modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
heegyu/gpt2-emotion | heegyu | "2023-03-19T08:03:17Z" | 2,731 | 1 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"en",
"dataset:emotion",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-01-25T04:07:01Z" | ---
license: mit
datasets:
- emotion
language:
- en
library_name: transformers
---
- **Developed by:** Heegyu Kim
- **Model type:** GPT-2
- **Language(s) (NLP):** English
- **License:** MIT
# Uses
```
from transformers import pipeline
generator = pipeline('text-generation', 'heegyu/gpt2-emotion')
prompt = "sadness I'm so " # start token should be one of ["sadness", "joy", "love", "anger", "fear", "surprise"]
print(generator(prompt)[0]['generated_text'])
>>> sadness I'm so tired of seeing all the stupid things that i ve learned from past years that i feel like ive been so stupid and blah and then i feel like ive just wasted all my energy doing stupid shit like how i never
``` |
TencentARC/t2iadapter_canny_sd15v2 | TencentARC | "2023-07-31T11:08:54Z" | 2,731 | 3 | diffusers | [
"diffusers",
"art",
"t2i-adapter",
"controlnet",
"stable-diffusion",
"image-to-image",
"arxiv:2302.08453",
"base_model:runwayml/stable-diffusion-v1-5",
"license:apache-2.0",
"region:us"
] | image-to-image | "2023-07-14T19:00:40Z" | ---
license: apache-2.0
base_model: runwayml/stable-diffusion-v1-5
tags:
- art
- t2i-adapter
- controlnet
- stable-diffusion
- image-to-image
---
# T2I Adapter - Canny
T2I Adapter is a network providing additional conditioning to stable diffusion. Each t2i checkpoint takes a different type of conditioning as input and is used with a specific base stable diffusion checkpoint.
This checkpoint provides conditioning on canny edge's for the stable diffusion 1.5 checkpoint.
## Model Details
- **Developed by:** T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** Apache 2.0
- **Resources for more information:** [GitHub Repository](https://github.com/TencentARC/T2I-Adapter), [Paper](https://arxiv.org/abs/2302.08453).
- **Cite as:**
@misc{
title={T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models},
author={Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie},
year={2023},
eprint={2302.08453},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
### Checkpoints
| Model Name | Control Image Overview| Control Image Example | Generated Image Example |
|---|---|---|---|
|[TencentARC/t2iadapter_color_sd14v1](https://huggingface.co/TencentARC/t2iadapter_color_sd14v1)<br/> *Trained with spatial color palette* | A image with 8x8 color palette.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"/></a>|
|[TencentARC/t2iadapter_canny_sd14v1](https://huggingface.co/TencentARC/t2iadapter_canny_sd14v1)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"/></a>|
|[TencentARC/t2iadapter_sketch_sd14v1](https://huggingface.co/TencentARC/t2iadapter_sketch_sd14v1)<br/> *Trained with [PidiNet](https://github.com/zhuoinoulu/pidinet) edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"/></a>|
|[TencentARC/t2iadapter_depth_sd14v1](https://huggingface.co/TencentARC/t2iadapter_depth_sd14v1)<br/> *Trained with Midas depth estimation* | A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"/></a>|
|[TencentARC/t2iadapter_openpose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_openpose_sd14v1)<br/> *Trained with OpenPose bone image* | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"/></a>|
|[TencentARC/t2iadapter_keypose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_keypose_sd14v1)<br/> *Trained with mmpose skeleton image* | A [mmpose skeleton](https://github.com/open-mmlab/mmpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"/></a>|
