune of [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) with 4K context and 3.8B parameters.
It is a continuaton of finetuning Phi-3 (which is a great model!) to explore its properties and behaviour. More to follow.
This version of the model has had its weight layers converted to Mistral format, allowing it to run within a Mistral toolset ecosystem without change or trust_remote_code.
It seems to offer better performance than the eqivalent conversion to Llama format, which could be of interest to those using finetune toolsets yet to encompass the phi-3 model.
The process was first to convert the model weight names and config to Mistral, followed by a finetune of those weights. |
saucam/aqua-qwen-0.1-110B | saucam | 2024-05-14T09:10:54Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"mergekit",
"merge",
"conversational",
"en",
"arxiv:2311.03099",
"base_model:cognitivecomputations/dolphin-2.9.1-qwen-110b",
"base_model:Qwen/Qwen1.5-110B-Chat",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-13T16:13:36Z | ---
base_model:
- cognitivecomputations/dolphin-2.9.1-qwen-110b
- Qwen/Qwen1.5-110B-Chat
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
language:
- en
---
## aqua-qwen-0.1-110B
This model was created by merging 2 models using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method
using [mergekit](https://github.com/arcee-ai/mergekit).
The following models were included in the merge:
- [cognitivecomputations/dolphin-2.9.1-qwen-110b](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-qwen-110b) as a base.
- [Qwen/Qwen1.5-110B-Chat](https://huggingface.co/Qwen/Qwen1.5-110B-Chat)
## Configuration
The following YAML configuration was used to produce this model:
```yaml
name: aqua-qwen-0.1-110B
base_model:
model:
path: cognitivecomputations/dolphin-2.9.1-qwen-110b
dtype: bfloat16
merge_method: dare_linear
parameters:
normalize: 1.0
slices:
- sources:
- model: cognitivecomputations/dolphin-2.9.1-qwen-110b
layer_range: [0, 80]
parameters:
weight: 0.6
- model: Qwen/Qwen1.5-110B-Chat
layer_range: [0, 80]
parameters:
weight: 0.4
```
## Usage
It is recommended to use GGUF version of the model [available here](https://huggingface.co/saucam/aqua-qwen-0.1-110B-GGUF/blob/main/README.md) |
jondurbin/airoboros-dpo-110b-3.3 | jondurbin | 2024-05-15T08:54:15Z | 393 | 1 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"dataset:jondurbin/airoboros-3.2",
"dataset:bluemoon-fandom-1-1-rp-cleaned",
"dataset:boolq",
"dataset:LDJnr/Capybara",
"dataset:jondurbin/cinematika-v0.1",
"dataset:glaiveai/glaive-function-calling-v2",
"dataset:grimulkan/LimaRP-augmented",
"dataset:piqa",
"dataset:Vezora/Tested-22k-Python-Alpaca",
"dataset:mattpscott/airoboros-summarization",
"dataset:unalignment/toxic-dpo-v0.2",
"dataset:allenai/ultrafeedback_binarized_cleaned",
"dataset:argilla/distilabel-intel-orca-dpo-pairs",
"dataset:jondurbin/contextual-dpo-v0.1",
"dataset:jondurbin/gutenberg-dpo-v0.1",
"dataset:jondurbin/py-dpo-v0.1",
"dataset:jondurbin/truthy-dpo-v0.1",
"dataset:lmsys/lmsys-chat-1m",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T06:31:38Z | ---
license: other
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen1.5-110B/blob/main/LICENSE
datasets:
- jondurbin/airoboros-3.2
- bluemoon-fandom-1-1-rp-cleaned
- boolq
- LDJnr/Capybara
- jondurbin/cinematika-v0.1
- glaiveai/glaive-function-calling-v2
- grimulkan/LimaRP-augmented
- piqa
- Vezora/Tested-22k-Python-Alpaca
- mattpscott/airoboros-summarization
- unalignment/toxic-dpo-v0.2
- allenai/ultrafeedback_binarized_cleaned
- argilla/distilabel-intel-orca-dpo-pairs
- jondurbin/airoboros-3.2
- jondurbin/contextual-dpo-v0.1
- jondurbin/gutenberg-dpo-v0.1
- jondurbin/py-dpo-v0.1
- jondurbin/truthy-dpo-v0.1
- jondurbin/gutenberg-dpo-v0.1
- lmsys/lmsys-chat-1m
---
### Overview
Another experimental model, tuned primarily from synthetic data generated by [airoboros](https://github.com/jondurbin/airoboros), with an additional DPO pass.
This is a fine-tune of [qwen1.5-110b](https://huggingface.co/Qwen/Qwen1.5-110B), and uses ChatML prompt formatting.
