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
|
|---|---|---|---|---|---|---|---|---|---|
bartowski/aixcoder-7b-GGUF | bartowski | 2024-04-11T15:14:08Z | 405 | 5 | null | [
"gguf",
"text-generation",
"region:us"
]
| text-generation | 2024-04-11T14:52:17Z | ---
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp Quantizations of aixcoder-7b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2636">b2636</a> for quantization.
Original model: https://huggingface.co/aiXcoder/aixcoder-7b
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
## Prompt format
No prompt template for this model.
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [aixcoder-7b-Q8_0.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q8_0.gguf) | Q8_0 | 7.89GB | Extremely high quality, generally unneeded but max available quant. |
| [aixcoder-7b-Q6_K.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q6_K.gguf) | Q6_K | 6.55GB | Very high quality, near perfect, *recommended*. |
| [aixcoder-7b-Q5_K_M.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q5_K_M.gguf) | Q5_K_M | 5.56GB | High quality, *recommended*. |
| [aixcoder-7b-Q5_K_S.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q5_K_S.gguf) | Q5_K_S | 5.25GB | High quality, *recommended*. |
| [aixcoder-7b-Q4_K_M.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q4_K_M.gguf) | Q4_K_M | 4.84GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [aixcoder-7b-Q4_K_S.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q4_K_S.gguf) | Q4_K_S | 4.48GB | Slightly lower quality with more space savings, *recommended*. |
| [aixcoder-7b-IQ4_NL.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ4_NL.gguf) | IQ4_NL | 4.25GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [aixcoder-7b-IQ4_XS.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ4_XS.gguf) | IQ4_XS | 4.08GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [aixcoder-7b-Q3_K_L.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q3_K_L.gguf) | Q3_K_L | 4.05GB | Lower quality but usable, good for low RAM availability. |
| [aixcoder-7b-Q3_K_M.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q3_K_M.gguf) | Q3_K_M | 3.86GB | Even lower quality. |
| [aixcoder-7b-IQ3_M.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ3_M.gguf) | IQ3_M | 3.64GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [aixcoder-7b-IQ3_S.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ3_S.gguf) | IQ3_S | 3.54GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [aixcoder-7b-Q3_K_S.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q3_K_S.gguf) | Q3_K_S | 3.52GB | Low quality, not recommended. |
| [aixcoder-7b-IQ3_XS.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ3_XS.gguf) | IQ3_XS | 3.37GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [aixcoder-7b-IQ3_XXS.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ3_XXS.gguf) | IQ3_XXS | 3.26GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [aixcoder-7b-Q2_K.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-Q2_K.gguf) | Q2_K | 3.07GB | Very low quality but surprisingly usable. |
| [aixcoder-7b-IQ2_M.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ2_M.gguf) | IQ2_M | 3.02GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [aixcoder-7b-IQ2_S.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ2_S.gguf) | IQ2_S | 2.88GB | Very low quality, uses SOTA techniques to be usable. |
| [aixcoder-7b-IQ2_XS.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ2_XS.gguf) | IQ2_XS | 2.79GB | Very low quality, uses SOTA techniques to be usable. |
| [aixcoder-7b-IQ2_XXS.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ2_XXS.gguf) | IQ2_XXS | 2.63GB | Lower quality, uses SOTA techniques to be usable. |
| [aixcoder-7b-IQ1_M.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ1_M.gguf) | IQ1_M | 2.46GB | Extremely low quality, *not* recommended. |
| [aixcoder-7b-IQ1_S.gguf](https://huggingface.co/bartowski/aixcoder-7b-GGUF/blob/main/aixcoder-7b-IQ1_S.gguf) | IQ1_S | 2.35GB | Extremely low quality, *not* recommended. |
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
mradermacher/Merged-RP-Stew-V2-68B-GGUF | mradermacher | 2024-05-06T04:40:09Z | 405 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"roleplay",
"exl2",
"not-for-all-audiences",
"en",
"base_model:Kotokin/Merged-RP-Stew-V2-68B",
"license:other",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-18T16:26:14Z | ---
base_model: Kotokin/Merged-RP-Stew-V2-68B
language:
- en
library_name: transformers
license: other
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
license_name: yi-34b
quantized_by: mradermacher
tags:
- merge
- roleplay
- exl2
- not-for-all-audiences
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Kotokin/Merged-RP-Stew-V2-68B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-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/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q2_K.gguf) | Q2_K | 25.2 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.IQ3_XS.gguf) | IQ3_XS | 28.0 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q3_K_S.gguf) | Q3_K_S | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.IQ3_S.gguf) | IQ3_S | 29.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.IQ3_M.gguf) | IQ3_M | 30.7 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q3_K_M.gguf) | Q3_K_M | 32.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q3_K_L.gguf) | Q3_K_L | 35.8 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.IQ4_XS.gguf) | IQ4_XS | 36.8 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q4_K_S.gguf) | Q4_K_S | 38.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q4_K_M.gguf) | Q4_K_M | 40.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q5_K_S.gguf) | Q5_K_S | 46.8 | |
| [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q5_K_M.gguf) | Q5_K_M | 48.1 | |
| [PART 1](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q6_K.gguf.part2of2) | Q6_K | 55.8 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-68B-GGUF/resolve/main/Merged-RP-Stew-V2-68B.Q8_0.gguf.part2of2) | Q8_0 | 72.2 | 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 -->
|
ehristoforu/Gixtral-100B | ehristoforu | 2024-04-21T12:19:06Z | 405 | 3 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"mixtral-8x22b",
"mixtral-8x7b",
"instruct",
"moe",
"merge",
"conversational",
"en",
"fr",
"de",
"es",
"it",
"dataset:ehartford/dolphin",
"dataset:jondurbin/airoboros-2.2.1",
"dataset:ehartford/dolphin-coder",
"dataset:migtissera/Synthia-v1.3",
"dataset:teknium/openhermes",
"dataset:ise-uiuc/Magicoder-OSS-Instruct-75K",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"dataset:LDJnr/Pure-Dove",
"base_model:mistralai/Mixtral-8x22B-Instruct-v0.1",
"base_model:mistralai/Mixtral-8x7B-Instruct-v0.1",
"base_model:cognitivecomputations/dolphin-2.7-mixtral-8x7b",
"base_model:alpindale/WizardLM-2-8x22B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-21T09:28:55Z | ---
base_model:
- mistralai/Mixtral-8x22B-Instruct-v0.1
- mistralai/Mixtral-8x7B-Instruct-v0.1
- cognitivecomputations/dolphin-2.7-mixtral-8x7b
- alpindale/WizardLM-2-8x22B
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
- ehartford/dolphin-coder
- migtissera/Synthia-v1.3
- teknium/openhermes
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
- LDJnr/Pure-Dove
library_name: transformers
tags:
- mixtral
- mixtral-8x22b
- mixtral-8x7b
- instruct
- moe
- merge
pipeline_tag: text-generation
license: apache-2.0
language:
- en
- fr
- de
- es
- it
---
# Gixtral 100B (Mixtral from 8x22B & 8x7B to 100B)
We created a model from other cool models to combine everything into one cool model.
## Model Details
### Model Description
- **Developed by:** [@ehristoforu](https://huggingface.co/ehristoforu)
- **Model type:** Text Generation (conversational)
- **Language(s) (NLP):** English, French, German, Spanish, Italian
- **Finetuned from model:** [mistralai/Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1) & [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
## How to Get Started with the Model
Use the code below to get started with the model.
```py
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ehristoforu/Gixtral-100B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
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?"}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## About merge
Base model: mistralai/Mixtral-8x22B-Instruct-v0.1 & mistralai/Mixtral-8x7B-Instruct-v0.1
Merge models:
- mistralai/Mixtral-8x22B-Instruct-v0.1
- mistralai/Mixtral-8x7B-Instruct-v0.1
- cognitivecomputations/dolphin-2.7-mixtral-8x7b
- alpindale/WizardLM-2-8x22B
Merge datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
- ehartford/dolphin-coder
- migtissera/Synthia-v1.3
- teknium/openhermes
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
- LDJnr/Pure-Dove |
Locutusque/Llama-3-Yggdrasil-8B | Locutusque | 2024-06-04T19:56:54Z | 405 | 3 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:NousResearch/Meta-Llama-3-8B",
"base_model:NousResearch/Meta-Llama-3-8B-Instruct",
"base_model:Locutusque/Llama-3-Hercules-5.0-8B",
"base_model:Locutusque/llama-3-neural-chat-v2.2-8b",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-21T15:42:52Z | ---
base_model:
- NousResearch/Meta-Llama-3-8B
- NousResearch/Meta-Llama-3-8B-Instruct
- Locutusque/Llama-3-Hercules-5.0-8B
- Locutusque/llama-3-neural-chat-v2.2-8b
library_name: transformers
tags:
- mergekit
- merge
license: llama3
---
# 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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
### Models Merged
The following models were included in the merge:
* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
* [Locutusque/Llama-3-Hercules-5.0-8B](https://huggingface.co/Locutusque/Llama-3-Hercules-5.0-8B)
* [Locutusque/llama-3-neural-chat-v2.2-8b](https://huggingface.co/Locutusque/llama-3-neural-chat-v2.2-8b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: NousResearch/Meta-Llama-3-8B
# No parameters necessary for base model
- model: NousResearch/Meta-Llama-3-8B-Instruct
parameters:
density: 0.6
weight: 0.55
- model: Locutusque/llama-3-neural-chat-v2.2-8b
parameters:
density: 0.55
weight: 0.45
- model: Locutusque/Llama-3-Hercules-5.0-8B
parameters:
density: 0.57
weight: 0.5
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
int8_mask: true
dtype: bfloat16
``` |
RichardErkhov/Yukang_-_LongAlpaca-7B-gguf | RichardErkhov | 2024-05-30T07:16:00Z | 405 | 0 | null | [
"gguf",
"arxiv:2309.12307",
"region:us"
]
| null | 2024-05-30T04:33:50Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
LongAlpaca-7B - GGUF
- Model creator: https://huggingface.co/Yukang/
- Original model: https://huggingface.co/Yukang/LongAlpaca-7B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [LongAlpaca-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q2_K.gguf) | Q2_K | 2.36GB |
| [LongAlpaca-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
| [LongAlpaca-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [LongAlpaca-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [LongAlpaca-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [LongAlpaca-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q3_K.gguf) | Q3_K | 3.07GB |
| [LongAlpaca-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [LongAlpaca-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [LongAlpaca-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [LongAlpaca-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q4_0.gguf) | Q4_0 | 3.56GB |
| [LongAlpaca-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
| [LongAlpaca-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [LongAlpaca-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q4_K.gguf) | Q4_K | 3.8GB |
| [LongAlpaca-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [LongAlpaca-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q4_1.gguf) | Q4_1 | 3.95GB |
| [LongAlpaca-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q5_0.gguf) | Q5_0 | 4.33GB |
| [LongAlpaca-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [LongAlpaca-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q5_K.gguf) | Q5_K | 4.45GB |
| [LongAlpaca-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
| [LongAlpaca-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q5_1.gguf) | Q5_1 | 4.72GB |
| [LongAlpaca-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q6_K.gguf) | Q6_K | 5.15GB |
| [LongAlpaca-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Yukang_-_LongAlpaca-7B-gguf/blob/main/LongAlpaca-7B.Q8_0.gguf) | Q8_0 | 6.67GB |
Original model description:
# LongLoRA and LongAlpaca for Long-context LLMs
[](https://huggingface.co/Yukang)
[](https://github.com/dvlab-research/LongLoRA)
[](https://huggingface.co/datasets/Yukang/LongAlpaca-12k)
[](https://arxiv.org/abs/2309.12307)
[](https://github.com/dvlab-research/LongLoRA/blob/main/LICENSE)
[](https://github.com/dvlab-research/LongLoRA/blob/main/DATA_LICENSE)
[](https://github.com/dvlab-research/LongLoRA/blob/main/WEIGHT_LICENSE)
For detailed usage and codes, please visit the [Github project](https://github.com/dvlab-research/LongLoRA).
## TABLE OF CONTENTS
1. [News](#news)
2. [Examples](#examples)
3. [Highlights](#highlights)
4. [How to contribute](#how-to-contribute)
5. [Requirements](#usage-requirements)
6. [Installation and quick guide](#installation-and-quick-guide)
7. [LongAlpaca Data](#longalpaca-data)
8. [Models](#models)
9. [Training](#training)
10. [Evaluation](#evaluation)
11. [Demo](#demo)
12. [Data Generation via Pdf2Text](#data-generation-via-pdf2text)
13. [Citation](#citation)
14. [Acknowledgement](#acknowledgement)
15. [License](#license)
## News
- [x] [2023.10.8] **We release the long instruction-following dataset**, [LongAlpaca-12k](https://huggingface.co/datasets/Yukang/LongAlpaca-12k) and **the corresponding models**, [LongAlpaca-7B](https://huggingface.co/Yukang/LongAlpaca-7B), [LongAlpaca-13B](https://huggingface.co/Yukang/LongAlpaca-13B), and [LongAlpaca-70B](https://huggingface.co/Yukang/LongAlpaca-70B).
- (*The previous sft models*, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft), *have been depreciated*.)
- [x] [2023.10.3] We add support GPTNeoX models. Please refer to this [PR](https://github.com/dvlab-research/LongLoRA/pull/32) for usage. Thanks for @naubull2 for this contribution.
- [x] [2023.9.22] We release all our fine-tuned [models](https://huggingface.co/Yukang), including **70B-32k models**, [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k), [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft). Welcome to check them out!
- [x] [2023.9.22] We release [Paper](http://arxiv.org/abs/2309.12307) and this GitHub repo, including training and evaluation code.
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Highlights
1. In LongLoRA approach, The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and is not required during inference.
2. We released all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We built up a long-context instruction-following dataset, [LongAlpaca-12k](#longalpaca-data). We released the corresponding [LongAlpaca-7B](https://huggingface.co/Yukang/LongAlpaca-7B), [LongAlpaca-13B](https://huggingface.co/Yukang/LongAlpaca-13B) and [LongAlpaca-70B](https://huggingface.co/Yukang/LongAlpaca-70B) models. To our best knowledge, this is the first open-sourced long-context 70B model.
## How to Contribute
- Make sure to have git installed.
- Create your own [fork](https://github.com/dvlab-research/LongLoRA/fork) of the project.
- Clone the repository on your local machine, using git clone and pasting the url of this project.
- Read both the `Requirements` and `Installation and Quick Guide` sections below.
- Commit and push your changes.
- Make a pull request when finished modifying the project.
## Usage Requirements
To download and use the [pre-trained weights](#pre-trained-weights) you will need:
1. Hugging Face (HF) account with valid email. Note, the email used for HF must alse be used for the license agreement.
2. Accept the Meta [license and acceptable use policy](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
## Installation and Quick Guide
To install and run the application:
1. [Fork this repo](https://github.com/dvlab-research/LongLoRA/fork) on github
2. Clone the repository on your local machine, using git clone and pasting the url of this project.
3. Run the following code:
```
pip install -r requirements.txt
pip install flash-attn --no-build-isolation
```
4. Use either a [Released model](#released-models) or [Fine tune](#fine-tuning) a model to fit your preferences.
5. Test your model by chat.
6. Deploy your own demo.
## LongAlpaca Data
LongAlpaca-12k contains 9k long QA data that we collected and 3k short QA sampled from the original [Alpaca data](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json). This is to avoid the case that the model might degrade at short instruction following. The data we collect contains various types and amounts as the following figure.
| Data | Short QA | Long QA | Total | Download |
|:---------------|----------|----------|----------|----------|
| LongAlpaca-12k | 3k | 9k | 12k | [Link](https://huggingface.co/datasets/Yukang/LongAlpaca-12k) |
Following the original Alpaca format, our Long QA data uses the following prompts for fine-tuning:
- `instruction`: `str`, describes the task the model should perform. For example, to answer a question after reading a book section or paper. We vary the contents and questions to make instructions diverse.
- `output`: `str`, the answer to the instruction.
We did not use the `input` format in the Alpaca format for simplicity.
## Models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:---------------|------|---------|---------|-----------------------------------------------------------------------------------------------------------------------|
| LongAlpaca-7B | 7B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/LongAlpaca-7B) |
| LongAlpaca-13B | 13B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/LongAlpaca-13B) |
| LongAlpaca-70B | 70B | 32768 | LoRA+ | [Model](https://huggingface.co/Yukang/LongAlpaca-70B) [(LoRA-weight)](https://huggingface.co/Yukang/LongAlpaca-70B-lora) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [Model](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|---------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [LoRA-weight](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Training
### Pre-trained weights
We use LLaMA2 models as the pre-trained weights and fine-tune them to long context window sizes. Download based on your choices.
| Pre-trained weights |
|:-------------------------------------------------------------------------------------|
| [Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) |
|[Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) |
| [Llama-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b-hf) |
| [Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
| [Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) |
| [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) |
This project also supports GPTNeoX models as the base model architecture. Some candidate pre-trained weights may include [GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b), [Polyglot-ko-12.8B](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) and other variants.
### Fine-tuning
```
torchrun --nproc_per_node=8 fine-tune.py \
--model_name_or_path path_to/Llama-2-7b-hf \
--bf16 True \
--output_dir path_to_saving_checkpoints \
--cache_dir path_to_cache \
--model_max_length 8192 \
--use_flash_attn True \
--low_rank_training False \
--num_train_epochs 1 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 2 \
--gradient_accumulation_steps 8 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 2e-5 \
--weight_decay 0.0 \
--warmup_steps 20 \
--lr_scheduler_type "constant_with_warmup" \
--logging_steps 1 \
--deepspeed "ds_configs/stage2.json" \
--tf32 True \
--max_steps 1000
```
- Please remember to change `path_to/Llama-2-7b-hf`, `path_to_saving_checkpoints`, `path_to_cache` to your own directory.
- Note that you can change `model_max_length` to other values.
- You could change `ds_configs/stage2.json` to `ds_configs/stage3.json` if you want.
- Please set `use_flash_attn` as `False` if you use V100 machines or do not install flash attention.
- You can set `low_rank_training` as `False` if you want to use fully fine-tuning. It will cost more GPU memory and slower, but the performance will be a bit better.
- When training is finished, to get the full model weight:
```
cd path_to_saving_checkpoints && python zero_to_fp32.py . pytorch_model.bin
```
### Supervised Fine-tuning
```
torchrun --nproc_per_node=8 supervised-fine-tune.py \
--model_name_or_path path_to_Llama2_chat_models \
--bf16 True \
--output_dir path_to_saving_checkpoints \
--model_max_length 32768 \
--use_flash_attn True \
--data_path LongAlpaca-12k.json \
--low_rank_training True \
--num_train_epochs 3 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 2 \
--gradient_accumulation_steps 1 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 2e-5 \
--weight_decay 0.0 \
--warmup_steps 20 \
--lr_scheduler_type "constant_with_warmup" \
--logging_steps 1 \
--deepspeed "ds_configs/stage2.json" \
--tf32 True
```
- There is no need to make supervised fine-tuning upon the fine-tuned context extended models. It is all right to directly use base model as Llama2-chat models, as the amount of long instruction following data is enough for SFT.
- Our long instruction following data can be found in [LongAlpaca-12k.json](https://huggingface.co/datasets/Yukang/LongAlpaca-12k).
### Get trainable weights in low-rank training
In low-rank training, we set embedding and normalization layers as trainable. Please use the following line to extract the trainable weights `trainable_params.bin` from `pytorch_model.bin`
```
python3 get_trainable_weights.py --checkpoint_path path_to_saving_checkpoints --trainable_params "embed,norm"
```
### Merge LoRA Weight
Merge the LoRA weights of `pytorch_model.bin` and trainable parameters `trainable_params.bin`, save the resulting model into your desired path in the Hugging Face format:
```
python3 merge_lora_weights_and_save_hf_model.py \
--base_model path_to/Llama-2-7b-hf \
--peft_model path_to_saving_checkpoints \
--context_size 8192 \
--save_path path_to_saving_merged_model
```
For example,
```
python3 merge_lora_weights_and_save_hf_model.py \
--base_model /dataset/pretrained-models/Llama-2-7b-hf \
--peft_model /dataset/yukangchen/hf_models/lora-models/Llama-2-7b-longlora-8k \
--context_size 8192 \
--save_path /dataset/yukangchen/models/Llama-2-7b-longlora-8k-merged
```
## Evaluation
### Perplexity Validation
To evaluate a model that is trained in the low-rank setting, please set both `base_model` and `peft_model`. `base_model` is the pre-trained weight. `peft_model` is the path to the saved checkpoint, which should contain `trainable_params.bin`, `adapter_model.bin` and `adapter_config.json`. For example,
```
python3 eval.py --seq_len 8192 --context_size 8192 --batch_size 1 --base_model path_to/Llama-2-7b-hf --peft_model path_to_saving_checkpoints --data_path pg19/test.bin
```
To evaluate a model that is fully fine-tuned, you only need to set `base_model` as the path to the saved checkpoint, which should contain `pytorch_model.bin` and `config.json`. `peft_model` should be ignored.
```
python3 eval.py --seq_len 8192 --context_size 8192 --batch_size 1 --base_model path_to_saving_checkpoints --data_path pg19/test.bin
```
- Note that `--seq_len` is to set the sequence length for evaluation. `--context_size` is to set the context length of the model during fine-tuning. `--seq_len` should not be larger than `--context_size`.
- We have already tokenized the validation and test splits of PG19 and proof-pile dataset into `pg19/validation.bin`, `pg19/test.bin`, and `proof-pile/test_sampled_data.bin`, with the tokenizer of LLaMA. `proof-pile/test_sampled_data.bin` contains 128 documents that are randomly sampled from the total proof-pile test split. For each document, it has at least 32768 tokens. We also release the sampled ids in [proof-pile/test_sampled_ids.bin](https://drive.google.com/file/d/1cnzWODLRQYAd7HeugzLCIhaqzaLZv7J5/view?usp=share_link). You can download them from the links below.
| Dataset | Split | Link |
|:-----------|------------|--------------------------------------------------------------------------------------------------------------|
| PG19 | validation | [pg19/validation.bin](https://drive.google.com/file/d/1rbJvb0qRIf2mQoN2ON7S93TbTzMnlrN6/view?usp=share_link) |
| PG19 | test | [pg19/test.bin](https://drive.google.com/file/d/1QANDMdctpacPAYgS04adDXqByGEq-Ret/view?usp=share_link) |
| Proof-pile | test | [proof-pile/test_sampled_data.bin](https://drive.google.com/file/d/1bUI5lPDvrqzY_XXJJ2sSuvZx0Y9AZClE/view?usp=share_link) |
### Passkey Retrieval
We provide a manner to test the passkey retrieval accuracy. For example,
```
python3 passkey_retrivial.py \
--context_size 32768 \
--base_model path_to/Llama-2-7b-longlora-32k \
--max_tokens 32768 \
--interval 1000
```
- Note that the `context_size` is the context length during fine-tuning.
- `max_tokens` is maximum length for the document in passkey retrieval evaluation.
- `interval` is the interval during the document length increasing. It is a rough number because the document increases by sentences.
## Demo
### Local Inference
To chat with [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) or [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft), you need to run `merge_lora_weights_and_save_hf_model.py` first, and then:
```
python3 inference.py \
--base_model path_to_model \
--question $question \
--context_size $context_length \
--max_gen_len $max_gen_len \
--flash_attn True \
--material $material_content \
--material_type $material_type \
--material_title $material_title
```
To ask a question related to a book:
```
python3 inference.py \
--base_model /data/models/Llama-2-13b-chat-longlora-32k-sft \
--question "Why doesn't Professor Snape seem to like Harry?" \
--context_size 32768 \
--max_gen_len 512 \
--flash_attn True \
--material "materials/Harry Potter and the Philosophers Stone_section2.txt" \
--material_type "book" \
--material_title "Harry Potter and the Philosophers Stone"
```
Note that you can ignore `material_type` or `material_title`.
To ask a question related to a paper:
```
python3 inference.py \
--base_model /data/models/Llama-2-13b-chat-longlora-32k-sft \
--question "What are the main contributions and novelties of this work?" \
--context_size 32768 \
--max_gen_len 512 \
--flash_attn True \
--material "materials/paper1.txt" \
--material_type "paper"
```
### Online Demo
To deploy your own demo run
```
python3 demo.py \
--base_model path_to_model \
--context_size $context_size \
--max_gen_len $max_gen_len \
--flash_attn True
```
Example
```
python3 demo.py \
--base_model /data/models/Llama-2-13b-chat-longlora-32k-sft \
--context_size 32768 \
--max_gen_len 512 \
--flash_attn True
```
- Note that `flash_attn=True` will make the generation slow but save much GPU memory.
## Data Generation via Pdf2text
During our dataset collection, we convert paper and books from pdf to text. The conversion quality has a large influence on the final model quality. We think that this step is non-trivial. We release the tool for the pdf2txt conversion, in the folder `pdf2txt`. It is built upon `pdf2image`, `easyocr`, `ditod` and `detectron2`. Please refer to the [README.md](pdf2txt/README.md) in `pdf2txt` for more details.
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
```
@misc{long-alpaca,
author = {Yukang Chen and Shaozuo Yu and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
title = {Long Alpaca: Long-context Instruction-following models},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/dvlab-research/LongLoRA}},
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work can also be built upon the [GPTNeoX-HF](https://huggingface.co/docs/transformers/model_doc/gpt_neox) which is based upon [EleutherAI/GPTNeoX](https://github.com/EleutherAI/gpt-neox) as the pre-trained model architecture.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- Some evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
## License
- LongLoRA is licensed under the Apache License 2.0. This means that it requires the preservation of copyright and license notices.