|[TencentARC/t2iadapter_seg_sd14v1](https://huggingface.co/TencentARC/t2iadapter_seg_sd14v1)<br/>*Trained with semantic segmentation* | An [custom](https://github.com/TencentARC/T2I-Adapter/discussions/25) segmentation protocol image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"/></a> |
|[TencentARC/t2iadapter_canny_sd15v2](https://huggingface.co/TencentARC/t2iadapter_canny_sd15v2)||
|[TencentARC/t2iadapter_depth_sd15v2](https://huggingface.co/TencentARC/t2iadapter_depth_sd15v2)||
|[TencentARC/t2iadapter_sketch_sd15v2](https://huggingface.co/TencentARC/t2iadapter_sketch_sd15v2)||
|[TencentARC/t2iadapter_zoedepth_sd15v1](https://huggingface.co/TencentARC/t2iadapter_zoedepth_sd15v1)||
## Example
1. Dependencies
```sh
pip install diffusers transformers opencv-contrib-python
```
2. Run code:
```python
import cv2
from PIL import Image
import torch
import numpy as np
from diffusers import T2IAdapter, StableDiffusionAdapterPipeline
image = Image.open('./images/canny_input.png')
image = np.array(image)
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = Image.fromarray(image)
image.save('./images/canny.png')
adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_canny_sd15v2", torch_dtype=torch.float16)
pipe = StableDiffusionAdapterPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
adapter=adapter,
torch_dtype=torch.float16,
)
pipe.to("cuda")
generator = torch.manual_seed(0)
out_image = pipe(
"a rabbit wearing glasses",
image=image,
generator=generator,
).images[0]
out_image.save('./images/canny_out.png')
```
 |
jb723/LLaMA2-en-ko-7B-model | jb723 | "2023-10-08T10:14:07Z" | 2,730 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-07T11:37:45Z" | 학습 데이터 : AIHUB 한국어 영어 병렬 corpus, KoAlpaca dataset, Alpacadataset |
openthaigpt/openthaigpt-1.0.0-7b-chat | openthaigpt | "2024-06-14T13:50:25Z" | 2,730 | 13 | transformers | [
"transformers",
"safetensors",
"gguf",
"llama",
"text-generation",
"openthaigpt",
"th",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T05:52:51Z" | ---
license: llama2
language:
- th
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- openthaigpt
- llama
---
# 🇹🇭 OpenThaiGPT 7b 1.0.0
[More Info](https://openthaigpt.aieat.or.th/)
🇹🇭 **OpenThaiGPT 7b Version 1.0.0** is an advanced 7-billion-parameter Thai language chat model based on LLaMA v2 released on April 8, 2024. It has been specifically fine-tuned for Thai instructions and enhanced by incorporating over 10,000 of the most commonly used Thai words into the large language model's (LLM) dictionary, significantly boosting its response speed.
## Highlights
- **Leading-edge Thai language LLM**, setting new benchmarks by achieving the highest average scores across several Thai language exams when compared to all other open-source Thai LLMs.
- **The First 70b Thai opensource LLM**, achieving the higher score on Thai exams than OpenAI GPT 3.5, Google Gemini, and Claude 3 Haiku.
- **Support for extended conversations** across multiple turns.
- Support the use case of **Retrieval Augmented Generation (RAG)** for enriched response generation.
- **Generation speeds increased by tenfold**, thanks to the addition of 10,000 frequently used Thai words to the model's dictionary.
- Pretrained upon a foundation of **more than 65 billion Thai language words** and meticulously fine-tuned with over 1 million Thai instruction examples.
- Capable of understanding and processing **input contexts of up to 4096 Thai words**, allowing for detailed and complex instructions.