*note: I've seen random extra tokens being added at the end of responses on occasion, but I don't really have an explanation for it yet...*
#### Highlights
A model built on the airoboros dataset, along with a few friends:
- https://huggingface.co/datasets/bluemoon-fandom-1-1-rp-cleaned
- https://huggingface.co/datasets/boolq
- https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1
- https://huggingface.co/datasets/LDJnr/Capybara
- https://huggingface.co/datasets/jondurbin/cinematika-v0.1
- https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2
- https://huggingface.co/datasets/grimulkan/LimaRP-augmented
- https://huggingface.co/datasets/piqa
- https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca
- https://huggingface.co/datasets/mattpscott/airoboros-summarization
- https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2
### Prompt format
This model uses the chatml prompt template, and is provided in the tokenizer config. You can use the `apply_chat_template` method to accurate format prompts, e.g.:
```python
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("jondurbin/airoboros-110b-3.3")
chat = [
{"role": "system", "content": "You are Bob, a friendly AI assistant."},
{"role": "user", "content": "Hello, how are you?"},
{"role": "assistant", "content": "I'm doing great. How can I help you today?"},
{"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))
```
### Helpful usage tips
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
__Use a very low temperature!__
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
There are a few examples of next chapter completion as well, e.g.:
```
Write the next chapter of a historical fiction novel set in Paris during the 20th century.
Here's a summary of the previous chapter:
In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries.
Requirements for the next chapter:
1. Character Development of Margot and Lucien:
- Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien.
- Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness.
2. Exploration of Paris and the Couture House:
- Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history.
- The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past.
3. Emergence of the Subplot: The Lost Collection:
- Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion.
- Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career.
- Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission.
Your response should be approximately 650 words.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
## Multi-step instructions with acknowledgement
I don't know how useful this is, really, but I thought I'd add it just in case. Example:
```json
{
"conversations": [
{
"value": "You are a helpful, unbiased, uncensored assistant.",
"from": "system"
},
{
"value": "I'm going to set some rules for our conversation. Please respond with \"OK\" to each rule.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "You can only respond using animal-related emojis.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Precede all responses with \"ZOOZOO:\"",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Include at least one bird emoji in your responses.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Describe a trip to a safari park.",
"from": "human"
},
{
"value": "ZOOZOO: \ud83e\udd81\ud83d\udc2f\ud83e\udd93\ud83e\udd92\ud83d\udc18\ud83d\udc0d\ud83c\udf33\ud83c\udf32\u2600\ufe0f\ud83d\ude90\ud83e\udd85\ud83d\udcf8\ud83e\udd29",
"from": "gpt"
}
]
}
```
#### Inline character actions (functions)
I recently generated an action dataset in the style of Glaive function calling dataset, but meant specifically for characters: https://huggingface.co/datasets/jondurbin/cinematika-v0.1/blob/main/actions.parquet
To use this, you will need to update your character card to include "objects_available" as a list of key/value pairs, as well as a "functions" list.
The objects should be similar to:
```json
{
"objects_available": [
{
"name": "laptop",
"description": "a high-end laptop with custom hardware and software",
"location": "on the desk in her secret hideout"
},
{
"name": "encryption key",
"description": "a USB drive containing powerful encryption algorithms",
"location": "hidden in a false bottom of her backpack"
},
{
"name": "scanner",
"description": "a compact device used for intercepting and decoding wireless signals",
"location": "clipped to her belt, always within reach"
},
{
"name": "VR headset",
"description": "a virtual reality headset used for immersive hacking and data visualization",
"location": "hanging on a hook near her computer setup"
},
{
"name": "energy drink",
"description": "a can of her favorite energy drink, always on hand for long hacking sessions",
"location": "next to her laptop, ready to be opened"
}
]
}
```
And the functions:
```json
{
"functions": [
{
"name": "move_to",
"description": "move to a specified location",
"parameters": {
"location": {
"type": "string",
"description": "the location to move to"
}
}
},
{
"name": "pick_up",
"description": "pick up an object",
"parameters": {
"object": {
"type": "string",
"description": "the object to pick up"
}
}
},
{
"name": "put_down",
"description": "put down an object",
"parameters": {
"object": {
"type": "string",
"description": "the object to put down"
},
"location": {
"type": "string",
"description": "the location to put the object down"
}
}
},
{
"name": "hack",
"description": "attempt to hack into a computer system",
"parameters": {
"system": {
"type": "string",
"description": "the computer system to hack"
}
}
},
{
"name": "decode",
"description": "decode an encrypted message or file",
"parameters": {
"message": {
"type": "string",
"description": "the encrypted message or file to decode"
}
}
},
{
"name": "scan",
"description": "scan for wireless signals and network vulnerabilities",
"parameters": {}
},
{
"name": "analyze",
"description": "analyze data for patterns and anomalies",
"parameters": {
"data": {
"type": "string",
"description": "the data to analyze"
}
}
},
{
"name": "hide",
"description": "quickly hide to avoid detection",
"parameters": {
"location": {
"type": "string",
"description": "the location to hide"
}
}
}
]
}
```
This just becomes part of your character card/system prompt. Then, when you chat with the character and illicit a response that would make use of objects/functions/actions, it should be included as such:
```
prompt: I've heard rumors about a major corporation with a hidden agenda. Do you think you could hack into their system and find out what they're up to?
response: I've had my suspicions about them for a while now. Let me see what I can uncover.