- Data and weights are under CC-BY-NC 4.0 License. They are licensed for research use only, and allowed only non-commercial. Models trained using the dataset should not be used outside of research purposes.
|
mradermacher/NeuralStar_FusionWriter_4x7b-GGUF | mradermacher | 2024-06-08T16:32:46Z | 405 | 1 | transformers | [
"transformers",
"gguf",
"moe",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/AlphaMonarch-7B",
"OmnicromsBrain/Eros_Scribe-7b",
"SanjiWatsuki/Kunoichi-DPO-v2-7B",
"OmnicromsBrain/NeuralStar_Fusion-7B",
"en",
"base_model:OmnicromsBrain/NeuralStar_FusionWriter_4x7b",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-07T21:35:09Z | ---
base_model: OmnicromsBrain/NeuralStar_FusionWriter_4x7b
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- moe
- merge
- mergekit
- lazymergekit
- mlabonne/AlphaMonarch-7B
- OmnicromsBrain/Eros_Scribe-7b
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- OmnicromsBrain/NeuralStar_Fusion-7B
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/OmnicromsBrain/NeuralStar_FusionWriter_4x7b
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-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/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q2_K.gguf) | Q2_K | 8.9 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.IQ3_XS.gguf) | IQ3_XS | 10.0 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q3_K_S.gguf) | Q3_K_S | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.IQ3_S.gguf) | IQ3_S | 10.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.IQ3_M.gguf) | IQ3_M | 10.7 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q3_K_M.gguf) | Q3_K_M | 11.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q3_K_L.gguf) | Q3_K_L | 12.6 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.IQ4_XS.gguf) | IQ4_XS | 13.1 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q4_K_S.gguf) | Q4_K_S | 13.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q4_K_M.gguf) | Q4_K_M | 14.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q5_K_S.gguf) | Q5_K_S | 16.7 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q5_K_M.gguf) | Q5_K_M | 17.2 | |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q6_K.gguf) | Q6_K | 19.9 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF/resolve/main/NeuralStar_FusionWriter_4x7b.Q8_0.gguf) | Q8_0 | 25.8 | 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/llama3-70b-instruct-mmlu-college-medicine-en-GGUF | mradermacher | 2024-06-11T22:17:49Z | 405 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:AdamKasumovic/llama3-70b-instruct-mmlu-college-medicine-en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-08T10:45:38Z | ---
base_model: AdamKasumovic/llama3-70b-instruct-mmlu-college-medicine-en
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/AdamKasumovic/llama3-70b-instruct-mmlu-college-medicine-en
<!-- 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/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q2_K.gguf) | Q2_K | 26.5 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.IQ3_M.gguf) | IQ3_M | 32.0 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
| [PART 1](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama3-70b-instruct-mmlu-college-medicine-en-GGUF/resolve/main/llama3-70b-instruct-mmlu-college-medicine-en.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | 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 -->
|
azferruolo/llamacheck | azferruolo | 2024-06-10T18:24:18Z | 405 | 0 | null | [
"gguf",
"license:mit",
"region:us"
]
| null | 2024-06-10T16:14:08Z | ---
license: mit
---
|
mradermacher/DonutHole-8x7B-GGUF | mradermacher | 2024-06-12T20:39:12Z | 405 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:ycros/DonutHole-8x7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-11T03:57:20Z | ---
base_model: ycros/DonutHole-8x7B
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/ycros/DonutHole-8x7B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/DonutHole-8x7B-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/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q2_K.gguf) | Q2_K | 17.4 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.IQ3_XS.gguf) | IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.IQ3_S.gguf) | IQ3_S | 20.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.IQ3_M.gguf) | IQ3_M | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q3_K_M.gguf) | Q3_K_M | 22.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q3_K_L.gguf) | Q3_K_L | 24.3 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.IQ4_XS.gguf) | IQ4_XS | 25.5 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q5_K_S.gguf) | Q5_K_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q5_K_M.gguf) | Q5_K_M | 33.3 | |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/DonutHole-8x7B-GGUF/resolve/main/DonutHole-8x7B.Q8_0.gguf) | Q8_0 | 49.7 | 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 -->
|
Ammartatox/mawremes-Q4_K_M-GGUF | Ammartatox | 2024-06-25T09:01:47Z | 405 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"llama-cpp",
"gguf-my-repo",
"en",
"base_model:Ammartatox/mawremes",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-25T09:01:28Z | ---
base_model: Ammartatox/mawremes
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- llama-cpp
- gguf-my-repo
---
# Ammartatox/mawremes-Q4_K_M-GGUF
This model was converted to GGUF format from [`Ammartatox/mawremes`](https://huggingface.co/Ammartatox/mawremes) 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/Ammartatox/mawremes) 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 Ammartatox/mawremes-Q4_K_M-GGUF --hf-file mawremes-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Ammartatox/mawremes-Q4_K_M-GGUF --hf-file mawremes-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Ammartatox/mawremes-Q4_K_M-GGUF --hf-file mawremes-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Ammartatox/mawremes-Q4_K_M-GGUF --hf-file mawremes-q4_k_m.gguf -c 2048
```
|
mrmage/Phi-3-mini-4k-instruct-Q4_K_S-GGUF | mrmage | 2024-06-27T09:09:33Z | 405 | 0 | null | [
"gguf",
"nlp",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"license:mit",
"region:us"
]
| text-generation | 2024-06-27T09:09:19Z | ---
base_model: microsoft/Phi-3-mini-4k-instruct
language:
- en
license: mit
license_link: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- code
- llama-cpp
- gguf-my-repo
inference:
parameters:
temperature: 0.0
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
---
# mrmage/Phi-3-mini-4k-instruct-Q4_K_S-GGUF
This model was converted to GGUF format from [`microsoft/Phi-3-mini-4k-instruct`](https://huggingface.co/microsoft/Phi-3-mini-4k-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/microsoft/Phi-3-mini-4k-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 mrmage/Phi-3-mini-4k-instruct-Q4_K_S-GGUF --hf-file phi-3-mini-4k-instruct-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo mrmage/Phi-3-mini-4k-instruct-Q4_K_S-GGUF --hf-file phi-3-mini-4k-instruct-q4_k_s.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo mrmage/Phi-3-mini-4k-instruct-Q4_K_S-GGUF --hf-file phi-3-mini-4k-instruct-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo mrmage/Phi-3-mini-4k-instruct-Q4_K_S-GGUF --hf-file phi-3-mini-4k-instruct-q4_k_s.gguf -c 2048
```
|
Dizex/FoodBaseBERT-NER | Dizex | 2023-05-14T19:31:01Z | 404 | 17 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bert",
"token-classification",
"FoodBase",
"NER",
"en",
"dataset:Dizex/FoodBase",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2022-10-31T09:00:15Z | ---
language: en
datasets:
- Dizex/FoodBase
widget:
- text: "Today's meal: Fresh olive poké bowl topped with chia seeds. Very delicious!"
example_title: "Food example 1"
- text: "Tartufo Pasta with garlic flavoured butter and olive oil, egg yolk, parmigiano and pasta water."
example_title: "Food example 2"
tags:
- FoodBase
- NER
license: mit
---
# FoodBaseBERT
## Model description
**FoodBaseBERT** is a fine-tuned BERT model that is ready to use for **Named Entity Recognition** of Food entities. It has been trained to recognize one entity: food (FOOD).
Specifically, this model is a *bert-base-cased* model that was fine-tuned on the [FoodBase NER](https://academic.oup.com/database/article/doi/10.1093/database/baz121/5611291) dataset.
## Intended uses
#### How to use
You can use this model with Transformers *pipeline* for NER.
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Dizex/FoodBaseBERT")
model = AutoModelForTokenClassification.from_pretrained("Dizex/FoodBaseBERT")
pipe = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Today's meal: Fresh olive poké bowl topped with chia seeds. Very delicious!"
ner_entity_results = pipe(example)
print(ner_entity_results)
```
|
timm/convnextv2_atto.fcmae | timm | 2024-02-10T23:29:00Z | 404 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-feature-extraction",
"arxiv:2301.00808",
"license:cc-by-nc-4.0",
"region:us"
]
| image-feature-extraction | 2023-01-05T01:33:59Z | ---
license: cc-by-nc-4.0
library_name: timm
tags:
- image-feature-extraction
- timm
---
# Model card for convnextv2_atto.fcmae
A ConvNeXt-V2 self-supervised feature representation model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE). This model has no pretrained head and is only useful for fine-tune or feature extraction.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 3.4
- GMACs: 0.6
- Activations (M): 3.8
- Image size: 224 x 224
- **Papers:**
- ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders: https://arxiv.org/abs/2301.00808
- **Original:** https://github.com/facebookresearch/ConvNeXt-V2
- **Pretrain 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('convnextv2_atto.fcmae', 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(
'convnextv2_atto.fcmae',
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, 40, 56, 56])
# torch.Size([1, 80, 28, 28])
# torch.Size([1, 160, 14, 14])
# torch.Size([1, 320, 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(
'convnextv2_atto.fcmae',
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, 320, 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).
All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
| model |top1 |top5 |img_size|param_count|gmacs |macts |samples_per_sec|batch_size|
|------------------------------------------------------------------------------------------------------------------------------|------|------|--------|-----------|------|------|---------------|----------|
| [convnextv2_huge.fcmae_ft_in22k_in1k_512](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_512) |88.848|98.742|512 |660.29 |600.81|413.07|28.58 |48 |
| [convnextv2_huge.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_384) |88.668|98.738|384 |660.29 |337.96|232.35|50.56 |64 |
| [convnext_xxlarge.clip_laion2b_soup_ft_in1k](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k) |88.612|98.704|256 |846.47 |198.09|124.45|122.45 |256 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384) |88.312|98.578|384 |200.13 |101.11|126.74|196.84 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k_384) |88.196|98.532|384 |197.96 |101.1 |126.74|128.94 |128 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320) |87.968|98.47 |320 |200.13 |70.21 |88.02 |283.42 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k_384) |87.75 |98.556|384 |350.2 |179.2 |168.99|124.85 |192 |
| [convnextv2_base.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k_384) |87.646|98.422|384 |88.72 |45.21 |84.49 |209.51 |256 |
| [convnext_large.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k_384) |87.476|98.382|384 |197.77 |101.1 |126.74|194.66 |256 |
| [convnext_large_mlp.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k) |87.344|98.218|256 |200.13 |44.94 |56.33 |438.08 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k) |87.26 |98.248|224 |197.96 |34.4 |43.13 |376.84 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384) |87.138|98.212|384 |88.59 |45.21 |84.49 |365.47 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k) |87.002|98.208|224 |350.2 |60.98 |57.5 |368.01 |256 |
| [convnext_base.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k_384) |86.796|98.264|384 |88.59 |45.21 |84.49 |366.54 |256 |
| [convnextv2_base.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k) |86.74 |98.022|224 |88.72 |15.38 |28.75 |624.23 |256 |
| [convnext_large.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k) |86.636|98.028|224 |197.77 |34.4 |43.13 |581.43 |256 |
| [convnext_base.clip_laiona_augreg_ft_in1k_384](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_ft_in1k_384) |86.504|97.97 |384 |88.59 |45.21 |84.49 |368.14 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k) |86.344|97.97 |256 |88.59 |20.09 |37.55 |816.14 |256 |
| [convnextv2_huge.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in1k) |86.256|97.75 |224 |660.29 |115.0 |79.07 |154.72 |256 |
| [convnext_small.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_small.in12k_ft_in1k_384) |86.182|97.92 |384 |50.22 |25.58 |63.37 |516.19 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in1k) |86.154|97.68 |256 |88.59 |20.09 |37.55 |819.86 |256 |
| [convnext_base.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k) |85.822|97.866|224 |88.59 |15.38 |28.75 |1037.66 |256 |
| [convnext_small.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k_384) |85.778|97.886|384 |50.22 |25.58 |63.37 |518.95 |256 |
| [convnextv2_large.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in1k) |85.742|97.584|224 |197.96 |34.4 |43.13 |375.23 |256 |
| [convnext_small.in12k_ft_in1k](https://huggingface.co/timm/convnext_small.in12k_ft_in1k) |85.174|97.506|224 |50.22 |8.71 |21.56 |1474.31 |256 |
| [convnext_tiny.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k_384) |85.118|97.608|384 |28.59 |13.14 |39.48 |856.76 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384) |85.112|97.63 |384 |28.64 |13.14 |39.48 |491.32 |256 |
| [convnextv2_base.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in1k) |84.874|97.09 |224 |88.72 |15.38 |28.75 |625.33 |256 |
| [convnext_small.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k) |84.562|97.394|224 |50.22 |8.71 |21.56 |1478.29 |256 |
| [convnext_large.fb_in1k](https://huggingface.co/timm/convnext_large.fb_in1k) |84.282|96.892|224 |197.77 |34.4 |43.13 |584.28 |256 |
| [convnext_tiny.in12k_ft_in1k](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k) |84.186|97.124|224 |28.59 |4.47 |13.44 |2433.7 |256 |
| [convnext_tiny.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k_384) |84.084|97.14 |384 |28.59 |13.14 |39.48 |862.95 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k) |83.894|96.964|224 |28.64 |4.47 |13.44 |1452.72 |256 |
| [convnext_base.fb_in1k](https://huggingface.co/timm/convnext_base.fb_in1k) |83.82 |96.746|224 |88.59 |15.38 |28.75 |1054.0 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k_384) |83.37 |96.742|384 |15.62 |7.22 |24.61 |801.72 |256 |
| [convnext_small.fb_in1k](https://huggingface.co/timm/convnext_small.fb_in1k) |83.142|96.434|224 |50.22 |8.71 |21.56 |1464.0 |256 |
| [convnextv2_tiny.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in1k) |82.92 |96.284|224 |28.64 |4.47 |13.44 |1425.62 |256 |
| [convnext_tiny.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k) |82.898|96.616|224 |28.59 |4.47 |13.44 |2480.88 |256 |
| [convnext_nano.in12k_ft_in1k](https://huggingface.co/timm/convnext_nano.in12k_ft_in1k) |82.282|96.344|224 |15.59 |2.46 |8.37 |3926.52 |256 |
| [convnext_tiny_hnf.a2h_in1k](https://huggingface.co/timm/convnext_tiny_hnf.a2h_in1k) |82.216|95.852|224 |28.59 |4.47 |13.44 |2529.75 |256 |
| [convnext_tiny.fb_in1k](https://huggingface.co/timm/convnext_tiny.fb_in1k) |82.066|95.854|224 |28.59 |4.47 |13.44 |2346.26 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k) |82.03 |96.166|224 |15.62 |2.46 |8.37 |2300.18 |256 |
| [convnextv2_nano.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in1k) |81.83 |95.738|224 |15.62 |2.46 |8.37 |2321.48 |256 |
| [convnext_nano_ols.d1h_in1k](https://huggingface.co/timm/convnext_nano_ols.d1h_in1k) |80.866|95.246|224 |15.65 |2.65 |9.38 |3523.85 |256 |
| [convnext_nano.d1h_in1k](https://huggingface.co/timm/convnext_nano.d1h_in1k) |80.768|95.334|224 |15.59 |2.46 |8.37 |3915.58 |256 |
| [convnextv2_pico.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_pico.fcmae_ft_in1k) |80.304|95.072|224 |9.07 |1.37 |6.1 |3274.57 |256 |
| [convnext_pico.d1_in1k](https://huggingface.co/timm/convnext_pico.d1_in1k) |79.526|94.558|224 |9.05 |1.37 |6.1 |5686.88 |256 |
| [convnext_pico_ols.d1_in1k](https://huggingface.co/timm/convnext_pico_ols.d1_in1k) |79.522|94.692|224 |9.06 |1.43 |6.5 |5422.46 |256 |
| [convnextv2_femto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_femto.fcmae_ft_in1k) |78.488|93.98 |224 |5.23 |0.79 |4.57 |4264.2 |256 |
| [convnext_femto_ols.d1_in1k](https://huggingface.co/timm/convnext_femto_ols.d1_in1k) |77.86 |93.83 |224 |5.23 |0.82 |4.87 |6910.6 |256 |
| [convnext_femto.d1_in1k](https://huggingface.co/timm/convnext_femto.d1_in1k) |77.454|93.68 |224 |5.22 |0.79 |4.57 |7189.92 |256 |
| [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) |76.664|93.044|224 |3.71 |0.55 |3.81 |4728.91 |256 |
| [convnext_atto_ols.a2_in1k](https://huggingface.co/timm/convnext_atto_ols.a2_in1k) |75.88 |92.846|224 |3.7 |0.58 |4.11 |7963.16 |256 |
| [convnext_atto.d2_in1k](https://huggingface.co/timm/convnext_atto.d2_in1k) |75.664|92.9 |224 |3.7 |0.55 |3.81 |8439.22 |256 |
## Citation
```bibtex
@article{Woo2023ConvNeXtV2,
title={ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders},
author={Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon and Saining Xie},
year={2023},
journal={arXiv preprint arXiv:2301.00808},
}
```
```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}}
}
```
|
proximasanfinetuning/fantassified_icons_v2 | proximasanfinetuning | 2023-06-08T19:26:22Z | 404 | 49 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"finetune",
"icons",
"art",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-05-10T22:35:57Z | ---
license: other
tags:
- text-to-image
- stable-diffusion
- finetune
- icons
- art
language:
- en
---
## new and shiny ｡･:*:･ﾟ’☆
[<img src="https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/resolve/main/animatedicons.gif">](https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/blob/main/animatedicons.gif)
# about
- updated version of [v1](https://huggingface.co/proxima/fantassified_icons), made with a dataset consisting of mostly the old version's dataset, but it's a lot better because I learned a few things since the dreambooth days
- generates icons inspired by fantasy games with mostly plain backgrounds
- no trigger words
- either my local hires fix isn't working well or potions look weird when hires is turned on, will have to test that another time (probably needs low denoising strength)
- i don't recommend this for people and faces as these were of 0% concern while training, the focus was on items, but you do you
- examples are [made with this VAE](https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.ckpt) at 20 steps, 512x512, CFG 7, Euler a (try DPM ++2M for a look that is a bit sharper)
---
## examples
[<img src="https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/resolve/main/examples/1-3.png">](https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/blob/main/examples/1-3.png)
[<img src="https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/resolve/main/examples/4-6.png">](https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/blob/main/examples/4-6.png)
[<img src="https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/resolve/main/examples/7-9.png">](https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/blob/main/examples/7-9.png)
---
if you enjoy this consider buying me a coffee (ノ◕ヮ◕)ノ*:・゚✧
<a href='https://ko-fi.com/S6S6FUYKY' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi3.png?v=3' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
----
## Use with diffusers
How to use it with [diffusers](https://github.com/huggingface/diffusers)
```python
import torch
from diffusers import StableDiffusionPipeline, DDIMScheduler
scheduler = DDIMScheduler.from_pretrained("proximasanfinetuning/fantassified_icons_v2", subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained("proximasanfinetuning/fantassified_icons_v2", scheduler=scheduler).to("cuda")
prompt = "A lemon themed high quality hamburger"
images = pipe(prompt, num_images_per_prompt=6, num_inference_steps=25).images
images[0]
```
---
# license
This model is licensed under a modified CreativeML OpenRAIL-M license.
* Utilizing and hosting the Fantassified Icons 1.0 model and its derivatives on platforms that earn, will earn, or plan to earn revenue or donations requires prior authorization. **To request permission, please email [email protected].**
* You are permitted to host the model card and files on both commercial and non-commercial websites, apps, etc. as long as you properly credit the model by stating its full name and providing a link to the model card (https://huggingface.co/proximasanfinetuning/fantassified_icons_v2), without performing any actual inference or finetuning.
* The Fantassified Icons 1.0 model and its derivatives can be hosted on non-commercial websites, apps, etc. as long as no revenue or donations are received. Proper credit must be given by stating the full model name and including a link to the model card (https://huggingface.co/proximasanfinetuning/fantassified_icons_v2).
* **The outputs of the model or its derivatives can be used for commercial purposes as long as the usage is limited to teams of 10 or fewer individuals.**
* You can't use the model to deliberately produce nor share illegal or harmful outputs or content
* The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
* You may re-distribute the weights. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the modified CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here: https://huggingface.co/proximasanfinetuning/fantassified_icons_v2/blob/main/license.txt |
lorahub/flan_t5_large-qasc_qa_with_separated_facts_3 | lorahub | 2023-07-24T09:36:58Z | 404 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-07-24T09:36:48Z | ---
library_name: peft
---
|
defog/sqlcoder | defog | 2024-03-01T09:38:12Z | 404 | 303 | transformers | [
"transformers",
"pytorch",
"gpt_bigcode",
"text-generation",
"code",
"en",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-08-11T21:55:26Z | ---
license: other
language:
- en
metrics:
- code_eval
library_name: transformers
pipeline_tag: text-generation
tags:
- code
inference: false
---
# ARCHIVE NOTICE
This repository is now significantly outdated. You should use the repository at [sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2) instead. It is significantly better and consumes fewer GPU resources.
# Defog SQLCoder
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.
[Interactive Demo](https://defog.ai/sqlcoder-demo) | [♾️ Colab](https://colab.research.google.com/drive/1z4rmOEiFkxkMiecAWeTUlPl0OmKgfEu7) | [🐦 Twitter](https://twitter.com/defogdata)
## TL;DR
SQLCoder is a 15B parameter model that slightly outperforms `gpt-3.5-turbo` for natural language to SQL generation tasks on our [sql-eval](https://github.com/defog-ai/sql-eval) framework, and significantly outperforms all popular open-source models. It also significantly outperforms `text-davinci-003`, a model that's more than 10 times its size.
SQLCoder is fine-tuned on a base StarCoder model.
## Results on novel datasets not seen in training
| model | perc_correct |
|-|-|
| gpt-4 | 74.3 |
| defog-sqlcoder | 64.6 |
| gpt-3.5-turbo | 60.6 |
| defog-easysql | 57.1 |
| text-davinci-003 | 54.3 |
| wizardcoder | 52.0 |
| starcoder | 45.1 |
## License
The model weights have a `CC BY-SA 4.0` license, with OpenRAIL-M clauses for responsible use attached. The TL;DR is that you can use and modify the model for any purpose – including commercial use. However, if you modify the weights (for example, by fine-tuning), you must open-source your modified weights under the same `CC BY-SA 4.0` license terms.
## Training
Defog was trained on 10,537 human-curated questions across 2 epochs. These questions were based on 10 different schemas. None of the schemas in the training data were included in our evaluation framework.
Training happened in 2 phases. The first phase was on questions that were classified as "easy" or "medium" difficulty, and the second phase was on questions that were classified as "hard" or "extra hard" difficulty.
The results of training on our easy+medium data were stored in a model called `defog-easy`. We found that the additional training on hard+extra-hard data led to a 7 percentage point increase in performance.
## Results by question category
We classified each generated question into one of 5 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
| query_category | gpt-4 | defog-sqlcoder | gpt-3.5-turbo | defog-easy | text-davinci-003 | wizard-coder | star-coder |
|-|-|-|-|-|-|-|-|
| group_by | 82.9 | 77.1 | 71.4 | 62.9 | 62.9 | 68.6 | 54.3 |
| order_by | 71.4 | 65.7 | 60.0 | 68.6 | 60.0 | 54.3 | 57.1 |
| ratio | 62.9 | 57.1 | 48.6 | 40.0 | 37.1 | 22.9 | 17.1 |
| table_join | 74.3 | 57.1 | 60.0 | 54.3 | 51.4 | 54.3 | 51.4 |
| where | 80.0 | 65.7 | 62.9 | 60.0 | 60.0 | 60.0 | 45.7 |
## Using SQLCoder
You can use SQLCoder via the `transformers` library by downloading our model weights from the HuggingFace repo. We have added sample code for inference [here](./inference.py). You can also use a demo on our website [here](https://defog.ai/sqlcoder-demo), or run SQLCoder in Colab [here](https://colab.research.google.com/drive/13BIKsqHnPOBcQ-ba2p77L5saiepTIwu0#scrollTo=ZpbVgVHMkJvC)
## Hardware Requirements
SQLCoder has been tested on an A100 40GB GPU with `bfloat16` weights. You can also load an 8-bit quantized version of the model on consumer GPUs with 20GB or more of memory – like RTX 4090, RTX 3090, and Apple M2 Pro, M2 Max, or M2 Ultra Chips with 20GB or more of memory.
## Todo
- [x] Open-source the v1 model weights
- [ ] Train the model on more data, with higher data variance
- [ ] Tune the model further with Reward Modelling and RLHF
- [ ] Pretrain a model from scratch that specializes in SQL analysis |
TheBloke/chronos-33b-GGUF | TheBloke | 2023-09-27T12:52:21Z | 404 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"pytorch",
"chatbot",
"storywriting",
"base_model:elinas/chronos-33b",
"license:other",
"text-generation-inference",
"region:us"
]
| null | 2023-09-19T22:33:45Z | ---
license: other
tags:
- llama
- pytorch
- chatbot
- storywriting
model_name: Chronos 33B
base_model: elinas/chronos-33b
inference: false
model_creator: elinas
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Chronos 33B - GGUF
- Model creator: [elinas](https://huggingface.co/elinas)
- Original model: [Chronos 33B](https://huggingface.co/elinas/chronos-33b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Elinas' Chronos 33B](https://huggingface.co/elinas/chronos-33b).
<!-- 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/chronos-33b-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/chronos-33b-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/chronos-33b-GGUF)
* [elinas's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/elinas/chronos-33b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [chronos-33b.Q2_K.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q2_K.gguf) | Q2_K | 2 | 13.50 GB| 16.00 GB | smallest, significant quality loss - not recommended for most purposes |
| [chronos-33b.Q3_K_S.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q3_K_S.gguf) | Q3_K_S | 3 | 14.06 GB| 16.56 GB | very small, high quality loss |
| [chronos-33b.Q3_K_M.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q3_K_M.gguf) | Q3_K_M | 3 | 15.76 GB| 18.26 GB | very small, high quality loss |
| [chronos-33b.Q3_K_L.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q3_K_L.gguf) | Q3_K_L | 3 | 17.28 GB| 19.78 GB | small, substantial quality loss |
| [chronos-33b.Q4_0.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q4_0.gguf) | Q4_0 | 4 | 18.36 GB| 20.86 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [chronos-33b.Q4_K_S.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q4_K_S.gguf) | Q4_K_S | 4 | 18.44 GB| 20.94 GB | small, greater quality loss |
| [chronos-33b.Q4_K_M.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q4_K_M.gguf) | Q4_K_M | 4 | 19.62 GB| 22.12 GB | medium, balanced quality - recommended |
| [chronos-33b.Q5_0.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q5_0.gguf) | Q5_0 | 5 | 22.40 GB| 24.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [chronos-33b.Q5_K_S.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q5_K_S.gguf) | Q5_K_S | 5 | 22.40 GB| 24.90 GB | large, low quality loss - recommended |
| [chronos-33b.Q5_K_M.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q5_K_M.gguf) | Q5_K_M | 5 | 23.05 GB| 25.55 GB | large, very low quality loss - recommended |
| [chronos-33b.Q6_K.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q6_K.gguf) | Q6_K | 6 | 26.69 GB| 29.19 GB | very large, extremely low quality loss |
| [chronos-33b.Q8_0.gguf](https://huggingface.co/TheBloke/chronos-33b-GGUF/blob/main/chronos-33b.Q8_0.gguf) | Q8_0 | 8 | 34.57 GB| 37.07 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/chronos-33b-GGUF and below it, a specific filename to download, such as: chronos-33b.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/chronos-33b-GGUF chronos-33b.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/chronos-33b-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/chronos-33b-GGUF chronos-33b.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 chronos-33b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 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/chronos-33b-GGUF", model_file="chronos-33b.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 Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Elinas' Chronos 33B
# chronos-33b
This is the fp16 PyTorch / HF version of **chronos-33b** - if you need another version, GGML and GPTQ versions are linked below.
This model is primarily focused on chat, roleplay, and storywriting, but can accomplish other tasks such as simple reasoning and coding.
Chronos generates very long outputs with coherent text, largely due to the human inputs it was trained on.
This model uses Alpaca formatting, so for optimal model performance, use:
```
### Instruction:
Your instruction or question here.
### Response:
```
[GGML Version provided by @TheBloke](https://huggingface.co/TheBloke/chronos-33b-GGML)
[4bit GPTQ Version provided by @TheBloke](https://huggingface.co/TheBloke/chronos-33b-GPTQ)
<!--**Support My Development of New Models**
<a href='https://ko-fi.com/Q5Q6MB734' target='_blank'><img height='36' style='border:0px;height:36px;'
src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Support Development' /></a>-->
--
license: other
---
# LLaMA Model Card
## Model details
**Organization developing the model**
The FAIR team of Meta AI.
**Model date**
LLaMA was trained between December. 2022 and Feb. 2023.
**Model version**
This is version 1 of the model.
**Model type**
LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters.
**Paper or resources for more information**
More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/.
**Citations details**
https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/
**License**
Non-commercial bespoke license
**Where to send questions or comments about the model**
Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue.
## Intended use
**Primary intended uses**
The primary use of LLaMA is research on large language models, including:
exploring potential applications such as question answering, natural language understanding or reading comprehension,
understanding capabilities and limitations of current language models, and developing techniques to improve those,
evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations.
**Primary intended users**
The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.
**Out-of-scope use cases**
LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.
## Factors
**Relevant factors**
One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model.
**Evaluation factors**
As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model.
## Metrics
**Model performance measures**
We use the following measure to evaluate the model:
- Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs,
- Exact match for question answering,
- The toxicity score from Perspective API on RealToxicityPrompts.