## Benchmark by OpenThaiGPT Eval
** Please take a look at ``OTG 7b (April 2024)`` for this model's evaluation result.
| **Exams** | **OTG 7b (Aug 2023)** | **OTG 13b (Dec 2023)** | <b style="color:blue">OTG 7b (April 2024)</b> | **OTG 13b (April 2024)** | **OTG 70b (April 2024)** | **SeaLLM 7b v1** | **SeaLLM 7b v2** | **SeaLion 7b** | **WanchanGLM 7b** | **Sailor-7b-Chat** | **TyphoonGPT 7b Instruct** | **GPT3.5** | **GPT4** | **Gemini Pro** | **Gemini 1.5** | **Claude 3 Haiku** | **Claude 3 Sonnet** | **Claude 3 Opus** |
|----------------------------|-----------------------|------------------------|-------------------------|--------------------------|--------------------------|------------------|------------------|----------------|-------------------|--------------------|----------------------------|------------|----------|----------------|----------------|--------------------|---------------------|-------------------|
| **A-Level** | 17.50% | 34.17% | <b style="color:blue">25.00%</b> | 30.83% | 45.83% | 18.33% | 34.17% | 21.67% | 17.50% | 40.00% | 37.50% | 38.33% | 65.83% | 56.67% | 55.83% | 58.33% | 59.17% | 77.50% |
| **TGAT** | 24.00% | 22.00% | <b style="color:blue">22.00%</b> | 36.00% | 36.00% | 14.00% | 28.00% | 24.00% | 16.00% | 34.00% | 30.00% | 28.00% | 44.00% | 22.00% | 28.00% | 36.00% | 34.00% | 46.00% |
| **TPAT1** | 22.50% | 47.50% | <b style="color:blue">42.50%</b> | 27.50% | 62.50% | 22.50% | 27.50% | 22.50% | 17.50% | 40.00% | 47.50% | 45.00% | 52.50% | 52.50% | 50.00% | 52.50% | 50.00% | 62.50% |
| **thai_investment_consultant_exams** | 8.00% | 28.00% | <b style="color:blue">76.00%</b> | 84.00% | 68.00% | 16.00% | 28.00% | 24.00% | 16.00% | 24.00% | 32.00% | 40.00% | 64.00% | 52.00% | 32.00% | 44.00% | 64.00% | 72.00% |
| **facebook_beleble_tha_200** | 25.00% | 45.00% | <b style="color:blue">34.50%</b> | 39.50% | 70.00% | 13.50% | 51.00% | 27.00% | 24.50% | 63.00% | 51.50% | 50.00% | 72.50% | 65.00% | 74.00% | 63.50% | 77.00% | 90.00% |
| **xcopa_th_200** | 45.00% | 56.50% | <b style="color:blue">49.50%</b> | 51.50% | 74.50% | 26.50% | 47.00% | 51.50% | 48.50% | 68.50% | 65.00% | 64.00% | 82.00% | 68.00% | 74.00% | 64.00% | 80.00% | 86.00% |
| **xnli2.0_th_200** | 33.50% | 34.50% | <b style="color:blue">39.50%</b> | 31.00% | 47.00% | 21.00% | 43.00% | 37.50% | 33.50% | 16.00% | 20.00% | 50.00% | 69.00% | 53.00% | 54.50% | 50.00% | 68.00% | 68.50% |
| **ONET M3** | 17.85% | 38.86% | <b style="color:blue">34.11%</b> | 39.36% | 56.15% | 15.58% | 23.92% | 21.79% | 19.56% | 21.37% | 28.03% | 37.91% | 49.97% | 55.99% | 57.41% | 52.73% | 40.60% | 63.87% |
| **ONET M6** | 21.14% | 28.87% | <b style="color:blue">22.53%</b> | 23.32% | 42.85% | 15.09% | 19.48% | 16.96% | 20.67% | 28.64% | 27.46% | 34.44% | 46.29% | 45.53% | 50.23% | 34.79% | 38.49% | 48.56% |
| **AVERAGE SCORE** | 23.83% | 37.27% | <b style="color:blue;font-size:1.3em">38.40%</b> | 40.33% | 55.87% | 18.06% | 33.56% | 27.44% | 23.75% | 37.28% | 37.67% | 43.07% | 60.68% | 52.30% | 52.89% | 50.65% | 56.81% | 68.32% |
Thai language multiple choice exams, Test on unseen test sets, Zero-shot learning. Benchmark source code and exams information: https://github.com/OpenThaiGPT/openthaigpt_eval
(Updated on: 7 April 2024)
## Benchmark on M3Exam evaluated by an external party (Float16.cloud)
| **Models** | **ENGLISH (M3EXAM)** | **THAI (M3EXAM)** |