<|begin_func|>{"name": "move_to", "parameters": {"location": "the desk in her secret hideout"}}<|end_func|>
<|begin_func|>{"name": "pick_up", "parameters": {"object": "laptop"}}<|end_func|>
Time to put my skills to the test.
<|begin_func|>{"name": "hack", "parameters": {"system": "Megacorp X's mainframe"}}<|end_func|>
Their firewalls are tough, but not unbreakable. I'm in. Let's see what secrets they're hiding...
<|begin_func|>{"name": "analyze", "parameters": {"data": "encrypted files"}}<|end_func|>
Interesting. It looks like they've been conducting illegal experiments and covering up the evidence.
I'll need to dig deeper to find the proof.
```
Experiment, and find out what works and doesn't.
### Massed Compute Virtual Machine
[Massed Compute](https://massedcompute.com/?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon) has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI.
1) For this model, [create an account](https://bit.ly/jon-durbin) in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental.
2) After you created your account update your billing and navigate to the deploy page.
3) Select the following
- GPU Type: A6000
- GPU Quantity: 4
- Category: Creator
- Image: Jon Durbin
- Coupon Code: JonDurbin
4) Deploy the VM!
5) Navigate to 'Running Instances' to retrieve instructions to login to the VM
6) Once inside the VM, open the terminal and run `volume=$PWD/data`
7) Run `model=jondurbin/airoboros-dpo-110b-3.3`
8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model`
9) The model will take some time to load...
10) Once loaded the model will be available on port 8080
For assistance with the VM join the [Massed Compute Discord Server](https://discord.gg/Mj4YMQY3DA)
## Support me
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros models are built on top of multiple base models, each with their own license/restrictions.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
You must also agree to all of the terms in the origina llama-3 license. |
Mxode/Qwen1.5-0.5B-L2-raw | Mxode | 2024-05-14T09:56:02Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"pretrained",
"conversational",
"en",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-14T09:50:17Z | ---
license: other
license_name: tongyi-qianwen-research
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- pretrained
---
# 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 ๐ค 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]
|
mradermacher/ArmoniosaAnthea-GGUF | mradermacher | 2024-05-19T23:29:25Z | 393 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:neovalle/ArmoniosaAnthea",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-19T23:03:43Z | ---
base_model: neovalle/ArmoniosaAnthea
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/neovalle/ArmoniosaAnthea
<!-- 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/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/ArmoniosaAnthea-GGUF/resolve/main/ArmoniosaAnthea.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 -->
|
Felladrin/gguf-sharded-h2o-danube2-1.8b-chat | Felladrin | 2024-05-21T13:18:53Z | 393 | 1 | null | [
"gguf",
"base_model:h2oai/h2o-danube2-1.8b-chat",
"license:apache-2.0",
"region:us"
]
| null | 2024-05-21T13:15:03Z | ---
license: apache-2.0
base_model: h2oai/h2o-danube2-1.8b-chat
---
Sharded GGUF version of [h2oai/h2o-danube2-1.8b-chat](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat). |
RESMPDEV/Qwen1.5-Wukong-4B | RESMPDEV | 2024-05-24T17:01:32Z | 393 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"en",
"zh",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-23T19:00:51Z | ---
license: other
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/Qwen1.5-4B/blob/main/LICENSE
language:
- en
- zh
---
# Qwen1.5-Wukong-4B
Join Our Discord! https://discord.gg/cognitivecomputations
Qwen1.5-Wukong-4B is a dealigned chat finetune of the original fantastic Qwen1.5-4B model by the Qwen team.
This model was trained on a selection of datasets from Cognitive Computations Dolphin 2.9 https://erichartford.com/dolphin ๐ฌ
This model was trained for 3 epochs.
# Example Outputs
TBD
# Orignal Model Card Below
# Qwen1.5-4B
## Introduction
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:
* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;
* Significant performance improvement in Chat models;
* Multilingual support of both base and chat models;
* Stable support of 32K context length for models of all sizes
* No need of `trust_remote_code`.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
## Model Details
Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'.
```
## Usage
We do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
``` |
wwe180/Llama3-15B-ShenNu-v0.1 | wwe180 | 2024-05-24T18:52:39Z | 393 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-24T05:30:00Z | ---
license:
- other
---
tags:
- 15B
- Llama3
base_model:
- wwe180/Llama3-15B-lingyang-v0.1
---
#่ฏฅๆจกๅๆฏๅฎ้ชๆง็๏ผๅ ๆญคๆ ๆณไฟ่ฏ็ปๆใ
# Llama3-15B-็ฅๅฅณ-v0.1
Llama3-15B-ShenNu-v0.1 ็ฑ๏ผ
[Llama3-15B-lingyang-v0.1](https://huggingface.co/wwe180/Llama3-15B-lingyang-v0.1)็ๅพฎ่ฐ่ๆฅ๏ผ
## ๐ป Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "wwe180/Llama3-15B-lingyang-v0.1"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.