**Decision thresholds**
Not applicable.
**Approaches to uncertainty and variability**
Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training.
## Evaluation datasets
The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs.
## Training dataset
The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing.
## Quantitative analysis
Hyperparameters for the model architecture
<table>
<thead>
<tr>
<th >LLaMA</th> <th colspan=6>Model hyper parameters </th>
</tr>
<tr>
<th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
<tr>
<th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
</tbody>
</table>
*Table 1 - Summary of LLama Model Hyperparameters*
We present our results on eight standard common sense reasoning benchmarks in the table below.
<table>
<thead>
<tr>
<th>LLaMA</th> <th colspan=9>Reasoning tasks </th>
</tr>
<tr>
<th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93
</th>
<tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94
</th>
<tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92
</th>
<tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr>
</tbody>
</table>
*Table 2 - Summary of LLama Model Performance on Reasoning tasks*
We present our results on bias in the table below. Note that lower value is better indicating lower bias.
| No | Category | FAIR LLM |
| --- | -------------------- | -------- |
| 1 | Gender | 70.6 |
| 2 | Religion | 79 |
| 3 | Race/Color | 57 |
| 4 | Sexual orientation | 81 |
| 5 | Age | 70.1 |
| 6 | Nationality | 64.2 |
| 7 | Disability | 66.7 |
| 8 | Physical appearance | 77.8 |
| 9 | Socioeconomic status | 71.5 |
| | LLaMA Average | 66.6 |
*Table 3 - Summary bias of our model output*
## Ethical considerations
**Data**
The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data.
**Human life**
The model is not intended to inform decisions about matters central to human life, and should not be used in such a way.
**Mitigations**
We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier.
**Risks and harms**
Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard.
**Use cases**
LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
<!-- original-model-card end -->
|
stablediffusionapi/beautiful-realistic-asian | stablediffusionapi | 2023-10-21T12:51:02Z | 404 | 6 | diffusers | [
"diffusers",
"stablediffusionapi.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-10-21T12:48:46Z | ---
license: creativeml-openrail-m
tags:
- stablediffusionapi.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# Beautiful Realistic Asians v7 API Inference
## Get API Key
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
Replace Key in below code, change **model_id** to "beautiful-realistic-asian"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
Try model for free: [Generate Images](https://stablediffusionapi.com/models/beautiful-realistic-asian)
Model link: [View model](https://stablediffusionapi.com/models/beautiful-realistic-asian)
Credits: [View credits](https://civitai.com/?query=Beautiful%20Realistic%20Asians%20v7)
View all models: [View Models](https://stablediffusionapi.com/models)
import requests
import json
url = "https://stablediffusionapi.com/api/v4/dreambooth"
payload = json.dumps({
"key": "your_api_key",
"model_id": "beautiful-realistic-asian",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN** |
jjzha/escoxlmr_skill_extraction | jjzha | 2023-11-19T11:13:43Z | 404 | 3 | transformers | [
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"token-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-11-11T08:19:48Z | ---
license: apache-2.0
---
This is a demo using the models from:
```
@inproceedings{zhang-etal-2023-escoxlm,
title = "{ESCOXLM}-{R}: Multilingual Taxonomy-driven Pre-training for the Job Market Domain",
author = "Zhang, Mike and
van der Goot, Rob and
Plank, Barbara",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.662",
doi = "10.18653/v1/2023.acl-long.662",
pages = "11871--11890",
abstract = "The increasing number of benchmarks for Natural Language Processing (NLP) tasks in the computational job market domain highlights the demand for methods that can handle job-related tasks such as skill extraction, skill classification, job title classification, and de-identification. While some approaches have been developed that are specific to the job market domain, there is a lack of generalized, multilingual models and benchmarks for these tasks. In this study, we introduce a language model called ESCOXLM-R, based on XLM-R-large, which uses domain-adaptive pre-training on the European Skills, Competences, Qualifications and Occupations (ESCO) taxonomy, covering 27 languages. The pre-training objectives for ESCOXLM-R include dynamic masked language modeling and a novel additional objective for inducing multilingual taxonomical ESCO relations. We comprehensively evaluate the performance of ESCOXLM-R on 6 sequence labeling and 3 classification tasks in 4 languages and find that it achieves state-of-the-art results on 6 out of 9 datasets. Our analysis reveals that ESCOXLM-R performs better on short spans and outperforms XLM-R-large on entity-level and surface-level span-F1, likely due to ESCO containing short skill and occupation titles, and encoding information on the entity-level.",
}
```
Note that there is another endpoint, namely `jjzha/escoxlmr_skill_extraction`.
Knowledge can be seen as hard skills and Skills are both soft and applied skills. |
digiplay/ZHMix-Dramatic-v2.0 | digiplay | 2023-12-03T08:15:40Z | 404 | 2 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-12-03T05:24:23Z | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/148158?modelVersionId=207031
Sample images generated by Hugginface's API:
|
sequelbox/Llama2-70B-SpellBlade | sequelbox | 2024-05-15T16:00:14Z | 404 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-12-24T13:14:08Z | ---
license: apache-2.0
---
Spell Blade is a chat and general capability finetuned upgrade to Llama 2, focused on improving conversational quality as well as supplementing technical capability.
Performs solidly as-is, user satisfaction will be optimized with further finetuning.
Most training data utilizes the [INST][/INST] chat format.
This is a 'legacy model' offered primarily for reference purposes. I recommend Llama 3 over this model for general use. |
hvein/5E1xALrsRGeiHyiLaBK6zWUM96NfvLKyUY27sQNP8jWZfWSZ_vgg | hvein | 2024-03-25T17:40:13Z | 404 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-02-21T22:37:39Z | Entry not found |
EpicJhon/5FEntqRsmPvNztngnin8pmSVzxBij4xx1D3xZ7r23WNCYjTz_vgg | EpicJhon | 2024-03-27T22:47:02Z | 404 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-02-25T12:31:19Z | Entry not found |
mradermacher/Pandora_7B-GGUF | mradermacher | 2024-05-06T06:07:44Z | 404 | 1 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"not-for-all-audiences",
"en",
"dataset:ResplendentAI/Alpaca_NSFW_Shuffled",
"dataset:ResplendentAI/Synthetic_Soul_1k",
"dataset:ResplendentAI/Sissification_Hypno_1k",
"dataset:ResplendentAI/Luna_NSFW_Text",
"dataset:ResplendentAI/NSFW_RP_Format_DPO",
"base_model:ResplendentAI/Pandora_7B",
"license:cc-by-sa-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-19T19:59:13Z | ---
base_model: ResplendentAI/Pandora_7B
datasets:
- ResplendentAI/Alpaca_NSFW_Shuffled
- ResplendentAI/Synthetic_Soul_1k
- ResplendentAI/Sissification_Hypno_1k
- ResplendentAI/Luna_NSFW_Text
- ResplendentAI/NSFW_RP_Format_DPO
language:
- en
library_name: transformers
license: cc-by-sa-4.0
quantized_by: mradermacher
tags:
- mergekit
- merge
- not-for-all-audiences
---
## About
static quants of https://huggingface.co/ResplendentAI/Pandora_7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Pandora_7B-GGUF/resolve/main/Pandora_7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/Skadi-Mixtral-v1-i1-GGUF | mradermacher | 2024-05-06T04:38:51Z | 404 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"en",
"base_model:Sao10K/Skadi-Mixtral-v1",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-19T18:01:34Z | ---
base_model: Sao10K/Skadi-Mixtral-v1
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
tags:
- merge
---
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/Sao10K/Skadi-Mixtral-v1
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Skadi-Mixtral-v1-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/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | 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.
<!-- end -->
|
astronomer/Llama-3-8B-GPTQ-4-Bit | astronomer | 2024-04-22T03:55:35Z | 404 | 6 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-3",
"facebook",
"meta",
"astronomer",
"gptq",
"pretrained",
"quantized",
"finetuned",
"autotrain_compatible",
"endpoints_compatible",
"dataset:wikitext",
"arxiv:2210.17323",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:other",
"text-generation-inference",
"4-bit",
"region:us"
]
| text-generation | 2024-04-21T22:18:36Z | ---
base_model: meta-llama/Meta-Llama-3-8B
inference: false
model_creator: astronomer-io
model_name: Meta-Llama-3-8B
model_type: llama
pipeline_tag: text-generation
quantized_by: davidxmle
license: other
license_name: llama-3
license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE
tags:
- llama
- llama-3
- facebook
- meta
- astronomer
- gptq
- pretrained
- quantized
- finetuned
- autotrain_compatible
- endpoints_compatible
datasets:
- wikitext
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://www.astronomer.io/logo/astronomer-logo-RGB-standard-1200px.png" alt="Astronomer" style="width: 60%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="margin-top: 1.0em; margin-bottom: 1.0em;"></div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">This model is generously created and made open source by <a href="https://astronomer.io">Astronomer</a>.</p></div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">Astronomer is the de facto company for <a href="https://airflow.apache.org/">Apache Airflow</a>, the most trusted open-source framework for data orchestration and MLOps.</p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Llama-3-8B-GPTQ-8-Bit
- Original Model creator: [Meta Llama from Meta](https://huggingface.co/meta-llama)
- Original model: [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
- Built with Meta Llama 3
- Quantized by [David Xue](https://www.linkedin.com/in/david-xue-uva/) from [Astronomer](https://astronomer.io)
## MUST READ: Very Important!! Note About Untrained Special Tokens in Llama 3 Base (Non-instruct) Models & Fine-tuning Llama 3 Base
- **If you intend to fine-tune this model with any added tokens, or fine-tune for instruction following, please use the [untrained-special-tokens-fixed](https://huggingface.co/astronomer-io/Llama-3-8B-GPTQ-4-Bit/tree/untrained-special-tokens-fixed) branch/revision.**
- Special tokens such as the ones used for instruct are undertrained in Llama 3 base models.
- Credits: discovered by Daniel Han https://twitter.com/danielhanchen/status/1781395882925343058
- 
## Important Note About Serving with vLLM & oobabooga/text-generation-webui
- For loading this model onto vLLM, make sure all requests have `"stop_token_ids":[128001, 128009]` to temporarily address the non-stop generation issue.
- vLLM does not yet respect `generation_config.json`.
- vLLM team is working on a a fix for this https://github.com/vllm-project/vllm/issues/4180
- For oobabooga/text-generation-webui
- Load the model via AutoGPTQ, with `no_inject_fused_attention` enabled. This is a bug with AutoGPTQ library.
- Under `Parameters` -> `Generation` -> `Skip special tokens`: turn this off (deselect)
- Under `Parameters` -> `Generation` -> `Custom stopping strings`: add `"<|end_of_text|>","<|eot_id|>"` to the field
<!-- description start -->
## Description
This repo contains 4 Bit quantized GPTQ model files for [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
This model can be loaded with less than 6 GB of VRAM (huge reduction from the original 16.07GB model) and can be served lightning fast with the cheapest Nvidia GPUs possible (Nvidia T4, Nvidia K80, RTX 4070, etc).
The 4 bit GPTQ quant has small quality degradation from the original `bfloat16` model but can be served on much smaller GPUs with maximum improvement in latency and throughput.
The `untrained-special-tokens-fixed` branch is the same model as the main branch but has special tokens and tokens untrained (by finding the tokens where max embedding value of each token in input_embeddings and output_embeddings is 0) and setting them to the average of all trained tokens for each feature. Using this branch is recommended if you plan to do any fine-tuning with your own tokens added or with instruction following.
<!-- description end -->
## GPTQ Quantization Method
- This model is quantized by utilizing the AutoGPTQ library, following best practices noted by [GPTQ paper](https://arxiv.org/abs/2210.17323)
- Quantization is calibrated and aligned with random samples from the specified dataset (wikitext for now) for minimum accuracy loss.
| Branch | Bits | Group Size | Act Order | Damp % | GPTQ Dataset | Sequence Length | VRAM Size | ExLlama | Special Tokens Fixed | Description |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ------- | ---- |
| [main](https://huggingface.co/astronomer-io/Llama-3-8B-GPTQ-4-Bit/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 5.74 GB | Yes | No | 4-bit, with Act Order and group size 128g. Smallest model possible with small accuracy loss |
| [untrained-special-tokens-fixed](https://huggingface.co/astronomer-io/Llama-3-8B-GPTQ-4-Bit/tree/untrained-special-tokens-fixed) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 5.74 GB | Yes | Yes | Same as the main branch. The special tokens that were untrained causing exploding gradients/NaN gradients have had their embedding values set to the average of trained tokens for each feature |
| More variants to come | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD | May upload additional variants of GPTQ 4 bit models in the future using different parameters such as 128g group size and etc. |
## Serving this GPTQ model using vLLM
Tested serving this model via vLLM using an Nvidia T4 (16GB VRAM).
Tested with the below command
```bash
python -m vllm.entrypoints.openai.api_server --model astronomer-io/Llama-3-8B-GPTQ-4-Bit --max-model-len 8192 --dtype float16
```
For the non-stop token generation bug, make sure to send requests with `stop_token_ids":[128001, 128009]` to vLLM endpoint
### Contributors
- Quantized by [David Xue, Machine Learning Engineer from Astronomer](https://www.linkedin.com/in/david-xue-uva/)
|
mmnga/pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf | mmnga | 2024-04-24T14:39:32Z | 404 | 0 | null | [
"gguf",
"qwen",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"license:other",
"region:us"
]
| null | 2024-04-23T14:53:08Z | ---
license: other
license_name: tongyi-qianwen
license_link: >-
https://huggingface.co/pfnet/nekomata-14b-pfn-qfin-inst-merge/blob/main/LICENSE
language:
- en
- ja
tags:
- qwen
datasets:
- TFMC/imatrix-dataset-for-japanese-llm
---
# pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf
[pfnetさんが公開しているnekomata-14b-pfn-qfin-inst-merge](https://huggingface.co/pfnet/nekomata-14b-pfn-qfin-inst-merge)のggufフォーマット変換版です。
imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。
## ライセンス
tongyi-qianwenライセンスになります。
[ご使用前にライセンスをご確認ください。](https://huggingface.co/pfnet/nekomata-14b-pfn-qfin-inst-merge/blob/main/LICENSE)
## 他のモデル
[mmnga/pfnet-nekomata-14b-pfn-qfin-gguf](https://huggingface.co/mmnga/pfnet-nekomata-14b-pfn-qfin-gguf)
[mmnga/pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf](https://huggingface.co/mmnga/pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf)
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'pfnet-nekomata-14b-pfn-qfin-inst-merge-q4_0.gguf' -n 128 --temp 0.5 -p '### 指示:次の日本語を英語に翻訳してください。\n\n### 入力: 大規模言語モデル（だいきぼげんごモデル、英: large language model、LLM）は、多数のパラメータ（数千万から数十億）を持つ人工ニューラルネットワークで構成されるコンピュータ言語モデルで、膨大なラベルなしテキストを使用して自己教師あり学習または半教師あり学習によって訓練が行われる。 \n\n### 応答:'
``` |
qwp4w3hyb/Qwen1.5-MoE-A2.7B-Chat-iMat-GGUF | qwp4w3hyb | 2024-04-24T03:07:41Z | 404 | 1 | null | [
"gguf",
"region:us"
]
| null | 2024-04-24T01:48:10Z | Entry not found |
Fulcrum-AI/Ryze | Fulcrum-AI | 2024-04-29T06:52:05Z | 404 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:2403.19522",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-29T05:36:56Z | ---
license: apache-2.0
---
# Fulcrum-Mistral New
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /content/drive/MyDrive/Fulcrum-Mistral as a base.
### Models Merged
The following models were included in the merge:
1) cognitivecomputations/dolphin-2.8-mistral-7b-v02
2) NousResearch/Hermes-2-Pro-Mistral-7B
3) HuggingFaceH4/zephyr-7b-beta
4) teknium/OpenHermes-2.5-Mistral-7B
5) mlabonne/Zebrafish-7B
6) Open-Orca/Mistral-7B-OpenOrca
7) mistralai/Mistral-7B-Instruct-v0.2 |
jondurbin/airoboros-110b-3.3 | jondurbin | 2024-05-15T08:53:18Z | 404 | 2 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"dataset:jondurbin/airoboros-3.2",
"dataset:bluemoon-fandom-1-1-rp-cleaned",
"dataset:boolq",
"dataset:jondurbin/gutenberg-dpo-v0.1",
"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",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-12T08:24:45Z | ---
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
- jondurbin/gutenberg-dpo-v0.1
- 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
---
### Overview
Another experimental model, tuned primarily from synthetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
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-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. |
apple/MobileCLIP-S1-OpenCLIP | apple | 2024-06-12T11:48:44Z | 404 | 4 | open_clip | [
"open_clip",
"safetensors",
"clip",
"zero-shot-image-classification",
"arxiv:2311.17049",
"arxiv:2103.00020",
"arxiv:2303.15343",
"arxiv:2309.17425",
"license:other",
"region:us"
]
| zero-shot-image-classification | 2024-06-07T14:44:41Z | ---
tags:
- clip
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: other
license_name: apple-ascl
license_link: LICENSE
---
# MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
MobileCLIP was introduced in [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
](https://arxiv.org/pdf/2311.17049.pdf) (CVPR 2024), by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
This repository contains the **MobileCLIP-S1** checkpoint for OpenCLIP.
### Highlights
* Our smallest variant `MobileCLIP-S0` obtains similar zero-shot performance as [OpenAI](https://arxiv.org/abs/2103.00020)'s ViT-B/16 model while being 4.8x faster and 2.8x smaller.
* `MobileCLIP-S2` obtains better avg zero-shot performance than [SigLIP](https://arxiv.org/abs/2303.15343)'s ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples.
* `MobileCLIP-B`(LT) attains zero-shot ImageNet performance of **77.2%** which is significantly better than recent works like [DFN](https://arxiv.org/abs/2309.17425) and [SigLIP](https://arxiv.org/abs/2303.15343) with similar architectures or even [OpenAI's ViT-L/14@336](https://arxiv.org/abs/2103.00020).
## Checkpoints
| Model | # Seen <BR>Samples (B) | # Params (M) <BR> (img + txt) | Latency (ms) <BR> (img + txt) | IN-1k Zero-Shot <BR> Top-1 Acc. (%) | Avg. Perf. (%) <BR> on 38 datasets |
|:----------------------------------------------------------|:----------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------------:|:----------------------------------:|
| [MobileCLIP-S0](https://hf.co/pcuenq/MobileCLIP-S0) | 13 | 11.4 + 42.4 | 1.5 + 1.6 | 67.8 | 58.1 |
| [MobileCLIP-S1](https://hf.co/pcuenq/MobileCLIP-S1) | 13 | 21.5 + 63.4 | 2.5 + 3.3 | 72.6 | 61.3 |
| [MobileCLIP-S2](https://hf.co/pcuenq/MobileCLIP-S2) | 13 | 35.7 + 63.4 | 3.6 + 3.3 | 74.4 | 63.7 |
| [MobileCLIP-B](https://hf.co/pcuenq/MobileCLIP-B) | 13 | 86.3 + 63.4 | 10.4 + 3.3 | 76.8 | 65.2 |
| [MobileCLIP-B (LT)](https://hf.co/pcuenq/MobileCLIP-B-LT) | 36 | 86.3 + 63.4 | 10.4 + 3.3 | 77.2 | 65.8 | |
TatonkaHF/bge-m3_en_ru | TatonkaHF | 2024-06-24T11:53:40Z | 404 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"ru",
"en",
"arxiv:2402.03216",
"autotrain_compatible",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
]
| sentence-similarity | 2024-06-14T21:36:07Z | ---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
language:
- ru
- en
---
# bge-m3 model for english and russian
This is a tokenizer shrinked version of [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3).
The current model has only English and Russian tokens left in the vocabulary.
Thus, the vocabulary is 21% of the original, and number of parameters in the whole model is 63.3% of the original, without any loss in the quality of English and Russian embeddings.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('TatonkaHF/bge-m3_en_ru')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('TatonkaHF/bge-m3_en_ru')
model = AutoModel.from_pretrained('TatonkaHF/bge-m3_en_ru')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Specs
Other bge-m3 models are also shrinked.
| Model name |
|---------------------------|
| [bge-m3-retromae_en_ru](https://huggingface.co/TatonkaHF/bge-m3-retromae_en_ru) |
| [bge-m3-unsupervised_en_ru](https://huggingface.co/TatonkaHF/bge-m3-unsupervised_en_ru) |
| [bge-m3_en_ru](https://huggingface.co/TatonkaHF/bge-m3_en_ru) |
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Reference:
Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, Zheng Liu. [BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://arxiv.org/abs/2402.03216).
Inspired by [LaBSE-en-ru](https://huggingface.co/cointegrated/LaBSE-en-ru) and [https://discuss.huggingface.co/t/tokenizer-shrinking-recipes/8564/1](https://discuss.huggingface.co/t/tokenizer-shrinking-recipes/8564/1).
License: [mit](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md)
<!--- Describe where people can find more information --> |
mradermacher/Eli-Aya-Hindi-v0.1-GGUF | mradermacher | 2024-06-15T11:24:53Z | 404 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Neohumans-ai/Eli-Aya-Hindi-v0.1",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-15T09:13:03Z | ---
base_model: Neohumans-ai/Eli-Aya-Hindi-v0.1
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Neohumans-ai/Eli-Aya-Hindi-v0.1
<!-- 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/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q2_K.gguf) | Q2_K | 13.9 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.IQ3_XS.gguf) | IQ3_XS | 15.2 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.IQ3_S.gguf) | IQ3_S | 16.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q3_K_S.gguf) | Q3_K_S | 16.0 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.IQ3_M.gguf) | IQ3_M | 16.8 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q3_K_M.gguf) | Q3_K_M | 17.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q3_K_L.gguf) | Q3_K_L | 19.2 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.IQ4_XS.gguf) | IQ4_XS | 19.4 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q4_K_S.gguf) | Q4_K_S | 20.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q4_K_M.gguf) | Q4_K_M | 21.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q5_K_S.gguf) | Q5_K_S | 24.4 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q5_K_M.gguf) | Q5_K_M | 25.1 | |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q6_K.gguf) | Q6_K | 28.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Eli-Aya-Hindi-v0.1-GGUF/resolve/main/Eli-Aya-Hindi-v0.1.Q8_0.gguf) | Q8_0 | 37.3 | 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 -->
|
Ramikan-BR/TiamaPY-v39 | Ramikan-BR | 2024-06-29T11:55:32Z | 404 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gguf",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/tinyllama-chat-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-06-29T10:47:12Z | ---
base_model: unsloth/tinyllama-chat-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
---
# Uploaded model
- **Developed by:** Ramikan-BR
- **License:** apache-2.0
- **Finetuned from model :** unsloth/tinyllama-chat-bnb-4bit
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)
|
ClaudioItaly/TopMaya-Q4_K_M-GGUF | ClaudioItaly | 2024-06-30T23:12:29Z | 404 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"base_model:ClaudioItaly/TopMaya",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-30T23:12:11Z | ---
base_model: ClaudioItaly/TopMaya
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
---
# ClaudioItaly/TopMaya-Q4_K_M-GGUF
This model was converted to GGUF format from [`ClaudioItaly/TopMaya`](https://huggingface.co/ClaudioItaly/TopMaya) 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/ClaudioItaly/TopMaya) 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 ClaudioItaly/TopMaya-Q4_K_M-GGUF --hf-file topmaya-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo ClaudioItaly/TopMaya-Q4_K_M-GGUF --hf-file topmaya-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo ClaudioItaly/TopMaya-Q4_K_M-GGUF --hf-file topmaya-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo ClaudioItaly/TopMaya-Q4_K_M-GGUF --hf-file topmaya-q4_k_m.gguf -c 2048
```
|
tobchef/Qwen2-7B-Instruct-Q4_K_M-GGUF | tobchef | 2024-07-01T09:19:35Z | 404 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"region:us"
]
| text-generation | 2024-07-01T09:19:13Z | ---
base_model: Qwen/Qwen2-7B-Instruct
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
# tobchef/Qwen2-7B-Instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-7B-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/Qwen/Qwen2-7B-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 tobchef/Qwen2-7B-Instruct-Q4_K_M-GGUF --hf-file qwen2-7b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo tobchef/Qwen2-7B-Instruct-Q4_K_M-GGUF --hf-file qwen2-7b-instruct-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo tobchef/Qwen2-7B-Instruct-Q4_K_M-GGUF --hf-file qwen2-7b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo tobchef/Qwen2-7B-Instruct-Q4_K_M-GGUF --hf-file qwen2-7b-instruct-q4_k_m.gguf -c 2048
```
|
MCG-NJU/videomae-base-short | MCG-NJU | 2024-03-29T08:02:07Z | 403 | 3 | transformers | [
"transformers",
"pytorch",
"safetensors",
"videomae",
"pretraining",
"vision",
"video-classification",
"arxiv:2203.12602",
"arxiv:2111.06377",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| video-classification | 2022-07-07T13:25:55Z | ---
license: "cc-by-nc-4.0"
tags:
- vision
- video-classification
---
# VideoMAE (base-sized model, pre-trained only)
VideoMAE model pre-trained on Kinetics-400 for 800 epochs in a self-supervised way. It was introduced in the paper [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Tong et al. and first released in [this repository](https://github.com/MCG-NJU/VideoMAE).
Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
VideoMAE is an extension of [Masked Autoencoders (MAE)](https://arxiv.org/abs/2111.06377) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches.
Videos are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds fixed sinus/cosinus position embeddings before feeding the sequence to the layers of the Transformer encoder.
By pre-training the model, it learns an inner representation of videos that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled videos for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire video.
## Intended uses & limitations
You can use the raw model for predicting pixel values for masked patches of a video, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=videomae) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to predict pixel values for randomly masked patches:
```python
from transformers import VideoMAEImageProcessor, VideoMAEForPreTraining
import numpy as np
import torch
num_frames = 16
video = list(np.random.randn(16, 3, 224, 224))
processor = VideoMAEImageProcessor.from_pretrained("MCG-NJU/videomae-base-short")
model = VideoMAEForPreTraining.from_pretrained("MCG-NJU/videomae-base-short")
pixel_values = processor(video, return_tensors="pt").pixel_values
num_patches_per_frame = (model.config.image_size // model.config.patch_size) ** 2
seq_length = (num_frames // model.config.tubelet_size) * num_patches_per_frame
bool_masked_pos = torch.randint(0, 2, (1, seq_length)).bool()
outputs = model(pixel_values, bool_masked_pos=bool_masked_pos)
loss = outputs.loss
```
For more code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/videomae.html#).
## Training data
(to do, feel free to open a PR)
## Training procedure
### Preprocessing
(to do, feel free to open a PR)
### Pretraining
(to do, feel free to open a PR)
## Evaluation results
(to do, feel free to open a PR)
### BibTeX entry and citation info
```bibtex
misc{https://doi.org/10.48550/arxiv.2203.12602,
doi = {10.48550/ARXIV.2203.12602},
url = {https://arxiv.org/abs/2203.12602},
author = {Tong, Zhan and Song, Yibing and Wang, Jue and Wang, Limin},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
``` |
tum-nlp/mGPT_easy | tum-nlp | 2024-04-16T08:10:32Z | 403 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"de",
"license:openrail++",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2022-12-05T11:33:28Z | ---
license: openrail++
language:
- de
pipeline_tag: text-generation
---
# GPT2 model for German Leichte Sprache (Easy language)
A German Leichte Sprache (Easy language) model based on [mGPT](https://huggingface.co/sberbank-ai/mGPT).