|---------------------|------------------|---------------|
| <b style="color:blue">OTG-7b</b> | <b style="color:blue">40.92 %</b> | <b style="color:blue">25.14 %</b> |
| OTG-13b | 53.69 % | 36.49 % |
| OTG-70b | 72.58 %< | 48.29 % |
| GPT-3.5-turbo-0613* | - | 34.1 % |
| GPT-4-0613* | - | 56.0 % |
More information: https://blog.float16.cloud/the-first-70b-thai-llm/
## Licenses
**Source Code**: License Apache Software License 2.0.<br>
**Weight**: Research and **Commercial uses**.<br>
## Sponsors
<img src="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/FDC9WYN2iykQbVW1rY4q5.png" width="600px">
## Supports
- Official website: https://openthaigpt.aieat.or.th
- Facebook page: https://web.facebook.com/groups/openthaigpt
- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
- E-mail: [email protected]
## Prompt Format
Prompt format is based on Llama2 with a small modification (Adding "###" to specify the context part)
```
<s>[INST] <<SYS>
{system_prompt}
<</SYS>>
{human_turn1}###{context_turn1} [/INST]{assistant_turn1}</s><s>{human_turn2}###{context_turn2} [/INST] ...
```
### System prompt:
```
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
```
### Examples
#### Single Turn Conversation Example
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]
```
#### Single Turn Conversation with Context (RAG) Example
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
กรุงเทพมีพื้นที่เท่าไร่###กรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน [/INST]
```
#### Multi Turn Conversation Example
##### First turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]
```
##### Second turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]
```
##### Third turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]ได้เลยค่ะ ส้มตำเป็นเมนูที่ทำง่ายและอร่อย มาเริ่มกันเลยนะคะ</s><s>เริ่มได้เลย [/INST]
```
##### Fourth turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]ได้เลยค่ะ ส้มตำเป็นเมนูที่ทำง่ายและอร่อย มาเริ่มกันเลยนะคะ</s><s>เริ่มได้เลย [/INST]
ตำไทยเป็นเมนูที่ใครๆ ก็คุ้นเคย ด้วยรสชาติที่กลมกล่อม หวาน เปรี้ยว เค็ม เผ็ด ครบรส วันนี้เราจะมาทำส้มตำด้วยกันค่ะ สิ่งแรกที่ต้องมีคือเครื่องปรุงดังนี้
- มะละกอดิบ 1 ลูก
- กุ้งแห้ง 1/2 ถ้วย
- กระเทียม 3 กลีบ
- พริกขี้หนู 3 เม็ด
- น้ำตาลปี๊บ 1 ช้อนโต๊ะ
- น้ำปลา 2 ช้อนโต๊ะ
- มะนาว 1 ลูก
- งาขาวคั่ว 1/4 ถ้วย
วิธีทำมีดังนี้ค่ะ
1. เริ่มจากล้างมะละกอให้สะอาด แล้วใช้มีดปอกเปลือก เอาไส้ออก หั่นเป็นเส้นบางๆ เตรียมไว้
2. ตำกุ้งแห้งให้ละเอียด แล้วตักขึ้นพักไว้
3. ใช้ครกหินหรือเครื่องปั่น บดพริกขี้หนูกับกระเทียมให้ละเอียด
4. ใส่กุ้งแห้งที่ตำแล้วลงไปผสม ตามด้วยน้ำตาลปี๊บ น้ำปลา มะนาว และเส้นมะละกอ คลุกเคล้าให้เข้ากัน
5. ชิมรสให้ได้รสหวาน เปรี้ยว เค็ม เผ็ด จากนั้นตักขึ้นเสิร์ฟพร้อมผักสด อาทิ กะหล่ำปลี ถั่วงอก แครอท ผักบุ้ง</s><s>ขอบคุณครับ [/INST]
```
#### Multi Turn Conversation with Context (RAG) Example
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
กรุงเทพมีพื้นที่เท่าไร่###กรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน [/INST]
กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม.</s><s>และประชากรล่ะ [/INST]
```
## How to use
### Huggingface
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Ensure CUDA is available
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Using device: {device}")
# Init Model
model_path="openthaigpt/openthaigpt-1.0.0-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.float16)