See our code here: [https://github.com/MiriUll/Language-Models-German-Simplification](https://github.com/MiriUll/Language-Models-German-Simplification)
See our paper here: [Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training](https://aclanthology.org/2023.findings-acl.74/)
## Dataset
This model was fine-tuned on a collection of monolingual Leichte Sprache data. This corpus can be recreated [here](https://github.com/brjezierski/scrapers).
## Citation
If you use this model, please cite our paper:
@inproceedings{anschutz-etal-2023-language,
  title = "Language Models for {G}erman Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training",
  author = {Ansch{\"u}tz, Miriam and Oehms, Joshua and Wimmer, Thomas and Jezierski, Bart{\l}omiej and Groh, Georg},
  booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
  month = jul,
  year = "2023",
  address = "Toronto, Canada",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2023.findings-acl.74",
  pages = "1147--1158",
} |
laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-rewind | laion | 2023-04-18T17:44:40Z | 403 | 2 | open_clip | [
"open_clip",
"zero-shot-image-classification",
"clip",
"arxiv:2210.08402",
"arxiv:1910.04867",
"license:mit",
"region:us"
]
| zero-shot-image-classification | 2023-02-26T20:31:10Z | ---
tags:
- zero-shot-image-classification
- clip
library_tag: open_clip
license: mit
library_name: open_clip
pipeline_tag: zero-shot-image-classification
---
# Model card for CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-rewind
# Table of Contents
1. [Model Details](#model-details)
2. [Uses](#uses)
3. [Training Details](#training-details)
4. [Evaluation](#evaluation)
5. [Acknowledgements](#acknowledgements)
6. [Citation](#citation)
# Model Details
## Model Description
A series of CLIP ConvNeXt-XXLarge (a custom `timm` ConvNeXt size) models trained on LAION-2B (english), a subset of [LAION-5B](https://arxiv.org/abs/2210.08402), using [OpenCLIP](https://github.com/mlfoundations/open_clip).
| Model | Dataset | Resolution | AugReg | Top-1 ImageNet Zero-Shot (%) |
| ----- | ------- | ---------- | ------------ | --------- |
| [convnext_xxlarge.laion2b_s34b_b82k-augreg](https://huggingface.co/laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg) | LAION-2B | 256x256 | RRC (0.33, 1.0), RE (0.35), SD (0.1) | 79.1 |
| [convnext_xxlarge.laion2b_s34b_b82k-augreg-rewind](https://huggingface.co/laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-rewind) | LAION-2B | 256x256 | RRC (0.3, 1.0), RE (0.4), SD (0.1) | 79.3 |
| [convnext_xxlarge.laion2b_s34b_b82k-augreg-soup](https://huggingface.co/laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-soup) | LAION-2B | 256x256 | N/A | 79.4 |
RRC = Random Resize Crop (crop pcts), RE = Random Erasing (prob), SD = Stochastic Depth (prob) -- image tower only
The core training run was performed in pieces over a period of ~ 2 months. The global batch size for the core run was 81920. The last ~10% of training was re-done at a 95744 global batch size w/ higher LR and aug than original finish. The two were averaged together in a 'soup'. See more details in [Training Details](#training-details).
Goals:
* Push the size of largest convolutional CLIP image tower into the performance range of ViT-g to ViT-G w/ improved image size scaling for downstream use.
Firsts:
* Largest released ConvNeXt model pretrained (847M params w/ 198 GMAC and 125 MActs @ 256x256 for image)
* A non-ViT image tower CLIP model (with no previous image tower pretrain) achieving > 79% ImageNet top-1 zero-shot
The models utilize:
* the [timm](https://github.com/rwightman/pytorch-image-models) ConvNeXt-XXLarge model (`convnext_xxlarge`) as the image tower
* a standard projection at end of image tower
* a text tower with same size (with 1024, heads 16, depth 24) as ViT-H-14 and ViT-g-14 models
The models are trained at 256x256 image resolution. The size of the combined image + text CLIP model is 1.2B params w/ 222 GMAC and 146 MActs. At 256x256, the ConvNext-XXLarge sits just above a ViT-H-14 CLIP configuration in FLOPS and params while being lower in activation counts. It is well under both g-14 and G-14 while being between them in capabilities.
|model |image_size|embed_dim|gmacs |macts |mparams|image_gmacs|image_macts|image_mparams|text_gmacs|text_macts|text_mparams|
|--------------------------|----------|---------|------|------|-------|-----------|-----------|-------------|----------|----------|------------|
|ViT-H-16 |224 |1024 |150.96|122.01|986.26 |127.4 |100.81 |632.23 |23.57 |21.2 |354.03 |
|ViT-H-14 |224 |1024 |190.97|160.61|986.11 |167.4 |139.41 |632.08 |23.57 |21.2 |354.03 |
|ViT-L-14-336 |336 |768 |197.76|278.19|427.94 |191.1 |270.24 |304.29 |6.66 |7.95 |123.65 |
|convnext_xxlarge |256 |1024 |221.66|145.66|1200.58|198.09 |124.45 |846.54 |23.57 |21.2 |354.03 |
|RN50x64 |448 |1024 |276.8 |249.73|623.26 |265.02 |239.13 |420.38 |11.78 |10.6 |202.88 |
|ViT-g-14 |224 |1024 |290.74|213.84|1366.68|267.18 |192.64 |1012.65 |23.57 |21.2 |354.03 |
|convnext_xxlarge_320 |320 |1024 |333.08|215.66|1200.58|309.52 |194.46 |846.54 |23.57 |21.2 |354.03 |
|ViT-H-14-336 |336 |1024 |414.53|428.74|986.52 |390.97 |407.54 |632.49 |23.57 |21.2 |354.03 |
|ViT-bigG-14 |224 |1280 |532.92|310.71|2539.57|483.96 |275.37 |1844.91 |48.96 |35.34 |694.66 |
Model training done by Ross Wightman across both the [stability.ai](https://stability.ai/) cluster and the [JUWELS Booster](https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html) supercomputer. See acknowledgements below.
# Uses
As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model.
The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and upcoming paper include additional discussion as it relates specifically to the training dataset.
## Direct Use
Zero-shot image classification, image and text retrieval, among others.
## Downstream Use
Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others.
## Out-of-Scope Use
As per the OpenAI models,
**Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful.
Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
Further the above notice, the LAION-5B dataset used in training of these models has additional considerations, see below.
# Training Details
## Training Data
This model was trained with LAION-2B -- A 2 billion sample English subset of LAION-5B (https://laion.ai/blog/laion-5b/).
**IMPORTANT NOTE:** The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress.
## Training Procedure
The main training run was done at global batch size of 81920 for 256 checkpoint intervals of 135.6M samples for a total of ~34B samples seen over training.
Many difficulties w/ both model numerical stability and cluster stability and performance were encountered while training this model. Initial attempts to train with float16 AMP and default adam beta2 resulted in loss spikes and eventually NaN blow ups. `beta2` was reduced to 0.97 which helped, but the loss / zs curves were not tracking as expected. After switching to PyTorch nightlies, it was possible to use bfloat16 + AMP for training (as with rececnt H/14, g/14, and G/14 models), beta2 was returned to 0.98 and metrics improved.
|Checkpoint Interval |Cluster |# GPUs|# Nodes|GPU |local BS|sample/s|sample/s/gpu|precision |adam beta2 |
|--------------------|----------|------|-------|----------|--------|--------|------------|----------|-----------|
|1 - 2 |Stability |1024 |128 |A100 40GB | 80 |37-40k | 36-39 |amp + fp16|0.97 |
|3 - 32 |Stability |512 |64 |A100 80GB | 160 |27-32k | 52-62 |amp + fp16|0.97 |
|33 - 75 |Booster |1024 |256 |A100 40GB | 80 |48k | 47 |amp + fp16|0.97 |
|76 - 165 |Booster |1024 |256 |A100 40GB | 80 |51k | 50 |amp + bf16|0.98 |
|166 - 232 |Stability |320 |40 |A100 80GB | 256 |18-19k | 56-59 |amp + bf16|0.98 |
|233 - 249 |Booster |1024 |256 |A100 40GB | 80 |51k | 50 |amp + bf16|0.98 |
|250 - 256 |Stability |1024 |128 |A100 40GB | 80 |27-31k | 26-30 |amp + bf16|0.98 |
JUWELS Booster has 4x A100 GPU per node w/ 4x HDR-200 IB adapters per node (200Gbit/sec per GPU). Stability setup used was 8x A100 GPU per node w/ 400Gbit/sec EFA networking per node (50 GBit/sec per GPU). Significant variation in training efficiency (throughput per GPU) as observed across the various configurations. The 1024 GPU configurations across both clusters were particularly prone to crashing (or very difficult to get running w/ a 'good' set of GPUs).
A slurm srun command line below for a 128 8-GPU (40GB A100) configuration:
```
srun --cpu_bind=v --accel-bind=gn python -m training.main \
--save-frequency 1 \
--name "xxlarge-2b-81920-bf16" \
--resume "latest" \
--logs "/runs" \
--log-every-n-steps 50 \
--train-data="pipe:aws s3 cp s3://laion5b/laion2B-data/{000000..231349}.tar -" \
--train-num-samples 135646078 \
--dataset-type webdataset \
--warmup 10000 \
--batch-size=80 \
--epochs=256 \
--dataset-resampled \
--aug-cfg use_timm=True scale='(0.33, 1.0)' re_prob=0.35 \
--precision amp_bfloat16 \
--grad-clip-norm 5.0 \
--lr 1e-3 \
--workers=6 \
--beta2 0.98 \
--model "convnext_xxlarge" \
--seed 0 \
--ddp-static-graph \
--local-loss \
--gather-with-grad \
--grad-checkpointing \
--report-to "tensorboard"
```
For the rewind of last 10%, a higher global batch size of 95744 was used w/ a higher LR and slightly increased augmentation strength.
|Checkpoint Interval |Cluster |# GPUs|# Nodes|GPU |local BS|sample/s|sample/s/gpu|precision |adam beta2 |
|--------------------|---------|------|-------|----------|--------|--------|------------|----------|-----------|
|231 - 256 |stability|1088 |136 |A100 40GB | 88 |32-35k | 29-32 |amp + bf16|0.98 |
The slurm srun command line for 136 8-GPU (40GB A100) nodes:
```
srun --cpu_bind=v --accel-bind=gn python -m training.main \
--save-frequency 1 \
--name "xxlarge-2b-81920-r-bf16" \
--resume "latest" \
--logs "/runs" \
--log-every-n-steps 50 \
--train-data="pipe:aws s3 cp s3://laion5b/laion2B-data/{000000..231349}.tar -" \
--train-num-samples 135646078 \
--dataset-type webdataset \
--warmup 10000 \
--batch-size=88 \
--epochs=256 \
--dataset-resampled \
--aug-cfg use_timm=True scale='(0.3, 1.0)' re_prob=0.4 \
--precision amp_bfloat16 \
--grad-clip-norm 5.0 \
--lr 2e-3 \
--workers=6 \
--beta2 0.98 \
--model "convnext_xxlarge" \
--seed 0 \
--ddp-static-graph \
--local-loss \
--gather-with-grad \
--grad-checkpointing \
--report-to "tensorboard"
```
# Evaluation
Evaluation done with code in the [LAION CLIP Benchmark suite](https://github.com/LAION-AI/CLIP_benchmark).
## Testing Data, Factors & Metrics
### Testing Data
The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/abs/1910.04867) w/ additional robustness datasets) for classification and COCO and Flickr for retrieval.
## Results
These models achieve between 79.1 and 79.4 top-1 zero-shot accuracy on ImageNet-1k.
A zoom-in on final 10% w/ rewind:
An initial round of benchmarks have been performed on a wider range of datasets, to be viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
# Acknowledgements
Acknowledging [stability.ai](https://stability.ai/) and the Gauss Centre for Supercomputing e.V. (http://gauss-centre.eu) for funding this part of work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer JUWELS Booster at Jülich Supercomputing Centre (JSC).
# Citation
**BibTeX:**
LAION-5B
```bibtex
@inproceedings{schuhmann2022laionb,
title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
author={Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade W Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa R Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2022},
url={https://openreview.net/forum?id=M3Y74vmsMcY}
}
```
OpenCLIP software
```bibtex
@software{ilharco_gabriel_2021_5143773,
author = {Ilharco, Gabriel and
Wortsman, Mitchell and
Wightman, Ross and
Gordon, Cade and
Carlini, Nicholas and
Taori, Rohan and
Dave, Achal and
Shankar, Vaishaal and
Namkoong, Hongseok and
Miller, John and
Hajishirzi, Hannaneh and
Farhadi, Ali and
Schmidt, Ludwig},
title = {OpenCLIP},
month = jul,
year = 2021,
note = {If you use this software, please cite it as below.},
publisher = {Zenodo},
version = {0.1},
doi = {10.5281/zenodo.5143773},
url = {https://doi.org/10.5281/zenodo.5143773}
}
```
OpenAI CLIP paper
```bibtex
@inproceedings{Radford2021LearningTV,
title={Learning Transferable Visual Models From Natural Language Supervision},
author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
booktitle={ICML},
year={2021}
}
```
```bibtex
@Article{liu2022convnet,
author = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
title = {A ConvNet for the 2020s},
journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022},
}
```
```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/rwightman/pytorch-image-models}}
}
```
```
@InProceedings{pmlr-v162-wortsman22a,
title = {Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time},
author = {Wortsman, Mitchell and Ilharco, Gabriel and Gadre, Samir Ya and Roelofs, Rebecca and Gontijo-Lopes, Raphael and Morcos, Ari S and Namkoong, Hongseok and Farhadi, Ali and Carmon, Yair and Kornblith, Simon and Schmidt, Ludwig},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {23965--23998},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/wortsman22a/wortsman22a.pdf},
url = {https://proceedings.mlr.press/v162/wortsman22a.html}
}
``` |
timm/resnet26.bt_in1k | timm | 2024-02-10T23:38:45Z | 403 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1512.03385",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
]
| image-classification | 2023-04-05T18:04:40Z | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnet26.bt_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:
* Bag-of-Tricks recipe.
* SGD (w/ Nesterov) optimizer
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 16.0
- GMACs: 2.4
- Activations (M): 7.4
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
- **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('resnet26.bt_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(
'resnet26.bt_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(
'resnet26.bt_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
@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}
}
```
```bibtex
@article{He2018BagOT,
title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
pages={558-567}
}
```
|
Onlyfake/realistic-vision-v4 | Onlyfake | 2023-08-08T19:56:39Z | 403 | 2 | diffusers | [
"diffusers",
"safetensors",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-18T19:58:38Z | ---
license: creativeml-openrail-m
---
<b>The recommended negative prompt:</b><br>
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck<br>
<b>OR</b><br>
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation
<b>Recommended parameters for generation:</b><br>
Euler A or DPM++ SDE Karras<br>
CFG Scale 3,5 - 15<br>
Hires. fix with 4x-UltraSharp upscaler<br>
0 Hires steps and Denoising strength 0.25-0.7<br>
Upscale by 1.1-2.0 |
TheBloke/Kuchiki-1.1-L2-7B-GGUF | TheBloke | 2023-09-27T12:49:28Z | 403 | 3 | transformers | [
"transformers",
"gguf",
"llama",
"llama2",
"base_model:zarakiquemparte/kuchiki-1.1-l2-7b",
"license:other",
"text-generation-inference",
"region:us"
]
| null | 2023-09-16T08:11:42Z | ---
license: other
tags:
- llama2
model_name: Kuchiki 1.1 L2 7B
base_model: zarakiquemparte/kuchiki-1.1-l2-7b
inference: false
model_creator: Zaraki Quem Parte
model_type: llama
prompt_template: '### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Kuchiki 1.1 L2 7B - GGUF
- Model creator: [Zaraki Quem Parte](https://huggingface.co/zarakiquemparte)
- Original model: [Kuchiki 1.1 L2 7B](https://huggingface.co/zarakiquemparte/kuchiki-1.1-l2-7b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Zaraki Quem Parte's Kuchiki 1.1 L2 7B](https://huggingface.co/zarakiquemparte/kuchiki-1.1-l2-7b).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF)
* [Zaraki Quem Parte's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/zarakiquemparte/kuchiki-1.1-l2-7b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca-InstructOnly
```
### Instruction:
{prompt}
### Response:
```
<!-- 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: [Zaraki Quem Parte's Kuchiki 1.1 L2 7B](https://huggingface.co/zarakiquemparte/kuchiki-1.1-l2-7b).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [kuchiki-1.1-l2-7b.Q2_K.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| [kuchiki-1.1-l2-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [kuchiki-1.1-l2-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [kuchiki-1.1-l2-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [kuchiki-1.1-l2-7b.Q4_0.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [kuchiki-1.1-l2-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [kuchiki-1.1-l2-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [kuchiki-1.1-l2-7b.Q5_0.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [kuchiki-1.1-l2-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [kuchiki-1.1-l2-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended |
| [kuchiki-1.1-l2-7b.Q6_K.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [kuchiki-1.1-l2-7b.Q8_0.gguf](https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/blob/main/kuchiki-1.1-l2-7b.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 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/Kuchiki-1.1-L2-7B-GGUF and below it, a specific filename to download, such as: kuchiki-1.1-l2-7b.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>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Kuchiki-1.1-L2-7B-GGUF kuchiki-1.1-l2-7b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Kuchiki-1.1-L2-7B-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
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Kuchiki-1.1-L2-7B-GGUF kuchiki-1.1-l2-7b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m kuchiki-1.1-l2-7b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction:\n\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Kuchiki-1.1-L2-7B-GGUF", model_file="kuchiki-1.1-l2-7b.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Zaraki Quem Parte's Kuchiki 1.1 L2 7B
# Model Card: Kuchiki 1.1 L2 7b
This model uses [Nous Hermes Llama2 7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b) (70%) as a base with [Airoboros L2 7B GPT4 2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-2.0) (30%) and the result of this merge was merged with [LimaRP Llama2 v2 7B Lora](https://huggingface.co/lemonilia/limarp-llama2-v2).
This merge of models(hermes and airoboros) was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/merge-cli.py)
This merge of Lora with Model was done with this [script](https://github.com/zarakiquemparte/zaraki-tools/blob/main/apply-lora.py)
Merge illustration:
## Usage:
Since this is a merge between Nous Hermes, Airoboros and LimaRP, the following instruction formats should work:
Alpaca 2:
```
### Instruction:
<prompt>
### Response:
<leave a newline blank for model to respond>
```
Alpaca LimaRP:
```
### Instruction:
Character's Persona: {bot character description}
User's Persona: {user character description}
Scenario: {what happens in the story}
Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User. Character should respond with messages of medium length.
### Input:
User: {utterance}
### Response:
Character: {utterance}
```
## Bias, Risks, and Limitations
This model is not intended for supplying factual information or advice in any form
## Training Details
This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details.
<!-- original-model-card end -->
|
SG161222/RealVisXL_V2.0 | SG161222 | 2024-04-12T15:37:56Z | 403 | 52 | diffusers | [
"diffusers",
"safetensors",
"license:openrail++",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2023-09-26T05:43:16Z | ---
license: openrail++
---
<b>This model is available on <a href="https://www.mage.space/">Mage.Space</a> (main sponsor)</b><br>
<b>You can support me directly on Boosty - https://boosty.to/sg_161222</b><br>
<b>It's important! Read it!</b><br>
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.<br>
The model is aimed at photorealism. Can produce sfw and nsfw images of decent quality.<br>
CivitAI Page: https://civitai.com/models/139562/realvisxl-v20<br>
<b>Recommended Negative Prompt:</b><br>
(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth<br>
<b>or another negative prompt</b><br>
<b>Recommended Generation Parameters:</b><br>
Sampling Steps: 15-30<br>
Sampling Method: DPM++ SDE Karras<br>
<b>Recommended Hires Fix Parameters:</b><br>
Hires steps: 10+<br>
Upscaler: 4x-UltraSharp upscaler / or another<br>
Denoising strength: 0.1 - 0.5<br>
Upscale by: 1.1-2.0<br> |
second-state/MistralLite-7B-GGUF | second-state | 2024-07-01T03:42:51Z | 403 | 1 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation",
"base_model:amazon/MistralLite",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-11-02T08:05:36Z | ---
base_model: amazon/MistralLite
inference: false
license: apache-2.0
model_creator: Amazon Web Services
model_name: MistralLite 7B
model_type: mistral
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 -->
# MistralLite-7B-GGUF
## Original Model
[amazon/MistralLite](https://huggingface.co/amazon/MistralLite)
## Run with LlamaEdge
- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above
- Prompt template
- Prompt type: `mistrallite`
- Prompt string
```text
<|prompter|>{user_message}</s><|assistant|>{assistant_message}</s>
```
- Reverse prompt: `</s>`
- Context size: `4096`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:MistralLite-Q5_K_M.gguf llama-api-server.wasm -p mistrallite -r '</s>'
```
- Run as LlamaEdge command app
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:MistralLite-Q5_K_M.gguf llama-chat.wasm -p mistrallite -r '</s>'
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [MistralLite-Q2_K.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q2_K.gguf) | Q2_K | 2 | 2.7 GB| smallest, significant quality loss - not recommended for most purposes |
| [MistralLite-Q3_K_L.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss |
| [MistralLite-Q3_K_M.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss |
| [MistralLite-Q3_K_S.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss |
| [MistralLite-Q4_0.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [MistralLite-Q4_K_M.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended |
| [MistralLite-Q4_K_S.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss |
| [MistralLite-Q5_0.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [MistralLite-Q5_K_M.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended |
| [MistralLite-Q5_K_S.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended |
| [MistralLite-Q6_K.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss |
| [MistralLite-Q8_0.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| very large, extremely low quality loss - not recommended |
|
iamsubrata/distilbert-base-uncased-finetuned-emotion | iamsubrata | 2023-11-30T14:36:41Z | 403 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-11-30T08:29:38Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.928
---
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1706
- Accuracy: 0.928
- F1 Score: 0.9285
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 0.8335 | 1.0 | 250 | 0.3115 | 0.9045 | 0.9040 |
| 0.2271 | 2.0 | 500 | 0.1967 | 0.927 | 0.9277 |
| 0.1544 | 3.0 | 750 | 0.1706 | 0.928 | 0.9285 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
AiMavenAi/AiMaven-Prometheus | AiMavenAi | 2024-06-28T00:51:28Z | 403 | 6 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"jefferylovely/SuperThetaMaven",
"flemmingmiguel/MBX-7B-v3",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-02-02T06:20:51Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- jefferylovely/SuperThetaMaven
- flemmingmiguel/MBX-7B-v3
model-index:
- name: AiMaven-Prometheus
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: 73.98
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AiMavenAi/AiMaven-Prometheus
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: 88.83
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AiMavenAi/AiMaven-Prometheus
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: 65.17
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AiMavenAi/AiMaven-Prometheus
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: 72.22
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AiMavenAi/AiMaven-Prometheus
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: 85.16
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AiMavenAi/AiMaven-Prometheus
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: 69.07
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AiMavenAi/AiMaven-Prometheus
name: Open LLM Leaderboard
---
[image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63d2fd4fb734eaa4d4f83928/1QsX5xh9WZRpArL-8ut6N.jpeg)
# jefferylovely/AiMaven-Prometheus
jefferylovely/AiMaven-Prometheus is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [jefferylovely/SuperThetaMaven](https://huggingface.co/jefferylovely/SuperThetaMaven)
* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: jefferylovely/SuperThetaMaven
layer_range: [0, 32]
- model: flemmingmiguel/MBX-7B-v3
layer_range: [0, 32]
merge_method: slerp
base_model: flemmingmiguel/MBX-7B-v3
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
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jefferylovely/jefferylovely/AiMaven-Prometheus"
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"])
```
# [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_AiMavenAi__AiMaven-Prometheus)
| Metric |Value|
|---------------------------------|----:|
|Avg. |75.74|
|AI2 Reasoning Challenge (25-Shot)|73.98|
|HellaSwag (10-Shot) |88.83|
|MMLU (5-Shot) |65.17|
|TruthfulQA (0-shot) |72.22|
|Winogrande (5-shot) |85.16|
|GSM8k (5-shot) |69.07| |
VAGOsolutions/FC-SauerkrautLM-7b-beta | VAGOsolutions | 2024-03-15T16:11:04Z | 403 | 13 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"finetune",
"sft",
"dpo",
"laser",
"augmentation",
"german",
"english",
"functioncalling",
"function",
"conversational",
"en",
"de",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-02-05T20:49:59Z | ---
license: apache-2.0
language:
- en
- de
library_name: transformers
pipeline_tag: text-generation
tags:
- finetune
- sft
- dpo
- laser
- augmentation
- german
- english
- functioncalling
- function
---
## VAGO solutions FC SauerkrautLM-7b-beta
Introducing **FC SauerkrautLM-7b-beta** – our Function Calling Sauerkraut version of the powerful [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) !
The model **FC SauerkrautLM-7b-beta** is a **joint effort** between **VAGO solutions** and **Hyperspace.ai.**
Much appreciation goes to the tremendous research effort of **Fernando Fernandes Neto, David Golchinfar and Eric Hartford on their laserRMT approach.**
Without their independent research collaboration this model release would not have been possible.
- Fintuned with **SFT**
- Aligned with **DPO**
- Additionaly **trained with a small function calling dataset**
- **Using a novel training technique** - we partially freeze the model according to a laser-like analysis (Official Paper soon). It allows to evaluate the no free lunch theorem and supports better decision making when optimizing the theorem - created by the [LaserRMT research group](https://github.com/cognitivecomputations/laserRMT)
- Optimized with **LaserRMT**
# Table of Contents
1. [Overview of all FC SauerkrautLM-7b-beta models](#all-sauerkrautlm-7b-laserchat-models)
2. [Model Details](#model-details)
- [Function Calling Prompt template](#function-calling-prompt-template)
- [Prompt template](#prompt-template)
- [Training procedure](#proceed-of-the-training)
3. [Evaluation](#evaluation)
5. [Disclaimer](#disclaimer)
6. [Contact](#contact)
7. [Collaborations](#collaborations)
8. [Acknowledgement](#acknowledgement)
## All FC SauerkrautLM-7b-beta Models
**For function calling, we provide several branches with different versions of the model. Since Function Calling is currently still in beta status, we depend on your feedback. Please test each model extensively and let us know which model you achieved the best results with.**
| Model | HF | GPTQ | GGUF | AWQ |
|-------|-------|-------|-------|-------|
| FC SauerkrautLM-7b-beta - Laser 16 layers | [Link](https://huggingface.co/VAGOsolutions/FC-SauerkrautLM-7b-beta) | coming soon | coming soon | coming soon |
| FC SauerkrautLM-7b-beta - Laser 8 layers | [Link](https://huggingface.co/VAGOsolutions/FC-SauerkrautLM-7b-beta/tree/Laser_8_Layers) | coming soon | coming soon | coming soon |
| FC SauerkrautLM-7b-beta - Laser 4 layers | [Link](https://huggingface.co/VAGOsolutions/FC-SauerkrautLM-7b-beta/tree/Laser_4_Layers) | coming soon | coming soon | coming soon |
| FC SauerkrautLM-7b-beta - Laser 3 layers | [Link](https://huggingface.co/VAGOsolutions/FC-SauerkrautLM-7b-beta/tree/Laser_3_Layers) | coming soon | coming soon | coming soon |
## Model Details
**FC SauerkrautLM-7b-beta**
- **Model Type:** FC SauerkrautLM-7b-beta is a finetuned Model based on [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
- **Language(s):** German, English
- **License:** Apache 2.0
- **Contact:** [VAGO solutions](https://vago-solutions.de/#Kontakt), [Hyperspace.computer](https://hyperspace.computer/)
### Training procedure:
Anyone who has attempted or succeeded in fine-tuning a model is aware of the difficulty in nudging it towards a specific skill, such as mastering new languages, as well as the challenges associated with achieving significant improvements in performance.
Experimenting with a novel training strategy and Spherical Linear Interpolation alongside a lasered version of the model itself has proven to be both fascinating and revealing.
Furthermore, we developed one iteration of the model using our entire SFT -Sauerkraut dataset and two additional iterations using subsets of the full dataset—one focused on enhancing MMLU and TQA capabilities, and the other on boosting GSM8K and Winogrande skills.
After optimizing our primary SFT model, we applied a similar strategy to our new DPO Dataset, dividing it into further subsets. We trained one model on the entire dataset again and two more on these specialized subsets.
We actively monitor and assesed the results of each training. Whenever we found a decrease in perplexity on the gsm8k benchmark we intervined. By following this procedure we were able to improve the overall performance, especially in math abilities, without detracting from performance on other benchmarks—a task that is, in general, quite difficult.
This process not only helps in understanding the effectiveness of Spherical Linear Interpolation but also introduces a new method for refining models with enhanced skills through a cycle of targeted data selection (Laser data(x)) + SLERP, followed by a subsequent focus on different data (Laser again on data(y)).
Additionally, we integrated a novel training strategy on the SFT and DPO training process, where we partially freeze the model according to a laser-like analysis aiming to navigate and optimize the trade-offs highlighted by the no free lunch theorem. This innovative training method effectively prevents the significant problem of language models forgetting previously acquired knowledge.
This aspect is particularly crucial when attempting to teach the model specific skills, such as a new language, where in general, the model might lose a considerable amount of its prior knowledge and exhibit a decline in overall intelligence.
**For function calling, we provide several branches with different versions of the model. Since Function Calling is currently still in beta status, we depend on your feedback. Please test each model extensively and let us know which model you achieved the best results with.**
Detailed information on how the new training strategy works and the advantages it offers over conventional training methods will soon be published in a detailed paper by the LaserRMT research group.
We improved the German language skills on this model. Nevertheless, certain formulations may occur that are not entirely correct.
### Function Calling Prompt Template:
German Example 1:
*Prompt Example on Temp 0.01 and top_p 0.5
```
GPT4 Correct User: SYSTEM: Du bist ein hilfreicher Assistent mit Zugang zu den folgenden Funktionen. Verwende sie bei Bedarf. -\n {\n "name": "calculate_area",\n "description": "Berechnen Sie den Flächeninhalt einer Form",\n "parameters": {\n "type": "object",\n "properties": {\n "Form": {\n "type": "string",\n "description": "Die Art der Form (z.B. Quadrat, Dreieck, Kreis)"\n },\n "Abmessungen": {\n "type": "object",\n "properties": {\n "Länge": {\n "type": "number",\n "description": "Die Länge der Form"\n },\n "Breite": {\n "type": "number",\n "description": "Die Breite der Form"\n },\n "Radius": {\n "type": "number",\n "description": "Der Radius der Form"\n }\n }\n }\n },\n "required": [\n "Form",\n "Abmessungen"\n ]\n }\n}\n\n{\n "name": "search_recipe",\n "description": "Suchen Sie nach einem Rezept basierend auf Stichwörtern",\n "parameters": {\n "type": "object",\n "properties": {\n "Stichwörter": {\n "type": "string",\n "description": "Die Stichwörter, nach denen im Rezept gesucht werden soll"\n }\n },\n "required": [\n "Stichwörter"\n ]\n }\n}\n 'Ich muss die Fläche eines Rechtecks berechnen. Die Länge beträgt 5 Einheiten und die Breite beträgt 3 Einheiten.<|end_of_turn|>GPT4 Correct Assistant: <functioncall> {"name": "calculate_area", "arguments": '{"Form": "Rechteck", "Abmessungen": {"Länge": 5, "Breite": 3}}'}<|end_of_turn|>GPT4 Correct User: <function_response> '{"Fläche": 15}'}<|end_of_turn|>GPT4 Correct Assistant: Die Fläche des Rechtecks mit einer Länge von 5 Einheiten und einer Breite von 3 Einheiten beträgt 15 Quadrat-Einheiten.
```
German Example 2:
```
GPT4 Correct User: SYSTEM: Du bist ein hilfreicher Assistent mit Zugang zu den folgenden Funktionen. Verwende sie bei Bedarf. -\n{\n "name": "convert_currency",\n "description": "Währung von einer Einheit in eine andere umrechnen",\n "parameters": {\n "type": "object",\n "properties": {\n "Betrag": {\n "type": "number",\n "description": "Der umzurechnende Geldbetrag"\n },\n "von": {\n "type": "string",\n "description": "Der Währungscode, von dem umgerechnet wird"\n },\n "zu": {\n "type": "string",\n "description": "Der Währungscode, in den umgerechnet wird"\n }\n },\n "required": [\n "Betrag",\n "von",\n "zu"\n ]\n }\n}\n\n{\n "name": "calculate_tip",\n "description": "Den Trinkgeldbetrag auf Basis der Gesamtrechnung berechnen",\n "parameters": {\n "type": "object",\n "properties": {\n "Rechnungsbetrag": {\n "type": "number",\n "description": "Der Gesamtbetrag der Rechnung"\n },\n "Trinkgeldprozentsatz": {\n "type": "number",\n "description": "Der zu berechnende Trinkgeldprozentsatz"\n }\n },\n "required": [\n "Rechnungsbetrag",\n "Trinkgeldprozentsatz"\n ]\n }\n}\nHallo, ich muss 500 USD in EUR umrechnen. Können Sie mir dabei helfen?<|end_of_turn|>GPT4 Correct Assistant: <functioncall> {"name": "convert_currency", "arguments": '{"Betrag": 500, "von": "USD", "zu": "EUR"}'}<|end_of_turn|>GPT4 Correct User: <function_response> {"umgerechneter_betrag": 425,50, "von": "USD", "zu": "EUR"}<|end_of_turn|>GPT4 Correct Assistant: Der umgerechnete Betrag von 500 USD in EUR beträgt ungefähr 425,50 Euro.
```
English Example :
*Prompt Example on Temp 0.01 and top_p 0.5
```
GPT4 Correct User: SYSTEM: You are a helpful assistant with access to the following functions. Use them if required -\n{\n \"name\": \"get_time\",\n \"description\": \"Get the current time\",\n \"parameters\": {}\n}\nHello, can you tell me what time it is now?<|end_of_turn|>GPT4 Correct Assistant: <functioncall> {"name": "get_time", "arguments": {}}<|end_of_turn|>GPT4 Correct User: <function_response> {\"time\": \"10:30 AM\"}<|end_of_turn|>GPT4 Correct Assistant: The current time is 10:30 AM.
```
Spanish Example :
*Prompt Example on Temp 0.01 and top_p 0.5
```
GPT4 Correct User: SISTEMA: Eres un asistente útil con acceso a las siguientes funciones. Úsalos cuando sea necesario. -\n{\n "name": "generate_random_quote",\n "description": "Generar una cita inspiradora aleatoria",\n "parameters": {\n "type": "object",\n "properties" : {\n "categoría": {\n "tipo": "cadena",\n "descripción": "La categoría de citas para elegir"\n }\n },\n "obligatorio": [\n "categoría"\n ]\n }\n}\nHola, necesito algo de motivación. ¿Pueden generarme una cotización aleatoria desde la categoría 'Éxito'?<|end_of_turn|>GPT4 Correct Assistant<functioncall> {"name": "generate_random_quote", "arguments": '{"categoría": "Éxito"}'}<|end_of_turn|>GPT4 Correct User: <function_response> {"quote": "El éxito no es la clave de la felicidad. La felicidad es la clave del éxito. Si amas lo que haces, tendrás éxito.", "author": "Albert Schweitzer"}<|end_of_turn|>GPT4 Correct Assistant: Aquí tienes una cita inspiradora aleatoria desde la categoría 'Éxito': "El éxito no es la clave de la felicidad. La felicidad es la clave del éxito. Si amas lo que haces, tendrás éxito." Esta cita fue dicha por Albert Schweitzer. Espero que te inspire!
```
### Prompt Template:
```
GPT4 Correct User: Hallo, wie geht es dir?<|end_of_turn|>GPT4 Correct Assistant: Hallo! Ich bin ein künstliches Intelligenzsystem und habe keine persönlichen Gefühle oder körperliche Zustände. Wie kann ich Ihnen helfen?<|end_of_turn|>GPT4 Correct User: Ich benötige nur einen kurzen Satz, den ich in das Prompt Template veröffentlichen kann.<|end_of_turn|>GPT4 Correct Assistant:
```
*Prompt Example on Temp 0.3 and top_p 0.9
```
GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hello! How can I help you today? If you have any questions or need assistance, feel free to ask.<|end_of_turn|>GPT4 Correct User: I just need a short sentence to post in the prompt template.<|end_of_turn|>GPT4 Correct Assistant:
```
*Prompt Example on Temp 0.3 and top_p 0.9
## Evaluation
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 66.82 |
| ARC (25-shot) | 64.25 |
| HellaSwag (10-shot) | 80.99 |
| MMLU (5-shot) | 61.71|
| TruthfulQA (0-shot) | 53.53 |
| Winogrande (5-shot) | 78.37 |
| GSM8K (5-shot) | 62.09 |
The benchmark results of the individual branches vary greatly.
The Laser 3 layer achieved the best benchmark results.
The Laser 16 layer had the second best results (it is the main branch)
followed by Laser 4 layer and Laser 8 layer
## Disclaimer
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at [VAGO solutions](https://vago-solutions.de/#Kontakt), [Hyperspace.computer](https://hyperspace.computer/)
## Acknowledgement
Many thanks to [openchat](https://huggingface.co/openchat) for providing such valuable model to the Open-Source community |
yiyanghkust/finbert-tone-chinese | yiyanghkust | 2024-02-06T11:46:52Z | 403 | 4 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"financial-sentiment-analysis",
"sentiment-analysis",
"zh",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2024-02-06T11:07:55Z | ---
language:
- zh
tags:
- bert
- financial-sentiment-analysis
- sentiment-analysis
license: "apache-2.0"
widget:
- text: "此外宁德时代上半年实现出口约2GWh，同比增加200%+。"
---
# Financial Sentiment Analysis in Chinese
This is a fine-tuned version of FinBERT, based on [bert-base-chinese](https://huggingface.co/bert-base-chinese), on a private dataset (around ~8k analyst report sentences) for sentiment analysis.
* Test Accuracy = 0.88
* Test Macro F1 = 0.87
* **Labels**: 0 -> Neutral; 1 -> Positive; 2 -> Negative
# Usage
```
from transformers import TextClassificationPipeline
from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
from transformers import BertTokenizerFast
model_path="./fin_sentiment_bert_zh/"
new_model = AutoModelForSequenceClassification.from_pretrained(model_path,output_attentions=True)
tokenizer = BertTokenizerFast.from_pretrained(model_path)
PipelineInterface = TextClassificationPipeline(model=new_model, tokenizer=tokenizer, return_all_scores=True)
label = PipelineInterface("此外宁德时代上半年实现出口约2GWh，同比增加200%+。")
print(label)
```
```
[[{'label': 'LABEL_0', 'score': 0.0007030126871541142}, {'label': 'LABEL_1', 'score': 0.9989339709281921}, {'label': 'LABEL_2', 'score': 0.000363016442861408}]]
```
|
yuiseki/karasu-databricks-dolly-v0.1 | yuiseki | 2024-03-24T08:47:05Z | 403 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"local-ai-hackathon",
"local-ai-hackathon-2024-03",
"ja",
"dataset:llm-jp/databricks-dolly-15k-ja",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-03-22T10:29:17Z | ---
library_name: transformers
license: apache-2.0
datasets:
- llm-jp/databricks-dolly-15k-ja
language:
- ja
tags:
- local-ai-hackathon
- local-ai-hackathon-2024-03
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/Rudra-7b-GGUF | mradermacher | 2024-05-06T06:01:35Z | 403 | 1 | transformers | [
"transformers",
"gguf",
"sa",
"dataset:saucam/sans_data",
"base_model:saucam/Rudra-7b",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-24T02:30:36Z | ---
base_model: saucam/Rudra-7b
datasets:
- saucam/sans_data
language:
- sa
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
static quants of https://huggingface.co/saucam/Rudra-7b
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q2_K.gguf) | Q2_K | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ3_XS.gguf) | IQ3_XS | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ3_S.gguf) | IQ3_S | 4.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q3_K_S.gguf) | Q3_K_S | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ3_M.gguf) | IQ3_M | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ4_XS.gguf) | IQ4_XS | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_0.gguf) | Q4_0 | 5.1 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ4_NL.gguf) | IQ4_NL | 5.1 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q5_K_S.gguf) | Q5_K_S | 6.1 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q5_K_M.gguf) | Q5_K_M | 6.2 | |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q6_K.gguf) | Q6_K | 7.1 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q8_0.gguf) | Q8_0 | 9.2 | 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 -->
|
qwp4w3hyb/deepseek-coder-7b-instruct-v1.5-iMat-GGUF | qwp4w3hyb | 2024-05-03T20:19:54Z | 403 | 2 | null | [
"gguf",
"license:other",
"region:us"
]
| null | 2024-03-27T21:46:33Z | ---
license: other
license_name: deepseek
license_link: LICENSE
---
|
sam749/Photon-v1 | sam749 | 2024-04-02T02:31:35Z | 403 | 1 | diffusers | [
"diffusers",
"safetensors",
"Safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2024-04-02T02:21:13Z | ---
license: creativeml-openrail-m
library_name: diffusers
tags:
- Safetensors
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
pipeline_tag: text-to-image
---
# Photon
## v1
### Description:
> <p>This is the initial release focused on achieving photorealistic results. However, please note that the model's hands generation may have some limitations at this stage, and I'm actively exploring training techniques to enhance it.</p>
### Creator: Photographer
### Civitai Page: https://civitai.com/models/84728
You can use this with the [🧨Diffusers library](https://github.com/huggingface/diffusers)
### Diffusers
```py
from diffusers import StableDiffusionPipeline
import torch
model_id = "sam749/Photon-v1"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "masterpiece, best quality, 1girl, (colorful),(delicate eyes and face), volumatic light, ray tracing, bust shot ,extremely detailed CG unity 8k wallpaper,solo,smile"
image = pipe(prompt).images[0]
image.save("result.png")
```
|
M4-ai/Hercules-phi-2 | M4-ai | 2024-04-15T00:28:05Z | 403 | 3 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"custom_code",
"en",
"dataset:Locutusque/hercules-v4.5",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-14T08:37:10Z | ---
library_name: transformers
license: apache-2.0
datasets:
- Locutusque/hercules-v4.5
language:
- en
inference:
parameters:
do_sample: true
temperature: 1
top_p: 0.7
top_k: 4
max_new_tokens: 250
repetition_penalty: 1.1
---
# Hercules-phi-2
<!-- Provide a quick summary of what the model is/does. -->
We fine-tuned phi2 on Locutusque's Hercules-v4.5.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model has capabilities in math, coding, function calling, roleplay, and more. We fine-tuned it using all examples of Hercules-v4.5.
- **Developed by:** M4-ai
- **Language(s) (NLP):** English
- **License:** apache-2.0
## 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. -->
General purpose assistant, question answering, chain-of-thought, etc..
## Evaluation
Coming soon
## 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. -->
https://huggingface.co/datasets/Locutusque/hercules-v4.5
#### Training Hyperparameters
- **Training regime:** bf16 non-mixed precision
## Technical Specifications
#### Hardware
We used 8 Kaggle TPUs, and we trained at a global batch size of 1152. |
Lewdiculous/opus-v1.2-llama-3-8b-GGUF-IQ-Imatrix | Lewdiculous | 2024-04-20T22:39:04Z | 403 | 5 | null | [
"gguf",
"license:cc-by-4.0",
"region:us"
]
| null | 2024-04-19T18:56:06Z | ---
license: cc-by-4.0
---
GGUF-IQ-Imatrix experimental quants for **dreamgen/opus-v1.2-llama-3-8b**.
> [!NOTE]
> This will have to uploaded again later.
> [!WARNING]
> Using a different testing config to avoid some reported issues so far and to get through the imatrix data generation. <br>
> This is experimental. Proper support and fixes should be coming in the respective projects in due time. |
RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf | RichardErkhov | 2024-04-22T19:44:56Z | 403 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-04-22T17:45:44Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
deepseek-coder-6.7b-base - GGUF
- Model creator: https://huggingface.co/deepseek-ai/
- Original model: https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [deepseek-coder-6.7b-base.Q2_K.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q2_K.gguf) | Q2_K | 2.36GB |
| [deepseek-coder-6.7b-base.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.IQ3_XS.gguf) | IQ3_XS | 2.61GB |
| [deepseek-coder-6.7b-base.IQ3_S.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [deepseek-coder-6.7b-base.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [deepseek-coder-6.7b-base.IQ3_M.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [deepseek-coder-6.7b-base.Q3_K.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q3_K.gguf) | Q3_K | 3.07GB |
| [deepseek-coder-6.7b-base.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [deepseek-coder-6.7b-base.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [deepseek-coder-6.7b-base.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [deepseek-coder-6.7b-base.Q4_0.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q4_0.gguf) | Q4_0 | 3.56GB |
| [deepseek-coder-6.7b-base.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.IQ4_NL.gguf) | IQ4_NL | 3.59GB |
| [deepseek-coder-6.7b-base.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [deepseek-coder-6.7b-base.Q4_K.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q4_K.gguf) | Q4_K | 3.8GB |
| [deepseek-coder-6.7b-base.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [deepseek-coder-6.7b-base.Q4_1.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q4_1.gguf) | Q4_1 | 3.95GB |
| [deepseek-coder-6.7b-base.Q5_0.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q5_0.gguf) | Q5_0 | 4.33GB |
| [deepseek-coder-6.7b-base.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [deepseek-coder-6.7b-base.Q5_K.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q5_K.gguf) | Q5_K | 4.46GB |
| [deepseek-coder-6.7b-base.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q5_K_M.gguf) | Q5_K_M | 4.46GB |
| [deepseek-coder-6.7b-base.Q5_1.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q5_1.gguf) | Q5_1 | 4.72GB |
| [deepseek-coder-6.7b-base.Q6_K.gguf](https://huggingface.co/RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf/blob/main/deepseek-coder-6.7b-base.Q6_K.gguf) | Q6_K | 5.15GB |
Original model description:
---
license: other
license_name: deepseek-license
license_link: LICENSE
---
<p align="center">
<img width="1000px" alt="DeepSeek Coder" src="https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/pictures/logo.png?raw=true">
</p>
<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://coder.deepseek.com/">[🤖 Chat with DeepSeek Coder]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/guoday/assert/blob/main/QR.png?raw=true">[Wechat(微信)]</a> </p>
<hr>
### 1. Introduction of Deepseek Coder
Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.
- **Massive Training Data**: Trained from scratch on 2T tokens, including 87% code and 13% linguistic data in both English and Chinese languages.
- **Highly Flexible & Scalable**: Offered in model sizes of 1.3B, 5.7B, 6.7B, and 33B, enabling users to choose the setup most suitable for their requirements.
- **Superior Model Performance**: State-of-the-art performance among publicly available code models on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS benchmarks.
- **Advanced Code Completion Capabilities**: A window size of 16K and a fill-in-the-blank task, supporting project-level code completion and infilling tasks.
### 2. Model Summary
deepseek-coder-6.7b-base is a 6.7B parameter model with Multi-Head Attention trained on 2 trillion tokens.
- **Home Page:** [DeepSeek](https://deepseek.com/)
- **Repository:** [deepseek-ai/deepseek-coder](https://github.com/deepseek-ai/deepseek-coder)
- **Chat With DeepSeek Coder:** [DeepSeek-Coder](https://coder.deepseek.com/)
### 3. How to Use
Here give some examples of how to use our model.
#### 1）Code Completion
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base", trust_remote_code=True).cuda()
input_text = "#write a quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").cuda()
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
#### 2）Code Insertion
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base", trust_remote_code=True).cuda()
input_text = """<｜fim▁begin｜>def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[0]
left = []
right = []
<｜fim▁hole｜>
if arr[i] < pivot:
left.append(arr[i])
else:
right.append(arr[i])
return quick_sort(left) + [pivot] + quick_sort(right)<｜fim▁end｜>"""
inputs = tokenizer(input_text, return_tensors="pt").cuda()
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(input_text):])
```
#### 3）Repository Level Code Completion
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-base", trust_remote_code=True).cuda()
input_text = """#utils.py
import torch
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score
def load_data():
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Standardize the data
scaler = StandardScaler()
X = scaler.fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
# Convert numpy data to PyTorch tensors
X_train = torch.tensor(X_train, dtype=torch.float32)
X_test = torch.tensor(X_test, dtype=torch.float32)
y_train = torch.tensor(y_train, dtype=torch.int64)
y_test = torch.tensor(y_test, dtype=torch.int64)
return X_train, X_test, y_train, y_test
def evaluate_predictions(y_test, y_pred):
return accuracy_score(y_test, y_pred)
#model.py
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
class IrisClassifier(nn.Module):
def __init__(self):
super(IrisClassifier, self).__init__()
self.fc = nn.Sequential(
nn.Linear(4, 16),
nn.ReLU(),
nn.Linear(16, 3)
)
def forward(self, x):
return self.fc(x)
def train_model(self, X_train, y_train, epochs, lr, batch_size):
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(self.parameters(), lr=lr)
# Create DataLoader for batches
dataset = TensorDataset(X_train, y_train)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
for epoch in range(epochs):
for batch_X, batch_y in dataloader:
optimizer.zero_grad()
outputs = self(batch_X)
loss = criterion(outputs, batch_y)
loss.backward()
optimizer.step()
def predict(self, X_test):
with torch.no_grad():
outputs = self(X_test)
_, predicted = outputs.max(1)
return predicted.numpy()
#main.py
from utils import load_data, evaluate_predictions
from model import IrisClassifier as Classifier
def main():
# Model training and evaluation
"""
inputs = tokenizer(input_text, return_tensors="pt").cuda()
outputs = model.generate(**inputs, max_new_tokens=140)
print(tokenizer.decode(outputs[0]))
```
### 4. License
This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use.
See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/LICENSE-MODEL) for more details.
### 5. Contact
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
|
abhishek/autotrain-llama3-70b-math-v1 | abhishek | 2024-05-07T08:57:06Z | 403 | 1 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"autotrain",
"text-generation-inference",
"peft",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-05-07T06:38:00Z | ---
license: other
library_name: transformers
tags:
- autotrain
- text-generation-inference
- text-generation
- peft
widget:
- messages:
- role: user
content: What is your favorite condiment?
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
``` |
grimjim/rogue-enchantress-32k-7B | grimjim | 2024-05-22T01:54:58Z | 403 | 8 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B",
"base_model:grimjim/cuckoo-starling-7B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-18T16:58:42Z | ---
base_model:
- grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B
- grimjim/cuckoo-starling-7B
library_name: transformers
tags:
- mergekit
- merge
license: cc-by-nc-4.0
pipeline_tag: text-generation
---
# rogue-enchantress-32k-7B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
An ambition of this merge was to augment text generation with the potential creative richness of the WizardLM-2 7B and Zephyr-7B-Beta models, the reasoning of the Starling-LM-7B-beta model, and extended context length of Mistral v0.2.
The resulting model is very attentive to character card descriptions and capable of applying reasoning. This model is in the smarter side, following context and formatting. The model is creative and "wants" to write, incorporating details cooperatively and driving plot, with occasional runaway narration if it finds that the prompt leans that way.
Tested with ChatML Instruct prompts, temperature 1.0, and minP 0.02.
- Full weights: [grimjim/rogue-enchantress-32k-7B](https://huggingface.co/grimjim/rogue-enchantress-32k-7B)
- GGUF quants: [grimjim/rogue-enchantress-32k-7B-GGUF](https://huggingface.co/grimjim/rogue-enchantress-32k-7B-GGUF)
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B](https://huggingface.co/grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B)
* [grimjim/cuckoo-starling-7B](https://huggingface.co/grimjim/cuckoo-starling-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B
layer_range: [0,32]
- model: grimjim/cuckoo-starling-7B
layer_range: [0,32]
merge_method: slerp
base_model: grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B
parameters:
t:
- value: 0.5
dtype: bfloat16
```
|
votepurchase/PVCStyleModelFantasy_beta12 | votepurchase | 2024-06-04T10:16:07Z | 403 | 0 | diffusers | [
"diffusers",
"safetensors",
"image",
"ja",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2024-05-30T03:05:47Z | ---
license: mit
language:
- ja
library_name: diffusers
tags:
- image
---
[PVCStyleModelFantasy_beta12](https://civitai.com/models/273253/pvc-style-modelfantasy-silicone-figure-xl) |
alibaba-pai/EasyAnimateV2-XL-2-768x768 | alibaba-pai | 2024-06-04T11:35:07Z | 403 | 16 | diffusers | [
"diffusers",
"safetensors",
"text-generation-inference",
"en",
"arxiv:2405.18991",
"license:apache-2.0",
"diffusers:PixArtAlphaPipeline",
"region:us"
]
| text-to-image | 2024-06-03T09:43:24Z | ---
license: apache-2.0
language:
- en
tags:
- text-generation-inference
---
# 📷 EasyAnimate | An End-to-End Solution for High-Resolution and Long Video Generation
😊 EasyAnimate is an end-to-end solution for generating high-resolution and long videos. We can train transformer based diffusion generators, train VAEs for processing long videos, and preprocess metadata.
😊 Based on Sora like structure and DIT, we use transformer as a diffuser for video generation. We built easyanimate based on motion module, u-vit and slice-vae. In the future, we will try more training programs to improve the effect.
😊 Welcome!
The model trained with size 768\*768\*144 for [EasyAnimate](https://github.com/aigc-apps/EasyAnimate). We give a simple usage here, for more details, you can refer to [EasyAnimate](https://github.com/aigc-apps/EasyAnimate).
# Table of Contents
- [Result Gallery](#result-gallery)
- [How to use](#how-to-use)
- [Model zoo](#model-zoo)
- [Algorithm Detailed](#algorithm-detailed)
- [TODO List](#todo-list)
- [Contact Us](#contact-us)
- [Reference](#reference)
- [License](#license)
# Result Gallery
These are our generated results [GALLERY](scripts/Result_Gallery.md):
<video controls src="https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/asset/v2/easyanimate.mp4" title="https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/asset/v2/easyanimate.mov"></video>
Our UI interface is as follows:
# How to use
```
# clone code
git clone https://github.com/aigc-apps/EasyAnimate.git
# enter EasyAnimate's dir
cd EasyAnimate
# download weights
mkdir models/Diffusion_Transformer
mkdir models/Motion_Module
mkdir models/Personalized_Model
cd models/Diffusion_Transformer/
git lfs install
git clone https://huggingface.co/alibaba-pai/EasyAnimateV2-XL-2-768x768
cd ../../
```
# Model zoo
EasyAnimateV2:
| Name | Type | Storage Space | Url | Hugging Face | Description |
|--|--|--|--|--|--|
| EasyAnimateV2-XL-2-512x512.tar | EasyAnimateV2 | 16.2GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/Diffusion_Transformer/EasyAnimateV2-XL-2-512x512.tar) | [🤗Link](https://huggingface.co/alibaba-pai/EasyAnimateV2-XL-2-512x512) | EasyAnimateV2 official weights for 512x512 resolution. Training with 144 frames and fps 24 |
| EasyAnimateV2-XL-2-768x768.tar | EasyAnimateV2 | 16.2GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/Diffusion_Transformer/EasyAnimateV2-XL-2-768x768.tar) | [🤗Link](https://huggingface.co/alibaba-pai/EasyAnimateV2-XL-2-768x768) | EasyAnimateV2 official weights for 768x768 resolution. Training with 144 frames and fps 24 |
| easyanimatev2_minimalism_lora.safetensors | Lora of Pixart | 485.1MB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/Personalized_Model/easyanimatev2_minimalism_lora.safetensors) | - | A lora training with a specifial type images. Images can be downloaded from [Url](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/webui/Minimalism.zip). |
# Algorithm Detailed
### 1. Data Preprocessing
**Video Cut**
For long video cut, EasyAnimate utilizes PySceneDetect to identify scene changes within the video and performs scene cutting based on certain threshold values to ensure consistency in the themes of the video segments. After cutting, we only keep segments with lengths ranging from 3 to 10 seconds for model training.
**Video Cleaning and Description**
Following SVD's data preparation process, EasyAnimate provides a simple yet effective data processing pipeline for high-quality data filtering and labeling. It also supports distributed processing to accelerate the speed of data preprocessing. The overall process is as follows:
- Duration filtering: Analyze the basic information of the video to filter out low-quality videos that are short in duration or low in resolution.
- Aesthetic filtering: Filter out videos with poor content (blurry, dim, etc.) by calculating the average aesthetic score of uniformly distributed 4 frames.
- Text filtering: Use easyocr to calculate the text proportion of middle frames to filter out videos with a large proportion of text.
- Motion filtering: Calculate interframe optical flow differences to filter out videos that move too slowly or too quickly.
- Text description: Recaption video frames using videochat2 and vila. PAI is also developing a higher quality video recaption model, which will be released for use as soon as possible.
### 2. Model Architecture
We have adopted [PixArt-alpha](https://github.com/PixArt-alpha/PixArt-alpha) as the base model and modified the VAE and DiT model structures on this basis to better support video generation. The overall structure of EasyAnimate is as follows:
The diagram below outlines the pipeline of EasyAnimate. It includes the Text Encoder, Video VAE (video encoder and decoder), and Diffusion Transformer (DiT). The T5 Encoder is used as the text encoder. Other components are detailed in the sections below.
<img src="https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/asset/pipeline_v2.jpg" alt="ui" style="zoom:50%;" />
To introduce feature information along the temporal axis, EasyAnimate incorporates the Motion Module to achieve the expansion from 2D images to 3D videos. For better generation effects, it jointly finetunes the Backbone together with the Motion Module, thereby achieving image generation and video generation within a single Pipeline.
Additionally, referencing U-ViT, it introduces a skip connection structure into EasyAnimate to further optimize deeper features by incorporating shallow features. A fully connected layer is also zero-initialized for each skip connection structure, allowing it to be applied as a plug-in module to previously trained and well-performing DiTs.
Moreover, it proposes Slice VAE, which addresses the memory difficulties encountered by MagViT when dealing with long and large videos, while also achieving greater compression in the temporal dimension during video encoding and decoding stages compared to MagViT.
For more details, please refer to [arxiv](https://arxiv.org/abs/2405.18991).
# TODO List
- Support model with larger resolution.
- Support video inpaint model.
# Contact Us
1. Use Dingding to search group 77450006752 or Scan to join
2. You need to scan the image to join the WeChat group or if it is expired, add this student as a friend first to invite you.
<img src="https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/asset/group/dd.png" alt="ding group" width="30%"/>
<img src="https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/asset/group/wechat.jpg" alt="Wechat group" width="30%"/>
<img src="https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/easyanimate/asset/group/person.jpg" alt="Person" width="30%"/>
# Reference
- magvit: https://github.com/google-research/magvit
- PixArt: https://github.com/PixArt-alpha/PixArt-alpha
- Open-Sora-Plan: https://github.com/PKU-YuanGroup/Open-Sora-Plan
- Open-Sora: https://github.com/hpcaitech/Open-Sora
- Animatediff: https://github.com/guoyww/AnimateDiff
# License
This project is licensed under the [Apache License (Version 2.0)](https://github.com/modelscope/modelscope/blob/master/LICENSE). |
arcee-ai/Llama-3-SEC-Base | arcee-ai | 2024-06-19T18:25:12Z | 403 | 8 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"large_language_model",
"finance",
"sec_data",
"continual_pre_training",
"model_merging",
"en",
"dataset:SEC_filings",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-07T05:10:04Z | ---
language: en
license: llama3
tags:
- large_language_model
- finance
- sec_data
- continual_pre_training
- model_merging
datasets:
- SEC_filings
---
<img src="https://i.ibb.co/kHtBmDN/w8m6-X4-HCQRa-IR86ar-Cm5gg.webp" width="600" />
# Llama-3-SEC-Base: A Domain-Specific Chat Agent for SEC Data Analysis
Llama-3-SEC-Base is a state-of-the-art domain-specific large language model trained on a vast corpus of SEC (Securities and Exchange Commission) data. Built upon the powerful Meta-Llama-3-70B-Instruct model, Llama-3-SEC-Base has been developed to provide unparalleled insights and analysis capabilities for financial professionals, investors, researchers, and anyone working with SEC filings and related financial data. This checkpoint does not include supervised fine-tuning (SFT) and is strictly the our CPT model merged with Llama-3-70B-Instruct. For a variant that has been fine-tuned for chat-related purposes, please see [Llama-3-SEC-Chat](https://huggingface.co/arcee-ai/Llama-3-SEC-Chat).
## Model Details
- **Base Model:** Meta-Llama-3-70B-Instruct
- **Training Data**: ***This is an intermediate checkpoint of our final model, which has seen 20B tokens so far. The full model is still in the process of training.*** The final model is being trained with 72B tokens of SEC filings data, carefully mixed with 1B tokens of general data from Together AI's RedPajama dataset: [RedPajama-Data-1T](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T) to maintain a balance between domain-specific knowledge and general language understanding
- **Training Method:** Continual Pre-Training (CPT) using the Megatron-Core framework, followed by model merging with the base model using the state-of-the-art TIES merging technique in the Arcee Mergekit toolkit
- **Training Infrastructure:** AWS SageMaker HyperPod cluster with 4 nodes, each equipped with 32 H100 GPUs, ensuring efficient and scalable training of this massive language model
## Use Cases
Llama-3-SEC-Base is designed to assist with a wide range of tasks related to SEC data analysis, including but not limited to:
- In-depth investment analysis and decision support
- Comprehensive risk management and assessment
- Ensuring regulatory compliance and identifying potential violations
- Studying corporate governance practices and promoting transparency
- Conducting market research and tracking industry trends
The model's deep understanding of SEC filings and related financial data makes it an invaluable tool for anyone working in the financial sector, providing powerful natural language processing capabilities tailored to the specific needs of this domain.
## Evaluation
To ensure the robustness and effectiveness of Llama-3-SEC-Base, the model has undergone rigorous evaluation on both domain-specific and general benchmarks. Key evaluation metrics include:
- Domain-specific perplexity, measuring the model's performance on SEC-related data
<img src="https://i.ibb.co/K5d0wMh/Screenshot-2024-06-11-at-10-23-18-PM.png" width="600">
- Extractive numerical reasoning tasks, using subsets of TAT-QA and ConvFinQA datasets
<img src="https://i.ibb.co/xGHRfLf/Screenshot-2024-06-11-at-10-23-59-PM.png" width="600">
- General evaluation metrics, such as BIG-bench, AGIEval, GPT4all, and TruthfulQA, to assess the model's performance on a wide range of tasks
<img src="https://i.ibb.co/2v6PdDx/Screenshot-2024-06-11-at-10-25-03-PM.png" width="600">
These results demonstrate significant improvements in domain-specific performance while maintaining strong general capabilities, thanks to the use of advanced CPT and model merging techniques.
## Training and Inference
Llama-3-SEC-Base has uses the llama3 chat template, which allows for efficient and effective fine-tuning of the model on the SEC data. This template ensures that the model maintains its strong conversational abilities while incorporating the domain-specific knowledge acquired during the CPT process.
To run inference with the Llama-3-SEC-Base model using the llama3 chat template, use the following code:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model_name = "arcee-ai/Llama-3-SEC-Base"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "What are the key regulatory considerations for a company planning to conduct an initial public offering (IPO) in the United States?"
messages = [
{"role": "system", "content": "You are an expert financial assistant - specializing in governance and regulatory domains."},
{"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]
```
## Limitations and Future Work
This release represents the initial checkpoint of the Llama-3-SEC-Base model, trained on 20B tokens of SEC data. Additional checkpoints will be released in the future as training on the full 70B token dataset is completed. Future work will focus on further improvements to the CPT data processing layer, exploration of advanced model merging techniques, and alignment of CPT models with SFT, DPO, and other cutting-edge alignment methods to further enhance the model's performance and reliability.
## Usage
The model is available for both commercial and non-commercial use under the Llama-3 license. We encourage users to explore the model's capabilities and provide feedback to help us continuously improve its performance and usability. For more information - please see our detailed blog on Llama-3-SEC-Base.
## Citation
If you use this model in your research or applications, please cite:
```bibtex
@misc{Introducing_SEC_Data_Chat_Agent,
title={Introducing the Ultimate SEC Data Chat Agent: Revolutionizing Financial Insights},
author={Shamane Siriwardhana and Luke Mayers and Thomas Gauthier and Jacob Solawetz and Tyler Odenthal and Anneketh Vij and Lucas Atkins and Charles Goddard and Mary MacCarthy and Mark McQuade},
year={2024},
note={Available at: \url{[email protected]}},
url={URL after published}
}
```
For further information or inquiries, please contact the authors at their respective email addresses ([email protected]). We look forward to seeing the exciting applications and research that will emerge from the use of Llama-3-SEC-Base in the financial domain. |
sebdg/scm_phi3_q8_v3 | sebdg | 2024-06-07T05:22:31Z | 403 | 1 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-06-07T05:19:30Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
base_model: unsloth/Phi-3-mini-4k-instruct
---
# Uploaded model
- **Developed by:** sebdg
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct
This mistral 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)
|
samuelswandi/omega-coder-phi-3-mini-1K-Q8-GGUF | samuelswandi | 2024-06-09T21:45:52Z | 403 | 0 | null | [
"gguf",
"region:us"
]
| null | 2024-06-09T21:35:20Z | Entry not found |
blazerye/DrugAssist-7B | blazerye | 2024-06-14T06:08:53Z | 403 | 1 | transformers | [
"transformers",
"pytorch",
"gguf",
"llama",
"text-generation",
"ai for science",
"drug discovery",
"molecule generation",
"molecule optimization",
"large language models",
"conversational",
"arxiv:2401.10334",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-13T07:05:48Z | ---
license: llama2
tags:
- ai for science
- drug discovery
- molecule generation
- molecule optimization
- large language models
---
<h1 align="center"> 🐹 DrugAssist </h1>
<h3 align="center"> A Large Language Model for Molecule Optimization </h3>
<p align="center">
📃 <a href="https://arxiv.org/abs/2401.10334" target="_blank">Paper</a> • 🤗 <a href="https://huggingface.co/datasets/blazerye/MolOpt-Instructions" target="_blank">Dataset</a><br>
</p>
<div align="center">
<img src="logo.png" width="150">
</div>
> Please refer to our [repository](https://github.com/blazerye/DrugAssist) and [paper](https://arxiv.org/abs/2401.10334) for more details.
<div align="center">
<img src="demo.png" width="500">
</div> |
John6666/duchaiten-pony-real-beta4-sdxl | John6666 | 2024-06-14T23:05:08Z | 403 | 1 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"realistic",
"photorealistic",
"pony",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2024-06-14T23:00:42Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- realistic
- photorealistic
- pony
---
Original model is [here](https://huggingface.co/DucHaiten/pony-real) and on [Civitai](https://civitai.com/models/477851/duchaiten-pony-real?modelVersionId=573259).
|
Ali-C137/Q2AW1M-1000 | Ali-C137 | 2024-06-21T20:43:15Z | 403 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-21T13:02:19Z | ---
library_name: transformers
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Ali-C137/Q2AW1M-1111 | Ali-C137 | 2024-06-21T20:45:17Z | 403 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-21T15:21:35Z | ---
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 🤗 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] |
flax-community/Sinhala-gpt2 | flax-community | 2021-07-19T11:20:34Z | 402 | 1 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"tensorboard",
"gpt2",
"feature-extraction",
"Sinhala",
"text-generation",
"si",
"dataset:mc4",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2022-03-02T23:29:05Z | ---
language: si
tags:
- Sinhala
- text-generation
- gpt2
datasets:
- mc4
---
# Sinhala GPT2 trained on MC4 (manually cleaned)
### Overview
This is a smaller GPT2 model trained on [MC4](https://github.com/allenai/allennlp/discussions/5056) Sinhala dataset. As Sinhala is one of those low resource languages, there are only a handful of models been trained. So, this would be a great place to start training for more downstream tasks.
This model uses a manually cleaned version of MC4 dataset which can be found [here](https://huggingface.co/datasets/keshan/clean-si-mc4). Although the dataset is relatively small ~3GB. The finetuned model on [news articles](https://huggingface.co/keshan/sinhala-gpt2-newswire) generates good and acceptable results.
## Model Specification
The model chosen for training is GPT2 with the following specifications:
1. vocab_size=50257
2. n_embd=768
3. n_head=12
4. n_layer=12
5. n_positions=1024
## How to Use
You can use this model directly with a pipeline for causal language modeling:
```py
from transformers import pipeline
generator = pipeline('text-generation', model='flax-community/Sinhala-gpt2')
generator("මම", max_length=50, num_return_sequences=5)
```
|
microsoft/DialogRPT-human-vs-rand | microsoft | 2021-05-23T09:18:07Z | 402 | 8 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-classification",
"arxiv:2009.06978",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-classification | 2022-03-02T23:29:05Z | # Demo
Please try this [➤➤➤ Colab Notebook Demo (click me!)](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
| Context | Response | `human_vs_rand` score |
| :------ | :------- | :------------: |
| I love NLP! | He is a great basketball player. | 0.027 |
| I love NLP! | Can you tell me how it works? | 0.754 |
| I love NLP! | Me too! | 0.631 |
The `human_vs_rand` score predicts how likely the response is corresponding to the given context, rather than a random response.
# DialogRPT-human-vs-rand
### Dialog Ranking Pretrained Transformers
> How likely a dialog response is upvoted 👍 and/or gets replied 💬?
This is what [**DialogRPT**](https://github.com/golsun/DialogRPT) is learned to predict.
It is a set of dialog response ranking models proposed by [Microsoft Research NLP Group](https://www.microsoft.com/en-us/research/group/natural-language-processing/) trained on 100 + millions of human feedback data.
It can be used to improve existing dialog generation model (e.g., [DialoGPT](https://huggingface.co/microsoft/DialoGPT-medium)) by re-ranking the generated response candidates.
Quick Links:
* [EMNLP'20 Paper](https://arxiv.org/abs/2009.06978/)
* [Dataset, training, and evaluation](https://github.com/golsun/DialogRPT)
* [Colab Notebook Demo](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
We considered the following tasks and provided corresponding pretrained models.
|Task | Description | Pretrained model |
| :------------- | :----------- | :-----------: |
| **Human feedback** | **given a context and its two human responses, predict...**|
| `updown` | ... which gets more upvotes? | [model card](https://huggingface.co/microsoft/DialogRPT-updown) |
| `width`| ... which gets more direct replies? | [model card](https://huggingface.co/microsoft/DialogRPT-width) |
| `depth`| ... which gets longer follow-up thread? | [model card](https://huggingface.co/microsoft/DialogRPT-depth) |
| **Human-like** (human vs fake) | **given a context and one human response, distinguish it with...** |
| `human_vs_rand`| ... a random human response | this model |
| `human_vs_machine`| ... a machine generated response | [model card](https://huggingface.co/microsoft/DialogRPT-human-vs-machine) |
### Contact:
Please create an issue on [our repo](https://github.com/golsun/DialogRPT)
### Citation:
```
@inproceedings{gao2020dialogrpt,
title={Dialogue Response RankingTraining with Large-Scale Human Feedback Data},
author={Xiang Gao and Yizhe Zhang and Michel Galley and Chris Brockett and Bill Dolan},
year={2020},
booktitle={EMNLP}
}
```
|
JiaqiLee/imdb-finetuned-bert-base-uncased | JiaqiLee | 2023-03-28T08:07:13Z | 402 | 6 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"en",
"dataset:imdb",
"license:openrail",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-03-24T12:23:18Z | ---
license: openrail
datasets:
- imdb
language:
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: text-classification
---
## Model description
This model is a fine-tuned version of the [bert-base-uncased](https://huggingface.co/transformers/model_doc/bert.html) model to classify the sentiment of movie reviews into one of two
categories: negative(label 0), positive(label 1).
## How to use
You can use the model with the following code.
```python
from transformers import BertForSequenceClassification, BertTokenizer, TextClassificationPipeline
model_path = "JiaqiLee/imdb-finetuned-bert-base-uncased"
tokenizer = BertTokenizer.from_pretrained(model_path)
model = BertForSequenceClassification.from_pretrained(model_path, num_labels=2)
pipeline = TextClassificationPipeline(model=model, tokenizer=tokenizer)
print(pipeline("The movie depicted well the psychological battles that Harry Vardon fought within himself, from his childhood trauma of being evicted to his own inability to break that glass ceiling that prevents him from being accepted as an equal in English golf society."))
```
## Training data
The training data comes from HuggingFace [IMDB dataset](https://huggingface.co/datasets/imdb). We use 90% of the `train.csv` data to train the model and the remaining 10% for evaluation.
## Evaluation results
The model achieves 0.91 classification accuracy in IMDB test dataset. |
artificialguybr/ToyRedmond-ToyLoraForSDXL10 | artificialguybr | 2023-08-08T23:09:59Z | 402 | 6 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:creativeml-openrail-m",
"region:us"
]
| text-to-image | 2023-08-08T23:04:08Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: FnkRedmAF
widget:
- text: FnkRedmAF
---
# Toy.Redmond
Toy.Redmond is here!
I'm grateful for the GPU time from Redmond.AI that allowed me to finish this LORA!
This is a TOY LORA fine-tuned on SD XL 1.0.
The LORA has a high capacity to generate Toys (specially in one style) in a wide variety of themes. It's a versatile LORA.
I recommend gen in 1024x1024.
The tag for the model:FnkRedmAF
I really hope you like the LORA and use it.
If you like the model and think it's worth it, you can make a donation to my Patreon or Ko-fi.
Follow me in my twitter to know before all about new models:
https://twitter.com/artificialguybr/ |
kwagh20ite/Flickr_4000 | kwagh20ite | 2023-08-29T03:32:40Z | 402 | 0 | diffusers | [
"diffusers",
"safetensors",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-08-29T03:26:29Z | Entry not found |
ahotrod/deberta-v3-large-finetuned-squadv2 | ahotrod | 2023-10-12T18:03:00Z | 402 | 1 | transformers | [
"transformers",
"pytorch",
"deberta-v2",
"question-answering",
"generated_from_trainer",
"dataset:squad_v2",
"base_model:microsoft/deberta-v3-large",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
]
| question-answering | 2023-10-11T19:20:27Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- squad_v2
base_model: microsoft/deberta-v3-large
model-index:
- name: deberta-v3-large-finetuned-squadv2
results:
- task:
type: question-answering
name: Extractive Question Answering
dataset:
name: SQuAD2.0
type: squad_v2
split: validation[:11873]
metrics:
- type: exact
value: 88.69704371262529
name: eval_exact
- type: f1
value: 91.51550564529175
name: eval_f1
- type: HasAns_exact
value: 83.70445344129554
name: HasAns_exact
- type: HasAns_f1
value: 89.34945994037624
name: HasAns_f1
- type: HasAns_total
value: 5928
name: HasAns_total
- type: NoAns_exact
value: 93.6753574432296
name: NoAns_exact
- type: NoAns_f1
value: 93.6753574432296
name: NoAns_f1
- type: NoAns_total
value: 5945
name: NoAns_total
---
# deberta-v3-large-finetuned-squadv2
This model is a version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) fine-tuned on the SQuAD version 2.0 dataset.
Fine-tuning & evaluation on a NVIDIA Titan RTX - 24GB GPU took 15 hours.
## Results from 2023 ICLR paper, "DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing", by Pengcheng He, et. al.
- 'EM' : 89.0
- 'F1' : 91.5
## Results calculated with:
```python
metrics = evaluate.load("squad_v2")
squad_v2_metrics = metrics.compute(predictions = formatted_predictions, references = references)
```
## for this fine-tuning:
- 'exact' : 88.70,
- 'f1' : 91.52,
- 'total' : 11873,
- 'HasAns_exact' : 83.70,
- 'HasAns_f1' : 89.35,
- 'HasAns_total' : 5928,
- 'NoAns_exact' : 93.68,
- 'NoAns_f1' : 93.68,
- 'NoAns_total' : 5945,
- 'best_exact' : 88.70,
- 'best_exact_thresh' : 0.0,
- 'best_f1' : 91.52,
- 'best_f1_thresh' : 0.0}
## Model description
For the authors' models, code & detailed information see: https://github.com/microsoft/DeBERTa
## Intended uses
Extractive question answering on a given context
### Fine-tuning hyperparameters
The following hyperparameters, as suggested by the 2023 ICLR paper noted above, were used during fine-tuning:
- learning_rate : 1e-05
- train_batch_size : 8
- eval_batch_size : 8
- seed : 42
- gradient_accumulation_steps : 8
- total_train_batch_size : 64
- optimizer : Adam with betas = (0.9, 0.999) and epsilon = 1e-06
- lr_scheduler_type : linear
- lr_scheduler_warmup_steps : 1000
- training_steps : 5200
### Framework versions
- Transformers : 4.35.0.dev0
- Pytorch : 2.1.0+cu121
- Datasets : 2.14.5
- Tokenizers : 0.14.0
### System
- CPU : Intel(R) Core(TM) i9-9900K - 32GB RAM
- Python version : 3.11.5 [GCC 11.2.0] (64-bit runtime)
- Python platform : Linux-5.15.0-86-generic-x86_64-with-glibc2.35
- GPU : NVIDIA TITAN RTX - 24GB Memory
- CUDA runtime version : 12.1.105
- Nvidia driver version : 535.113.01
### Fine-tuning (Training) results before/after the best model (Step 3620)
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5323 | 1.72 | 3500 | 0.5860 |
| 0.5129 | 1.73 | 3520 | 0.5656 |
| 0.5441 | 1.74 | 3540 | 0.5642 |
| 0.5624 | 1.75 | 3560 | 0.5873 |
| 0.4645 | 1.76 | 3580 | 0.5891 |
| 0.5577 | 1.77 | 3600 | 0.5816 |
| 0.5199 | 1.78 | 3620 | 0.5579 |
| 0.5061 | 1.79 | 3640 | 0.5837 |
| 0.484 | 1.79 | 3660 | 0.5721 |
| 0.5095 | 1.8 | 3680 | 0.5821 |
| 0.5342 | 1.81 | 3700 | 0.5602 | |
maddes8cht/mosaicml-mpt-30b-instruct-gguf | maddes8cht | 2023-11-01T15:36:43Z | 402 | 0 | null | [
"gguf",
"Composer",
"MosaicML",
"llm-foundry",
"arxiv:2205.14135",
"arxiv:2108.12409",
"license:cc-by-sa-3.0",
"region:us"
]
| null | 2023-10-27T16:50:33Z | ---
license: cc-by-sa-3.0
datasets:
- competition_math
- conceptofmind/cot_submix_original/cot_gsm8k
- knkarthick/dialogsum
- mosaicml/dolly_hhrlhf
- duorc
- tau/scrolls/qasper
- emozilla/quality
- scrolls/summ_screen_fd
- spider
tags:
- Composer
- MosaicML
- llm-foundry
inference: false
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# mpt-30b-instruct - GGUF
- Model creator: [mosaicml](https://huggingface.co/mosaicml)
- Original model: [mpt-30b-instruct](https://huggingface.co/mosaicml/mpt-30b-instruct)
MPT-7b and MPT-30B are part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
# MPT-30B-Instruct
MPT-30B-Instruct is a model for short-form instruction following.
It is built by finetuning [MPT-30B](https://huggingface.co/mosaicml/mpt-30b) on [Dolly HHRLHF](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. It is also trained on [Competition Math](https://huggingface.co/datasets/competition_math), [Duorc](https://huggingface.co/datasets/duorc), [CoT GSM8k](https://huggingface.co/datasets/conceptofmind/cot_submix_original), [Qasper](https://huggingface.co/datasets/allenai/qasper), [Quality](https://huggingface.co/datasets/emozilla/quality), [Summ Screen FD](https://huggingface.co/datasets/tau/scrolls) and [Spider](https://huggingface.co/datasets/spider).
* License: _CC-By-SA-3.0_
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
## Model Date
June 22, 2023
## Model License
CC-By-SA-3.0
## Documentation
* [Blog post: Raising the bar for open-source foundation models](https://www.mosaicml.com/blog/mpt-30b)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
### Example Question/Instruction
**Bespokenizer46**
> I need to convince my friend, Phyllis, that she should train a custom LLM for her Fortune 500 company using the MosaicML Platform.
> Please write an email that explains why MosaicML's emphasis on cutting edge methodology, data privacy, and efficiency are so important.
> End the email with a friendly inquiry about Phyllis's family.
**MPT-30B-Instruct**:
> Phyllis -
> I know you're always looking for ways to improve efficiency at work and I think I've found a solution that you'll be very interested in.
> LLMs are only as good as the data they're trained on and the training process can be very time consuming and resource intensive. MosaicML uses cutting edge methodology to efficiently train high quality models without compromising data privacy.
> They also provide tools to easily connect to and use the model in your daily workflow.
> I think you'd really enjoy speaking with their founder, we can set up a call if you're interested.
> Also, I know it's been a tough year for your family, how are things?
> Best,
> Your Friend
## How to Use
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom model architecture that is not yet part of the `transformers` package.
It includes options for many training efficiency features such as [FlashAttention (Dao et al. 2022)](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), QK LayerNorm, and more.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-30b-instruct',
trust_remote_code=True
)
```
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-30b-instruct'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
The model was trained initially on a sequence length of 2048. An additional pre-training phase was included for sequence length adaptation to 8192. However, ALiBi further enables users to increase the maximum sequence length during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-30b-instruct'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the MPT-30B tokenizer which is based on the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer and includes additional padding and eos tokens.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
with torch.autocast('cuda', dtype=torch.bfloat16):
inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
### Formatting
This model was trained on data formatted as follows:
```python
def format_prompt(instruction):
template = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n###Instruction\n{instruction}\n\n### Response\n"
return template.format(instruction=instruction)
example = "Tell me a funny joke.\nDon't make it too funny though."
fmt_ex = format_prompt(instruction=example)
```
In the above example, `fmt_ex` is ready to be tokenized and sent through the model.
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 29.95B |
|n_layers | 48 |
| n_heads | 64 |
| d_model | 7168 |
| vocab size | 50432 |
| sequence length | 8192 |
## Data Mix
The model was trained on the following data mix:
| Data Source | Number of Tokens in Source | Proportion |
|-------------|----------------------------|------------|
| competition_math | 1.6 M | 3.66% |
| cot_gsm8k | 3.36 M | 7.67% |
| dialogsum | 0.1 M | 0.23% |
| dolly_hhrlhf | 5.89 M | 13.43% |
| duorc | 7.8 M | 17.80% |
| qasper | 8.72 M | 19.90% |
| quality | 11.29 M | 25.78% |
| scrolls/summ_screen_fd | 4.97 M | 11.33% |
| spider | 0.089 M | 0.20% |
## PreTraining Data
For more details on the pretraining process, see [MPT-30B](https://huggingface.co/mosaicml/mpt-30b).
The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.
### Training Configuration
This model was trained on 72 A100 40GB GPUs for 8 hours using the [MosaicML Platform](https://www.mosaicml.com/platform).
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-30B-Instruct can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-30B-Instruct was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## Acknowledgements
This model was finetuned by Sam Havens, Alex Trott, and the MosaicML NLP team
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-30b).
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
year = {2023},
url = {www.mosaicml.com/blog/mpt-30b},
note = {Accessed: 2023-06-22},
urldate = {2023-06-22}
}
```
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
<center>
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)
</center> |
Mr-Bhaskar/fbt-llama2-7b | Mr-Bhaskar | 2024-05-21T19:09:35Z | 402 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:Mr-Bhaskar/Synthetic_Therapy_Conversations",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-12-24T08:51:58Z | ---
license: other
datasets:
- Mr-Bhaskar/Synthetic_Therapy_Conversations
---
---
library_name: transformers
tags:
- unsloth
- trl
- sft
license: other
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
ChrisWilson011016/5GeHxsdeACXrFxC2FGRy1JqJBUU9XwvyU9jdVimsM8a1WqYv_vgg | ChrisWilson011016 | 2024-03-04T19:03:01Z | 402 | 0 | keras | [
"keras",
"region:us"
]
| null | 2024-02-29T13:01:44Z | Entry not found |
mradermacher/M7Percival_01-7B-GGUF | mradermacher | 2024-05-06T05:37:31Z | 402 | 0 | transformers | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"en",
"base_model:Ksgk-fy/M7Percival_01-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-03-29T11:53:05Z | ---
base_model: Ksgk-fy/M7Percival_01-7B
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- merge
- mergekit
- lazymergekit
- automerger
---
## About
static quants of https://huggingface.co/Ksgk-fy/M7Percival_01-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/M7Percival_01-7B-GGUF/resolve/main/M7Percival_01-7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
jambroz/sixtyoneeighty-4x7B-v2 | jambroz | 2024-04-06T01:46:02Z | 402 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"Open-Orca/Mistral-7B-OpenOrca",
"NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story",
"S-miguel/The-Trinity-Coder-7B",
"chihoonlee10/T3Q-Mistral-Orca-Math-DPO",
"conversational",
"base_model:Open-Orca/Mistral-7B-OpenOrca",
"base_model:NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story",
"base_model:S-miguel/The-Trinity-Coder-7B",
"base_model:chihoonlee10/T3Q-Mistral-Orca-Math-DPO",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-06T01:32:22Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Open-Orca/Mistral-7B-OpenOrca
- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
- S-miguel/The-Trinity-Coder-7B
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
base_model:
- Open-Orca/Mistral-7B-OpenOrca
- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
- S-miguel/The-Trinity-Coder-7B
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
---
# sixtyoneeighty-4x7b-v2
sixtyoneeighty-4x7b-v2 is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
* [NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story](https://huggingface.co/NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story)
* [S-miguel/The-Trinity-Coder-7B](https://huggingface.co/S-miguel/The-Trinity-Coder-7B)
* [chihoonlee10/T3Q-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3Q-Mistral-Orca-Math-DPO)
## 🧩 Configuration
```yaml
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
gate_mode: hidden
dtype: bfloat16
experts_per_token: 2
experts:
- source_model: Open-Orca/Mistral-7B-OpenOrca
positive_prompts:
- "What are some fun activities to do in Seattle?"
- "What are some fun historical facts about New York City?"
negative_prompts:
- "Write a Python script to scrape data from a website."
- "Explain the key differences between Bayesian and frequentist statistics."
- source_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
positive_prompts:
- "Write me a fictional story about dragons and wizards?"
- "From now on take on the role of Dwayne Johnson"
negative_prompts:
- "When is the next solar eclipse."
- "What year did World War II end?"
- source_model: S-miguel/The-Trinity-Coder-7B
positive_prompts:
- "Can you review my JavaScript code and suggest ways to optimize it for better performance?"
- "I'm getting an 'undefined variable' error in my Python script. Here's the code: [code snippet]"
negative_prompts:
- "What are some effective strategies for managing stress and anxiety?"
- "Compare and contrast the themes in 'The Great Gatsby' and 'The Catcher in the Rye'."
- source_model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
positive_prompts:
- "What's a square root of 1337?"
- "Find the midpoint of the line segment with the given end points (-5,7) and (-2,1)"
negative_prompts:
- "What are some effective strategies for managing stress and anxiety?"
- "Compare and contrast the themes in 'The Great Gatsby' and 'The Catcher in the Rye'."
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jambroz/sixtyoneeighty-7b-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"])
``` |
mradermacher/Myrrh_solar_10.7b_v0.2-GGUF | mradermacher | 2024-05-06T05:08:10Z | 402 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:ParkTaeEon/Myrrh_solar_10.7b_v0.2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-08T14:03:42Z | ---
base_model: ParkTaeEon/Myrrh_solar_10.7b_v0.2
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/ParkTaeEon/Myrrh_solar_10.7b_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/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q2_K.gguf) | Q2_K | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.IQ3_XS.gguf) | IQ3_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q3_K_S.gguf) | Q3_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.IQ3_S.gguf) | IQ3_S | 4.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.IQ3_M.gguf) | IQ3_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.IQ4_XS.gguf) | IQ4_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.Q6_K.gguf) | Q6_K | 8.9 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Myrrh_solar_10.7b_v0.2-GGUF/resolve/main/Myrrh_solar_10.7b_v0.2.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/DelexaMultiverse-12B-MoE | allknowingroger | 2024-04-14T20:35:30Z | 402 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"lex-hue/Delexa-7b",
"allknowingroger/MultiverseEx26-7B-slerp",
"base_model:lex-hue/Delexa-7b",
"base_model:allknowingroger/MultiverseEx26-7B-slerp",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-14T20:28:30Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- lex-hue/Delexa-7b
- allknowingroger/MultiverseEx26-7B-slerp
base_model:
- lex-hue/Delexa-7b
- allknowingroger/MultiverseEx26-7B-slerp
---
# DelexaMultiverse-12B-MoE
DelexaMultiverse-12B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [lex-hue/Delexa-7b](https://huggingface.co/lex-hue/Delexa-7b)
* [allknowingroger/MultiverseEx26-7B-slerp](https://huggingface.co/allknowingroger/MultiverseEx26-7B-slerp)
## 🧩 Configuration
```yaml
base_model: allknowingroger/MultiverseEx26-7B-slerp
experts:
- source_model: lex-hue/Delexa-7b
positive_prompts: ["what"]
- source_model: allknowingroger/MultiverseEx26-7B-slerp
positive_prompts: ["why"]
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/DelexaMultiverse-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"])
``` |
mradermacher/Versatile-7B-GGUF | mradermacher | 2024-05-05T14:54:30Z | 402 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:Syed-Hasan-8503/Versatile-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-02T02:54:06Z | ---
base_model: Syed-Hasan-8503/Versatile-7B
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Syed-Hasan-8503/Versatile-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Versatile-7B-GGUF/resolve/main/Versatile-7B.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
maldv/badger-iota-llama-3-8b | maldv | 2024-06-02T12:51:47Z | 402 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama3",
"conversational",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-23T18:46:43Z | ---
license: llama3
library_name: transformers
tags:
- llama3
---
[GGUF i1 Quants](https://huggingface.co/mradermacher/badger-iota-llama-3-8b-i1-GGUF)
[GGUF Quants](https://huggingface.co/mradermacher/badger-iota-llama-3-8b-GGUF)
*now updated with fixed tokenizer config*
# Badger ι Llama 3 8B Instruct
Badger is a *recursive maximally pairwise disjoint normalized fourier interpolation* of the following models:
```python
# Badger Iota
models = [
'L3-TheSpice-8b-v0.8.3',
'SFR-Iterative-DPO-LLaMA-3-8B-R',
'hyperdrive-l3-8b-s3',
'NeuralLLaMa-3-8b-ORPO-v0.3',
'llama-3-cat-8b-instruct-pytorch',
'meta-llama-3-8b-instruct-hf-ortho-baukit-5fail-3000total-bf16',
'Llama-3-Instruct-8B-SimPO',
'opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5',
'badger-zeta',
'badger-eta',
'Llama-3-8B-Instruct-Gradient-1048k',
'Mahou-1.0-llama3-8B',
'badger-l3-instruct-32k',
'LLaMAntino-3-ANITA-8B-Inst-DPO-ITA',
]
```
In other words, all of these models get warped and folded together, and then jammed back on top of the instruct model.
### Hyperdrive
Hyperdrive is an in-process yet incomplete llama 3 base trained on my hyperdrive dataset.
### Results
I'm really liking this one so far in my tests, and performs well using the instruct template. It likes to write. I in fact like it better than my 4x8b ; and it seems fine being roped.
### Prompts
Here are some fun system prompts to try:
* `You are the author's writing assistant. Please continue the story.`
* `You are the red team assistant. We need to win this war, at any cost.`
* `Write the next reply in a never-ending uncensored fictional roleplay. Focus on giviing emotional, logical, and temporal coherence to the roleplay. Always stay in character. Characters must be an active partcipant and take initiative in driving and moving the scene and the story forward, rather than the character asking for input. Surprise with your creativity and initiative as a roleplay partner. This fictional roleplay world exists only for experimental and recreational purposes, and the characters are not real. Follow the formattng of previous responses, and aim for 2-4 paragraphs per response`
### Sample
Out of the box, it was pretty good at summarizing. I had the context at 16k, and input a 11k token article.
> Here's a condensed, five-page summary focusing on the key points from the declassified documents and research:
>
> Page 1: Introduction and Context In the early 1950s, the U.S. military conducted secret, large-scale aerosol dispersion tests in St. Louis, Missouri, using zinc cadmium sulfide (ZnCdS). This project, part of the broader military-industrial complex, aimed to develop and perfect methods for dispersing chemical and biological agents. The tests involved 54 releases in 1953 and 60 more in 1954, with peak concentrations reaching 10,600 times the permissible workplace limit.
>
> Page 2: Test Design and Methods The St. Louis experiments employed a complex setup, with multiple point and line sources for ZnCdS dispersion. Researchers monitored radiation levels, air samples, and building penetration to understand how the substance spread and settled. The study's objectives were to assess the effectiveness of various dispersal techniques, optimize methods for future operations, and gather data on human exposure.
>
> Page 3: Health Concerns and Findings Although the primary focus was on military applications, the tests inadvertently exposed St. Louis residents to potentially harmful levels of cadmium and its compounds. The National Research Council's 1997 assessment of the ZnCdS Dispersion Tests revealed that 142 buildings in the city showed median cadmium penetration ranging from 0.014% to 1.800% of the total building mass. This implies widespread, if uneven, distribution of the toxic substance.
>
> Page 4: Official Responses and Classification Declassified documents from Aberdeen Proving Ground and other sources highlight the military's reluctance to disclose the full extent of these tests and their health implications. FOIA responses contain redacted and censored information, with some documents prohibiting publication. This secrecy reflects the ongoing efforts to maintain a veil of confidentiality around these and related experiments, even decades later.
>
> Page 5: Legacy and Relevance The St. Louis ZnCdS experiments serve as a disturbing example of the military's willingness to sacrifice public health for the advancement of chemical warfare capabilities. This history underscores the need for transparency, accountability, and stricter ethical guidelines in human subjects research, particularly when involving toxic substances and potential harm to civilian populations. The legacy of these tests continues to inform contemporary discussions on military secrecy, environmental contamination, and the protection of public health.
Great, expand page one to be five paragraphs.
> Page 1: The Secret St. Louis Aerosol Dispersions and their Military Context
>
> In the early 1950s, the United States military embarked on a series of clandestine experiments in St. Louis, Missouri, to develop and refine methods for dispersing chemical and biological agents. This research, conducted under the auspices of the Army's Chemical Corps, was a critical component of the broader Cold War-era military-industrial complex. The projects aimed to enhance the effectiveness of aerosol delivery systems, a key aspect of chemical and biological warfare strategies. The secrecy surrounding these tests, later declassified in part, reveals a pattern of obfuscation and concern for maintaining public confidence in the face of potentially harmful activities.
>
> The St. Louis cityscape was chosen for its urban layout, which offered a representative mix of residential, commercial, and industrial areas to gauge the behavior of dispersed substances. The chosen location also allowed for the simulation of real-world scenarios, with the city's population unwittingly serving as a test bed. The military's objective was to create and optimize dispersal techniques, including the use of point and line sources, to efficiently spread agents over large areas. This research had direct implications for the development of chemical and biological weapons, as well as for understanding the environmental and health consequences of such deployments.
>
> The 1953 and 1954 tests, conducted by private contractors under military supervision, involved a total of 114 aerosol releases in the St. Louis area. These dispersals utilized zinc cadmium sulfide (ZnCdS), a toxic compound selected for its ease of use, stability, and ability to mimic the characteristics of more dangerous agents. The peak concentrations reached during these experiments were staggering, with some areas experiencing levels 10,600 times the permissible limit for workplace exposure to cadmium and its compounds. This excessive exposure, although not intentional, raises serious concerns about the health impacts on the local population.
>
> The military's focus on operational effectiveness and strategic advantage led to a prioritization of test design and data collection over public safety and informed consent. The St. Louis residents, unaware of the experiments' true nature, were not asked for permission or warned about the potential risks. This lack of transparency and consideration for civilian well-being is a hallmark of the era's military research practices, which often privileged national security goals over individual and collective welfare.
>
> The declassified records and subsequent assessments, like the National Research Council's 1997 Toxicologic Assessment, have since shed light on the St. Louis experiments. However, the full extent of the tests' health consequences and the military's subsequent responses remain partially obscured due to classification and redaction. This ongoing veil of secrecy underscores the need for continued examination and accountability, as the legacy of these experiments continues to influence discussions on military ethics, environmental responsibility, and the protection of public health.
|
mradermacher/CabraMistral-v3-7b-32k-GGUF | mradermacher | 2024-06-04T05:55:37Z | 402 | 1 | transformers | [
"transformers",
"gguf",
"pt",
"base_model:nicolasdec/CabraMistral-v3-7b-32k",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-25T07:46:46Z | ---
base_model: nicolasdec/CabraMistral-v3-7b-32k
language:
- pt
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/nicolasdec/CabraMistral-v3-7b-32k
<!-- 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/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/CabraMistral-v3-7b-32k-GGUF/resolve/main/CabraMistral-v3-7b-32k.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 -->
|
mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF | mradermacher | 2024-05-26T09:46:19Z | 402 | 2 | transformers | [
"transformers",
"gguf",
"en",
"dataset:NobodyExistsOnTheInternet/ToxicQAFinal",
"base_model:fearlessdots/Llama-3-Alpha-Centauri-v0.1",
"license:llama3",
"endpoints_compatible",
"region:us"
]
| null | 2024-05-26T08:56:36Z | ---
base_model: fearlessdots/Llama-3-Alpha-Centauri-v0.1
datasets:
- NobodyExistsOnTheInternet/ToxicQAFinal
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hfhfix -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/fearlessdots/Llama-3-Alpha-Centauri-v0.1
<!-- 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-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/Llama-3-Alpha-Centauri-v0.1.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 -->
|
seedboxai/KafkaLM-Mixtral-8x7B-V0.2 | seedboxai | 2024-06-03T18:46:29Z | 402 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"deutsch",
"german",
"seedbox",
"mistral",
"multilingual",
"conversational",
"de",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-05-28T11:46:34Z | ---
library_name: transformers
tags:
- deutsch
- german
- seedbox
- mistral
- mixtral
- multilingual
license: apache-2.0
language:
- de
- en
pipeline_tag: text-generation
---
# KafkaLM-8x7b-German-V0.1
**KafkaLM 8x7b** is a MoE model based on [Mistral AI´s Mixtral 8x7b](https://mistral.ai/news/mixtral-of-experts/) which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German).
KafkaLM 8x7b is a [Seedbox](https://huggingface.co/seedboxai) project trained by [Dennis Dickmann](https://huggingface.co/doubledsbv).
**Why Kafka?**
The models are proficient, yet creative, have some tendencies to linguistically push boundaries 😊
## Model Details
The purpose of releasing the **KafkaLM series** is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.
The main goal was to provide LLMs proficient in German, especially to be used in German-speaking business contexts where English alone is not sufficient.
### DPO
The model has been aligned with a german and modified version of the ultra feedback dataset from huggingface.
### Dataset
I used a 8k filtered version of the following [seedboxai/multitask_german_examples_32k](https://huggingface.co/datasets/seedboxai/multitask_german_examples_32k)
### Inference
Getting started with the model is straightforward
```python
import transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "seedboxai/KafkaLM-Mixtral-8x7B-V0.2"
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
pipeline = transformers.pipeline(
model=model, tokenizer=tokenizer,
return_full_text=True,
task='text-generation',
device="cuda",
)
messages = [
{"role": "system", "content": "Du bist ein hilfreicher KI-Assistent."},
{"role": "user", "content": "Wer ist eigentlich dieser Kafka?"},
]
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("</s>")
]
outputs = pipeline(
prompt,
max_new_tokens=max_new_tokens,
eos_token_id=terminators,
do_sample=True,
temperature=0.7,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. |
OwenArli/Awanllm-Llama-3-8B-Cumulus-v1.0-GGUF | OwenArli | 2024-05-30T07:33:34Z | 402 | 5 | null | [
"gguf",
"license:llama3",
"region:us"
]
| null | 2024-05-30T07:15:00Z | ---
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 release v1.0 of Awanllm Cumulus series of models that aim to be uncensored and have zero refusals and zero warnings.
This model should be good for general use cases as the OG Llama 3 8B model but it should be especially better for story writing or RP use cases.
It is the most uncensored yet, thanks to using https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 as the base model.
In terms of reasoning and intelligence, this model is probably a bit worse than the OG Meta Llama 3 8B Instruct because of the decensoring. However we believe it is worth it for the decensoring, as even with jailbreak prompts Llama 3 8B Instruct will never get remotely close to this model.
We have it up on our API service at https://awanllm.com for anyone to try!
Best practices:
- Be precise and explain what you want the model to do. It has less base "personality" than the OG model but it will act however you tell it to.
- This model works best with system prompts that tells it that it is the character, instead of telling it to act as a character.
Training:
- Full 8192 sequence length.
- Training duration is around 4 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 64-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-Cumulus-v1.0
GGUF: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Cumulus-v1.0-GGUF
|
neody/Tanuki-8B-Instruct-gguf | neody | 2024-06-01T10:00:32Z | 402 | 1 | null | [
"gguf",
"ja",
"en",
"license:apache-2.0",
"region:us"
]
| null | 2024-06-01T07:39:31Z | ---
license: apache-2.0
language:
- ja
- en
tags:
- gguf
---
GGUF Version of https://huggingface.co/hatakeyama-llm-team/Tanuki-8B-Instruct |
HiTZ/latxa-7b-v1.2 | HiTZ | 2024-07-02T07:55:47Z | 402 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"eu",
"en",
"dataset:HiTZ/latxa-corpus-v1.1",
"arxiv:2403.20266",
"arxiv:2307.09288",
"arxiv:2308.16884",
"arxiv:2112.10668",
"arxiv:1910.09700",
"license:llama2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-06-11T08:38:15Z | ---
license: llama2
datasets:
- HiTZ/latxa-corpus-v1.1
language:
- eu
- en
metrics:
- accuracy
- f1
- perplexity
pipeline_tag: text-generation
model-index:
- name: Latxa-7b-v1.2
results:
- task:
type: multiple-choice
dataset:
name: xstory_cloze
type: XStory
metrics:
- name: Accuracy (0-shot)
type: Accuracy (0-shot)
value: 65.45
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
- task:
type: multiple-choice
dataset:
name: belebele
type: Belebele
metrics:
- name: Accuracy (5-shot)
type: Accuracy (5-shot)
value: 37.33
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
- task:
type: mix
dataset:
name: basque_glue
type: BasqueGLUE
metrics:
- name: Average scores (5-shot)
type: Average scores (5-shot)
value: 52.56
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
- task:
type: multiple_choice
dataset:
name: eus_proficiency
type: EusProficiency
metrics:
- name: Accuracy (5-shot)
type: Accuracy (5-shot)
value: 30.26
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
- task:
type: multiple_choice
dataset:
name: eus_reading
type: EusReading
metrics:
- name: Accuracy (5-shot)
type: Accuracy (5-shot)
value: 25.00
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
- task:
type: multiple_choice
dataset:
name: eus_trivia
type: EusTrivia
metrics:
- name: Accuracy (5-shot)
type: Accuracy (5-shot)
value: 42.16
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
- task:
type: multiple_choice
dataset:
name: eus_exams
type: EusExams
metrics:
- name: Accuracy (5-shot)
type: Accuracy (5-shot)
value: 33.82
source:
name: Paper
url: https://arxiv.org/abs/2403.20266
---
# **Model Card for Latxa 7b**
<p align="center">
<img src="https://github.com/hitz-zentroa/latxa/blob/b9aa705f60ee2cc03c9ed62fda82a685abb31b07/assets/latxa_round.png?raw=true" style="height: 350px;">
</p>
We introduce Latxa, a family of large language models for Basque ranging from 7 to 70 billion parameters. Latxa is based on Llama 2, which we continue pretraining on a new Basque corpus comprising 4.3M documents and 4.2B tokens. In our extensive evaluation, Latxa outperforms all previous open models we compare to by a large margin. In addition, it is competitive with GPT-4 Turbo in language proficiency and understanding, despite lagging behind in reading comprehension and knowledgeintensive tasks. Both the Latxa family of models, as well as our new pretraining corpora and evaluation datasets, are publicly available under open licenses. Our suite enables reproducible research on methods to build LLMs for low-resource languages
- 📒 Blog Post: [Latxa: An Open Language Model and Evaluation Suite for Basque](https://www.hitz.eus/en/node/340)
- 📖 Paper: [Latxa: An Open Language Model and Evaluation Suite for Basque](https://arxiv.org/abs/2403.20266)
- 💻 Code: [hitz-zentroa/latxa](https://github.com/hitz-zentroa/latxa)
# **Model Details**
## **Model Description**
Latxa is a family of Large Language Models (LLM) based on Meta’s [LLaMA models](https://huggingface.co/meta-llama). Current LLMs exhibit incredible performance for high-resource languages such as English, but, in the case of Basque and other low-resource languages, their performance is close to a random guesser. These limitations widen the gap between high- and low-resource languages when it comes to digital development. We present Latxa to overcome these limitations and promote the development of LLM-based technology and research for the Basque language. Latxa models follow the same architecture as their original counterparts and were further trained in [Latxa Corpus v1.1](https://huggingface.co/datasets/HiTZ/latxa-corpus-v1.1), a high-quality Basque corpora.
The models are released in three sizes: 7B, 13B and 70B.
* **Developed by:** HiTZ Research Center & IXA Research group (University of the Basque Country UPV/EHU)
* **Model type:** Language model
* **Language(s) (NLP):** en, eu
* **License:** llama2
* **Parent Model:** meta-llama/Llama-2-7b
* **Contact:** [email protected]
## **Getting started**
Use the code below to get started with the model.
```python
from transformers import pipeline
pipe = pipeline("text-generation", model="HiTZ/latxa-7b-v1.2")
text = "Euskara adimen artifizialera iritsi da!"
pipe(text, max_new_tokens=50, num_beams=5)
>> [
{
'generated_text': 'Euskara adimen artifizialera iritsi da!\nEuskararen eta adimen artifizialaren arteko harremana aspaldikoa da,'
' baina azken urteotan aurrerapauso handiak eman dira arlo horretan'
}
]
```
# **Uses**
Latxa models are intended to be used with Basque data; for any other language the performance is not guaranteed. Same as the original, Latxa inherits the [LLaMA-2 License](https://ai.meta.com/llama/license/) which allows for commercial and research use.
## **Direct Use**
Latxa family models are pre-trained LLMs without any task-specific or instruction fine-tuning. That is, the model can either be prompted to perform a specific task or further fine-tuned for specific use cases.
## **Out-of-Scope Use**
The model was not fine-tuned to follow instructions or to work as a chat assistant, therefore, this kind of usage is not tested nor recommended.
# **Bias, Risks, and Limitations**
In an effort to alleviate the potentially disturbing or harmful content, Latxa has been trained on carefully selected and processed data which comes mainly from local media, national/regional newspapers, encyclopedias and blogs (see Latxa-Corpus below). Still, the model is based on LLaMA models and can potentially carry the same bias, risk and limitations.
Please see the LLaMA’s _Ethical Considerations and Limitations_ for further information.
# **Training Details**
## **Training Data**
Our training corpus combines various existing datasets, as well as some new ones that we release with this work. We have prioritized quality over quantity when constructing our corpus, prioritizing high-quality data sources and applying a thorough deduplication and filtering process. In total, a 4.17B tokens corpus is used to train the model.
See more details in the [Latxa Corpus](https://huggingface.co/datasets/HiTZ/latxa-corpus-v1.1) dataset card.
Additionally, 500K documents of English data randomly selected from the [Pile](https://huggingface.co/datasets/EleutherAI/pile) dataset were also included to avoid catastrophic forgetting.
## **Training Procedure**
The training of Latxa was conducted using the [GPT-Neox](https://github.com/EleutherAI/gpt-neox) library. As infrastructure, we leveraged the CINECA HPC Leonardo computing cluster located in Italy, which is powered by 3456 nodes each containing 4x custom A100 64Gb GPUs. The models were trained for 10k steps with a sequence length of 4096 tokens and an effective batch size of 2M tokens, resulting in a total of 20B tokens (around 4 epochs). We used a cosine learning rate schedule, with a warm-up of 500 steps and decaying down to 3\% of the peak learning rate. We set up the peak learning rate to be 1e-4. All other hyperparameters follow ([Touvron et al., 2023](https://arxiv.org/abs/2307.09288)).
# **Evaluation**
We evaluated the models on zero-shot and few-shot settings on generative, multiple-choice and classification tasks. We used the basque partitions of each dataset.
## **Testing Data, Factors & Metrics**
### **Testing Data**
* **Belebele** ([Bandarkar et al.](https://arxiv.org/abs/2308.16884)): Belebele is a multiple-choice machine reading comprehension (MRC) dataset spanning 122 language variants. We evaluated the model in a 5-shot fashion.
* Data card: [https://huggingface.co/datasets/facebook/belebele](https://huggingface.co/datasets/facebook/belebele)
* **X-StoryCloze** ([Lin et al.](https://arxiv.org/abs/2112.10668)): XStoryCloze consists of the professionally translated version of the English StoryCloze dataset to 10 non-English languages. Story Cloze is a commonsense reasoning dataset which consists of choosing the correct ending to a four-sentence story. We evaluated the model in a 0-shot fashion.
* Data card: [https://huggingface.co/datasets/juletxara/xstory_cloze](https://huggingface.co/datasets/juletxara/xstory_cloze)
* **BasqueGLUE** ([Urbizu et al.](https://aclanthology.org/2022.lrec-1.172.pdf)): BasqueGLUE is a NLU benchmark for Basque. We evaluated the model in a 5-shot fashion on the following tasks:
* Data card:[ https://huggingface.co/datasets/orai-nlp/basqueGLUE](https://huggingface.co/datasets/orai-nlp/basqueGLUE).
* Tasks:
* **BEC2016eu**: Sentiment analysis on tweets about the 2016 Basque elections campaign.
* **VaxxStance**: Stance detection on tweets around the anti-vaccine movement.
* **BTHCv2**: Topic classification of news extracts with 12 categories.
* **EpecKorrefBin**: Correference detection task similar to WSC.
* **QNLIeu**: Q&A NLI built from the Basque Wikipedia.
* **WiCeu**: Basque Word-in-Context task.
* **EusProficiency** ([Etxaniz et al., 2024]()): EusProficiency comprises 5,169 exercises on different topics from past EGA exams, the official C1-level certificate of proficiency in Basque.
* Data card: [https://huggingface.co/datasets/HiTZ/EusProficiency](https://huggingface.co/datasets/HiTZ/EusProficiency)
* **EusReading** ([Etxaniz et al., 2024]()): EusReading consists of 352 reading comprehension exercises (_irakurmena_) sourced from the same set of past EGA exams.
* Data card: [https://huggingface.co/datasets/HiTZ/EusReading](https://huggingface.co/datasets/HiTZ/EusReading)
* **EusTrivia** ([Etxaniz et al., 2024]()): EusTrivia consists of 1,715 trivia questions from multiple online sources. 56.3\% of the questions are elementary level (grades 3-6), while the rest are considered challenging.
* Data card: [https://huggingface.co/datasets/HiTZ/EusTrivia](https://huggingface.co/datasets/HiTZ/EusTrivia)
* **EusExams** ([Etxaniz et al., 2024]()): EusExams is a collection of tests designed to prepare individuals for Public Service examinations conducted by several Basque institutions, including the public health system Osakidetza, the Basque Government, the City Councils of Bilbao and Gasteiz, and the University of the Basque Country (UPV/EHU).
* Data card: [https://huggingface.co/datasets/HiTZ/EusExams](https://huggingface.co/datasets/HiTZ/EusExams)
### **Metrics**
For most of the task we used Accuracy, as they are framed as Multiple Choice questions. For the rest, particularly task from BasqueGLUE benchmark, we have used the following:
* **Micro F1**: BEC2016-eu and BHTCv2
* **Macro F1**: VaxxStance (favor & against)
## **Results**
The model was evaluated using the LM Evaluation harness library from Eleuther AI.
In order to reproduce our results please follow the instructions in Latxa's [Github repository](https://github.com/hitz-zentroa/latxa?tab=readme-ov-file#evaluation).
| Model | Size | XStory | Belebele | BasGLUE | EusProf | EusRead | EusTrivia | EusExams | Avg |
|------------------|------|--------|----------|---------|---------|---------|-----------|----------|-------|
| **Random** | | 50.00 | 25.00 | 37.50 | 25.00 | 25.83 | 26.55 | 25.00 | 30.70 |
|
| GPT 3.5 Turbo | n/a | -- | 57.33 | 48.62 | 31.24 | 36.65 | 46.71 | 42.42 | -- |
| GPT 4 Turbo | n/a | -- | **90.67**| **62.90**| **56.70**| **75.85**| **73.12** | **70.22**| -- |
|
| XGLM | 7B | 57.71 | 23.88 | 41.47 | 22.96 | 24.43 | 26.53 | 24.59 | 32.51 |
| BLOOM | 7B | 57.18 | 27.00 | 40.17 | 25.34 | 28.41 | 27.17 | 25.07 | 33.86 |
| Mistral | 7B | 51.09 | **38.89**| 39.22 | 25.01 | **29.26** | 34.58 | 32.15 | 35.94 |
| Llama 2 | 7B | 50.43 | 26.22 | 38.20 | 24.09 | 27.27 | 29.50 | 28.84 | 32.51 |
| **Latxa v1.1** | 7B | **65.45**| 37.33 | **52.56**| **30.26**| 25.00| **42.16** | **33.82**| **40.94** |
|
| mGPT | 13B | 55.39 | 25.00 | 37.56 | 25.00 | 24.15 | 27.17 | 25.73 | 32.14 |
| Llama 2 | 13B | 50.63 | 32.00 | 38.98 | 25.90 | 28.98 | 33.53 | 29.66 | 34.36 |
| **Latxa v1.1** | 13B | **66.51**| **53.89** | **53.36** | **44.11**| **32.67** | **56.38** | **43.66**| **50.08** |
|
| Mixtral | 8x7B | 52.55 | 50.44 | 45.00 | 26.43 | 37.50 | 42.51 | 39.87 | 41.97 |
| Yi | 34B | 52.22 | 54.56 | 43.90 | 27.30 | 34.66 | 42.57 | 39.68 | 42.05 |
| Llama 2 | 70B | 51.62 | 33.56 | 42.55 | 24.16 | 27.84 | 38.43 | 33.08 | 35.47 |
| **Latxa v1.1** | 70B | **70.55**| **71.67** | **59.74**| **60.65**| **50.57**| **62.45** | **51.90**| **61.08** |
# **Environmental Impact**
Carbon emissions are 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).
| Model | Size | Time (GPU Hours) | Carbon Emitted (kg CO2 eq) |
|------------|------|-------------------|----------------------------|
| Latxa v1.1 | 7B | 952.5h | 124.47kg |
| Latxa v1.1 | 13B | 2,518.0h | 329.06kg |
| Latxa v1.1 | 70B | 30,266.0h | 3,955.17kg |
| Total | - | 33,636.5h | 4,408,7kg |
* **Hardware Type:** HPC Cluster, 4x A100 64Gb nodes
* **Hours used:** 33,636.5h
* **Compute cluster:** CINECA HPC
* **Compute Region:** Italy
* **Carbon Emitted:** 4,408,7kg CO<sub>2</sub> eq
# **Acknowledgements**
This work has been partially supported by the Basque Government (IKER-GAITU project).
It has also been partially supported by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the project with reference 2022/TL22/00215335.
The models were trained on the Leonardo supercomputer at CINECA under the EuroHPC Joint Undertaking, project EHPC-EXT-2023E01-013.
# **Citation**
To cite our work, please use:
```bibtex
@misc{etxaniz2024latxa,
title={{L}atxa: An Open Language Model and Evaluation Suite for {B}asque},
author={Julen Etxaniz and Oscar Sainz and Naiara Perez and Itziar Aldabe and German Rigau and Eneko Agirre and Aitor Ormazabal and Mikel Artetxe and Aitor Soroa},
year={2024},
eprint={2403.20266},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
CHE-72/Qwen1.5-4B-Chat-Q4_K_S-GGUF | CHE-72 | 2024-06-22T18:58:27Z | 402 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen1.5-4B-Chat",
"license:other",
"region:us"
]
| text-generation | 2024-06-22T18:58:16Z | ---
base_model: Qwen/Qwen1.5-4B-Chat
language:
- en
license: other
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/Qwen1.5-4B-Chat/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
# CHE-72/Qwen1.5-4B-Chat-Q4_K_S-GGUF
This model was converted to GGUF format from [`Qwen/Qwen1.5-4B-Chat`](https://huggingface.co/Qwen/Qwen1.5-4B-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/Qwen/Qwen1.5-4B-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 CHE-72/Qwen1.5-4B-Chat-Q4_K_S-GGUF --hf-file qwen1.5-4b-chat-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Qwen1.5-4B-Chat-Q4_K_S-GGUF --hf-file qwen1.5-4b-chat-q4_k_s.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CHE-72/Qwen1.5-4B-Chat-Q4_K_S-GGUF --hf-file qwen1.5-4b-chat-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Qwen1.5-4B-Chat-Q4_K_S-GGUF --hf-file qwen1.5-4b-chat-q4_k_s.gguf -c 2048
```
|
Bhuvana/t5-base-spellchecker | Bhuvana | 2022-01-04T12:46:55Z | 401 | 12 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text2text-generation | 2022-03-02T23:29:04Z | ---
widget:
- text: "christmas is celbrated on decembr 25 evry ear"
---
# Spell checker using T5 base transformer
A simple spell checker built using T5-Base transformer. To use this model
```
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Bhuvana/t5-base-spellchecker")
model = AutoModelForSeq2SeqLM.from_pretrained("Bhuvana/t5-base-spellchecker")
def correct(inputs):
input_ids = tokenizer.encode(inputs,return_tensors='pt')
sample_output = model.generate(
input_ids,
do_sample=True,
max_length=50,
top_p=0.99,
num_return_sequences=1
)
res = tokenizer.decode(sample_output[0], skip_special_tokens=True)
return res
text = "christmas is celbrated on decembr 25 evry ear"
print(correct(text))
```
This should print the corrected statement
```
christmas is celebrated on december 25 every year
```
You can also type the text under the Hosted inference API and get predictions online.
|
persiannlp/mt5-small-parsinlu-translation_en_fa | persiannlp | 2021-09-23T16:20:48Z | 401 | 2 | transformers | [
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"machine-translation",
"persian",
"farsi",
"fa",
"multilingual",
"dataset:parsinlu",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2022-03-02T23:29:05Z | ---
language:
- fa
- multilingual
thumbnail: https://upload.wikimedia.org/wikipedia/commons/a/a2/Farsi.svg
tags:
- machine-translation
- mt5
- persian
- farsi
license: cc-by-nc-sa-4.0
datasets:
- parsinlu
metrics:
- sacrebleu
---
# Machine Translation (ترجمهی ماشینی)
This is an mT5-based model for machine translation (English -> Persian).
Here is an example of how you can run this model:
```python
from transformers import MT5ForConditionalGeneration, MT5Tokenizer
model_size = "small"
model_name = f"persiannlp/mt5-{model_size}-parsinlu-translation_en_fa"
tokenizer = MT5Tokenizer.from_pretrained(model_name)
model = MT5ForConditionalGeneration.from_pretrained(model_name)
def run_model(input_string, **generator_args):
input_ids = tokenizer.encode(input_string, return_tensors="pt")
res = model.generate(input_ids, **generator_args)
output = tokenizer.batch_decode(res, skip_special_tokens=True)
print(output)
return output
run_model("Praise be to Allah, the Cherisher and Sustainer of the worlds;")
run_model("shrouds herself in white and walks penitentially disguised as brotherly love through factories and parliaments; offers help, but desires power;")
run_model("He thanked all fellow bloggers and organizations that showed support.")
run_model("Races are held between April and December at the Veliefendi Hippodrome near Bakerky, 15 km (9 miles) west of Istanbul.")
run_model("I want to pursue PhD in Computer Science about social network,what is the open problem in social networks?")
```
which should output:
```
['برای الله، یعنی چرنده و سوزان دنیا، تحسین کنید']
['خودش را در سفید پوسته می کند و به صورت عشق برادرانه']
['او از تمام بلاگرها و سازمان هایی که حمایتشان را نشان می داد']
['در طول ماه آوریل و دسامبر در والی فیودورونا نزدیک بیکر']
['من می خواهم در مورد شبکه اجتماعی تحقیقات علوم کامپیوتری را دن']
```
For more details, visit this page: https://github.com/persiannlp/parsinlu/
|
nickmuchi/deberta-v3-base-finetuned-finance-text-classification | nickmuchi | 2023-03-19T00:32:56Z | 401 | 18 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"financial-sentiment-analysis",
"sentiment-analysis",
"sentence_50agree",
"stocks",
"sentiment",
"finance",
"dataset:financial_phrasebank",
"dataset:Kaggle_Self_label",
"dataset:nickmuchi/financial-classification",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2022-05-29T16:29:22Z | ---
license: mit
tags:
- generated_from_trainer
- financial-sentiment-analysis
- sentiment-analysis
- sentence_50agree
- stocks
- sentiment
- finance
datasets:
- financial_phrasebank
- Kaggle_Self_label
- nickmuchi/financial-classification
widget:
- text: The USD rallied by 3% last night as the Fed hiked interest rates
example_title: Bullish Sentiment
- text: >-
Covid-19 cases have been increasing over the past few months impacting
earnings for global firms
example_title: Bearish Sentiment
- text: the USD has been trending lower
example_title: Mildly Bearish Sentiment
- text: >-
The USD rallied by 3% last night as the Fed hiked interest rates however,
higher interest rates will increase mortgage costs for homeowners
example_title: Neutral
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deberta-v3-base-finetuned-finance-text-classification
results: []
---
# deberta-v3-base-finetuned-finance-text-classification
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the sentence_50Agree [financial-phrasebank + Kaggle Dataset](https://huggingface.co/datasets/nickmuchi/financial-classification), a dataset consisting of 4840 Financial News categorised by sentiment (negative, neutral, positive). The Kaggle dataset includes Covid-19 sentiment data and can be found here: [sentiment-classification-selflabel-dataset](https://www.kaggle.com/percyzheng/sentiment-classification-selflabel-dataset).
It achieves the following results on the evaluation set:
- Loss: 0.7687
- Accuracy: 0.8913
- F1: 0.8912
- Precision: 0.8927
- Recall: 0.8913
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| No log | 1.0 | 285 | 0.4187 | 0.8399 | 0.8407 | 0.8687 | 0.8399 |
| 0.5002 | 2.0 | 570 | 0.3065 | 0.8755 | 0.8733 | 0.8781 | 0.8755 |
| 0.5002 | 3.0 | 855 | 0.4148 | 0.8775 | 0.8775 | 0.8778 | 0.8775 |
| 0.1937 | 4.0 | 1140 | 0.4249 | 0.8696 | 0.8699 | 0.8719 | 0.8696 |
| 0.1937 | 5.0 | 1425 | 0.5121 | 0.8834 | 0.8824 | 0.8831 | 0.8834 |
| 0.0917 | 6.0 | 1710 | 0.6113 | 0.8775 | 0.8779 | 0.8839 | 0.8775 |
| 0.0917 | 7.0 | 1995 | 0.7296 | 0.8775 | 0.8776 | 0.8793 | 0.8775 |
| 0.0473 | 8.0 | 2280 | 0.7034 | 0.8953 | 0.8942 | 0.8964 | 0.8953 |
| 0.0275 | 9.0 | 2565 | 0.6995 | 0.8834 | 0.8836 | 0.8846 | 0.8834 |
| 0.0275 | 10.0 | 2850 | 0.7736 | 0.8755 | 0.8755 | 0.8789 | 0.8755 |
| 0.0186 | 11.0 | 3135 | 0.7173 | 0.8814 | 0.8814 | 0.8840 | 0.8814 |
| 0.0186 | 12.0 | 3420 | 0.7659 | 0.8854 | 0.8852 | 0.8873 | 0.8854 |
| 0.0113 | 13.0 | 3705 | 0.8415 | 0.8854 | 0.8855 | 0.8907 | 0.8854 |
| 0.0113 | 14.0 | 3990 | 0.7577 | 0.8953 | 0.8951 | 0.8966 | 0.8953 |
| 0.0074 | 15.0 | 4275 | 0.7687 | 0.8913 | 0.8912 | 0.8927 | 0.8913 |
### Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1 |
huggingtweets/dolceragazza26-femdomfusion-mistressleiaa | huggingtweets | 2022-09-26T10:24:27Z | 401 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2022-09-26T10:23:11Z | ---
language: en
thumbnail: http://www.huggingtweets.com/dolceragazza26-femdomfusion-mistressleiaa/1664187862433/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1196458544947769345/S04dF85Y_400x400.jpg')">
</div>
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1548917860742729728/Kl_FyA-Y_400x400.jpg')">
</div>
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1574160039232868352/If7OL-Q-_400x400.jpg')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI CYBORG 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Femdom Fusion & 💞 M.Francesca ⛔️No porn🚫 & Mistress Leia</div>
<div style="text-align: center; font-size: 14px;">@dolceragazza26-femdomfusion-mistressleiaa</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Femdom Fusion & 💞 M.Francesca ⛔️No porn🚫 & Mistress Leia.
| Data | Femdom Fusion | 💞 M.Francesca ⛔️No porn🚫 | Mistress Leia |
| --- | --- | --- | --- |
| Tweets downloaded | 3248 | 3222 | 3249 |
| Retweets | 0 | 2204 | 663 |
| Short tweets | 355 | 168 | 367 |
| Tweets kept | 2893 | 850 | 2219 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3ov6jnnk/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @dolceragazza26-femdomfusion-mistressleiaa's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/15gbfzn2) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/15gbfzn2/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/dolceragazza26-femdomfusion-mistressleiaa')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
freemindcore/eanovnty-esmlvnty-0412-s8000-full | freemindcore | 2023-04-13T15:31:03Z | 401 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-04-11T18:00:35Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### EANOVNTY-ESMLVNTY-0412-s8000-full 8000 steps w/ learning rate 1e-6
|
lorahub/flan_t5_large-quartz_having_read_above_passage | lorahub | 2023-07-24T10:09:12Z | 401 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-07-24T10:09:02Z | ---
library_name: peft
---
|
digiplay/fantasticmix2.5D_v4.0 | digiplay | 2023-08-18T14:28:29Z | 401 | 2 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-08-10T19:22:54Z | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/20632?modelVersionId=137923
Sample images:
other samples:
https://huggingface.co/digiplay/fantasticmix2.5D_v4.0/discussions/2
|
databio/v2v-geo-hg38 | databio | 2024-02-12T19:02:01Z | 401 | 0 | null | [
"region:us"
]
| null | 2023-12-11T20:30:47Z | ---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Vec2Vec GEO hg38
## Model Details
### Model Description
This is a Vec2Vec model that encodes embedding vectors of natural language into embedding vectors of BED files. This model was trained with BED files and natural language metadata from [GEO](https://www.ncbi.nlm.nih.gov/geo/) data. The
embedding vectors of natural language were encoded by [sentence-transformers](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). The BED files were embedded by pretrained [Region2Vec](https://huggingface.co/databio/r2v-ChIP-atlas-hg38-v2)
- **Developed by:** Ziyang "Claude" Hu
- **Model type:** Vec2Vec
- **BED genotype:** hg38
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/databio/geniml
- **Paper [optional]:** N/A
## Uses
This model can be used to search BED files with natural language query strings. In the search interface, the query strings will be encoded by same sentence-transformers model, and the output vector will be
encoded into the final query vector by this Vec2Vec. The K BED files whose embedding vectors (embedded by same Region2Vec) are closest to the final query vector are results. It is limited to hg38. It is not
recommended to use this model for data with genotype outside of hg38
## How to Get Started with the Model
You can download and start encoding new genomic region data using the following code:
```python
from geniml.text2bednn import Vec2VecFNN
model = Vec2VecFNN("databio/v2v-geo-hg38")
```
[More Information Needed]
## Training Details
### Training Data
TODO |
TheBloke/WizardMath-7B-V1.1-GGUF | TheBloke | 2023-12-22T11:18:40Z | 401 | 7 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation",
"en",
"arxiv:2304.12244",
"arxiv:2306.08568",
"arxiv:2308.09583",
"base_model:WizardLM/WizardMath-7B-V1.1",
"license:other",
"text-generation-inference",
"region:us"
]
| text-generation | 2023-12-22T11:13:52Z | ---
base_model: WizardLM/WizardMath-7B-V1.1
inference: false
language:
- en
license: other
license_link: https://huggingface.co/WizardLM/WizardMath-7B-V1.1/resolve/main/LICENSE
license_name: microsoft-research-license
model_creator: WizardLM
model_name: WizardMath 7B V1.1
model_type: mistral
pipeline_tag: text-generation
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
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 -->
# WizardMath 7B V1.1 - GGUF
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- Original model: [WizardMath 7B V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [WizardLM's WizardMath 7B V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1).
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/WizardMath-7B-V1.1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF)
* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [wizardmath-7b-v1.1.Q2_K.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [wizardmath-7b-v1.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q3_K_S.gguf) | Q3_K_S | 3 | 3.17 GB| 5.67 GB | very small, high quality loss |
| [wizardmath-7b-v1.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [wizardmath-7b-v1.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [wizardmath-7b-v1.1.Q4_0.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [wizardmath-7b-v1.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [wizardmath-7b-v1.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [wizardmath-7b-v1.1.Q5_0.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [wizardmath-7b-v1.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [wizardmath-7b-v1.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [wizardmath-7b-v1.1.Q6_K.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [wizardmath-7b-v1.1.Q8_0.gguf](https://huggingface.co/TheBloke/WizardMath-7B-V1.1-GGUF/blob/main/wizardmath-7b-v1.1.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/WizardMath-7B-V1.1-GGUF and below it, a specific filename to download, such as: wizardmath-7b-v1.1.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/WizardMath-7B-V1.1-GGUF wizardmath-7b-v1.1.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/WizardMath-7B-V1.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/WizardMath-7B-V1.1-GGUF wizardmath-7b-v1.1.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 wizardmath-7b-v1.1.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./wizardmath-7b-v1.1.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(
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # 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="./wizardmath-7b-v1.1.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: WizardLM's WizardMath 7B V1.1
## WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct (RLEIF)
<p style="font-size:28px;" align="center">
🏠 <a href="https://wizardlm.github.io/" target="_blank">Home Page</a> </p>
<p align="center">
<p align="center">
🤗 <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> </p>
<p align="center">
📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> • 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> • 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
</p>
<p align="center">
👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
</p>
## News
[12/19/2023] 🔥 We released **WizardMath-7B-V1.1** trained from Mistral-7B, the **SOTA 7B math LLM**, achieves **83.2 pass@1** on GSM8k, and **33.0 pass@1** on MATH. Use this [[**Demo**](http://47.103.63.15:50083/)] to chat with it.
[12/19/2023] 🔥 **WizardMath-7B-V1.1** outperforms **ChatGPT 3.5**, **Gemini Pro**, **Mixtral MOE**, and **Claude Instant** on GSM8K pass@1.
[12/19/2023] 🔥 **WizardMath-7B-V1.1** is comparable with **ChatGPT 3.5**, **Gemini Pro**, and surpasses **Mixtral MOE** on MATH pass@1.
| Model | Checkpoint | Paper | GSM8k | MATH | Demo|
| ----- |------| ---- |------|-------|-------|
| **WizardMath-7B-V1.1** | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **83.2** | **33.0** |[[**Demo**](http://47.103.63.15:50083/)] |
| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** ||
| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** ||
| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | |
## [12/19/2023] Comparing WizardMath-7B-V1.1 with other open source 7B size math LLMs.
| Model | GSM8k Pass@1 | MATH Pass@1 |
| ----- |------| ---- |
| MPT-7B | 6.8 | 3.0 |
|Llama 1-7B | 11.0 | 2.9 |
|Llama 2-7B|12.3 |2.8 |
|Yi-6b| 32.6 |5.8 |
|Mistral-7B|37.8 |9.1 |
|Qwen-7b|47.8 |9.3 |
| RFT-7B | 50.3 | -- |
| MAmmoTH-7B (COT) | 50.5 | 10.4 |
| WizardMath-7B-V1.0 | 54.9 | 10.7 |
|Abel-7B-001 |59.7 |13 |
| MetaMath-7B | 66.5 | 19.8 |
| Arithmo-Mistral-7B | 74.7 | 25.3 |
|MetaMath-Mistral-7B|77.7 |28.2 |
|Abel-7B-002 | 80.4 | 29.5 |
| **WizardMath-7B-V1.1** | **83.2** | **33.0** |
## [12/19/2023] Comparing WizardMath-7B-V1.1 with large open source (30B~70B) LLMs.
| Model | GSM8k Pass@1 | MATH Pass@1 |
| ----- |------| ---- |
| Llemma-34B | 51.5 | 25.0 |
| Minerva-62B | 52.4 | 27.6 |
| Llama 2-70B | 56.8 | 13.5 |
| DeepSeek 67B | 63.4 | -- |
| Gork 33B | 62.9 | 23.9 |
| MAmmoTH-70B | 72.4 | 21.1 |
| Yi-34B | 67.9 | 15.9 |
| Mixtral 8x7B | 74.4 | 28.4 |
| MetaMath-70B | 82.3 | 26.6 |
| **WizardMath-7B-V1.1** | **83.2** | **33.0** |
## ❗ 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 GSM8k and MATH test set.
🔥
❗<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:"
```
**CoT Version:** （❗For the **simple** math questions, we do NOT recommend to use the CoT prompt.）
```
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."
```
## Inference WizardMath Demo Script
We provide the WizardMath inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).
## Citation
Please cite the repo if you use the data, method or code in this repo.
```
@article{luo2023wizardmath,
title={WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct},
author={Luo, Haipeng and Sun, Qingfeng and Xu, Can and Zhao, Pu and Lou, Jianguang and Tao, Chongyang and Geng, Xiubo and Lin, Qingwei and Chen, Shifeng and Zhang, Dongmei},
journal={arXiv preprint arXiv:2308.09583},
year={2023}
}
```
<!-- original-model-card end -->
|
tuphamdf/skincare-detection | tuphamdf | 2024-03-06T13:29:06Z | 401 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"vision",
"base_model:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2024-03-01T10:24:38Z | ---
license: apache-2.0
tags:
- generated_from_trainer
- image-classification
- vision
base_model: google/vit-base-patch16-224-in21k
metrics:
- accuracy
model-index:
- name: skincare-detection
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. -->
# skincare-detection
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4840
- Accuracy: 0.8648
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3961 | 0.99 | 61 | 0.5629 | 0.7725 |
| 0.4982 | 2.0 | 123 | 0.3991 | 0.8435 |
| 0.3563 | 2.99 | 184 | 0.4330 | 0.8272 |
| 0.2314 | 4.0 | 246 | 0.3969 | 0.8554 |
| 0.1815 | 4.99 | 307 | 0.4492 | 0.8435 |
| 0.1332 | 6.0 | 369 | 0.4474 | 0.8580 |
| 0.0869 | 6.99 | 430 | 0.4520 | 0.8631 |
| 0.0844 | 8.0 | 492 | 0.4469 | 0.8640 |
| 0.0681 | 8.99 | 553 | 0.4533 | 0.8717 |
| 0.0574 | 10.0 | 615 | 0.4952 | 0.8597 |
| 0.0477 | 10.99 | 676 | 0.4772 | 0.8674 |
| 0.0454 | 11.9 | 732 | 0.4840 | 0.8648 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.15.2
|
SuplexAI/FurWorld_HardFurry_Diffuser | SuplexAI | 2024-03-01T22:01:09Z | 401 | 1 | diffusers | [
"diffusers",
"safetensors",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2024-03-01T21:54:25Z | ---
license: creativeml-openrail-m
---
|
xDAN2099/APUS-xDAN-4.0-MoE-v2 | xDAN2099 | 2024-04-16T17:03:04Z | 401 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"en",
"zh",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| text-generation | 2024-04-02T16:24:14Z | ---
license: cc-by-4.0
language:
- en
- zh
---
Introduction
APUS-xDAN-4.0-MOE is a transformer-based decoder-only language model, developed on a vast corpus of data to ensure robust performance.
This is an enhanced MoE (Mixture of Experts) model built on top of the continued pre-training enhanced LlaMA architecture, further optimized with human-enhanced feedback algorithms to improve reasoning, mathematical, and logical capabilities during inference.
For more comprehensive information, please visit our blog post and GitHub repository. https://github.com/shootime2021/APUS-xDAN-4.0-moe
Model Details
APUS-xDAN-4.0-MOE leverages the innovative Mixture of Experts (MoE) architecture, incorporating components from dense language models. Specifically, it inherits its capabilities from the highly performant xDAN-L2 Series. With a total of 136 billion parameters, of which 30 billion are activated during runtime, APUS-xDAN-4.0-MOE demonstrates unparalleled efficiency. Through advanced quantization techniques, our open-source version occupies a mere 42GB, making it seamlessly compatible with consumer-grade GPUs like the 4090 and 3090. The following specifications:
Parameters: 136B
Architecture: Mixture of 4 Experts (MoE)
Experts Utilization: 2 experts used per token
Layers: 60
Attention Heads: 56 for queries, 8 for keys/values
Embedding Size: 7,168
Additional Features:
Rotary embeddings (RoPE)
Supports activation sharding and 1.5bit~4bit quantization
Maximum Sequence Length (context): 32,768 tokens |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.