model.to(device)
# Prompt
prompt = "สวัสดีครับ OpenThaiGPT"
llama_prompt = f"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด<</SYS>>\n\n{prompt} [/INST]"
inputs = tokenizer.encode(llama_prompt, return_tensors="pt")
inputs = inputs.to(device)
# Generate
outputs = model.generate(inputs, max_length=512, num_return_sequences=1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
### vLLM
1. Install VLLM (https://github.com/vllm-project/vllm)
2. Run server
```bash
python -m vllm.entrypoints.api_server --model /path/to/model --tensor-parallel-size num_gpus
```
3. Run inference (CURL example)
```bash
curl --request POST \
--url http://localhost:8000/generate \
--header "Content-Type: application/json" \
--data '{"prompt": "<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด\n<</SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]","use_beam_search": false, "temperature": 0.1, "max_tokens": 512, "top_p": 0.75, "top_k": 40, "frequency_penalty": 0.3 "stop": "</s>"}'
```
### LlamaCPP (for GGUF)
1. Build and Install LlamaCPP (LLAMA_CUBLAS=1 is for GPU inference)
```bash
git clone https://github.com/ggerganov/llama.cpp.git \
&& cd llama.cpp \
&& make -j LLAMA_CUBLAS=1 CUDA_DOCKER_ARCH=all
```
2. Run server
```bash
./server -m /path/to/ggml-model-f16.gguf -c 3072 -ngl 81 -ts 1,1 --host 0.0.0.0
```
3. Run inference (CURL example)
```bash
curl --location 'http://localhost:8000/completion' \
--header 'Content-Type: application/json' \
--data '{
"prompt":"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด friendly\n\n<<SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]",
"max_tokens": 512,
"stop":"</s>"
}'
```
### Ollama
There are two ways to run on ollama
1. From this repo Modelfile and 4 bit quantized gguf
```bash
ollama create -f ./Modelfile
```
2. From Ollama CLI
```bash
ollama run pacozaa/openthaigpt
```
### GPU Memory Requirements
| **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
|------------------|----------------|------------------------|------------------------|---------------------------------------------|
| **7b** | 24 GB | 12 GB | 6 GB | Nvidia RTX 4060 8GB |
| **13b** | 48 GB | 24 GB | 12 GB | Nvidia RTX 4070 16GB |
| **70b** | 192 GB | 96 GB | 48 GB | Nvidia RTX 4090 24GB x 2 cards |
### Authors
* Kobkrit Viriyayudhakorn ([email protected])
* Sumeth Yuenyong ([email protected])
* Thaweewat Rugsujarit ([email protected])
* Jillaphat Jaroenkantasima ([email protected])
* Norapat Buppodom ([email protected])
* Koravich Sangkaew ([email protected])
* Peerawat Rojratchadakorn ([email protected])
* Surapon Nonesung ([email protected])
* Chanon Utupon ([email protected])
* Sadhis Wongprayoon ([email protected])
* Nucharee Thongthungwong ([email protected])
* Chawakorn Phiantham ([email protected])
* Patteera Triamamornwooth ([email protected])
* Nattarika Juntarapaoraya ([email protected])
* Kriangkrai Saetan ([email protected])
* Pitikorn Khlaisamniang ([email protected])
<i>Disclaimer: Provided responses are not guaranteed.</i> |
mradermacher/L3-8B-BlueSerpentine-GGUF | mradermacher | "2024-06-13T12:08:40Z" | 2,730 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama",
"not-for-all-audiences",
"en",
"base_model:v000000/L3-8B-BlueSerpentine",
"endpoints_compatible",
"region:us"
] | null | "2024-06-13T09:54:41Z" | ---
base_model: v000000/L3-8B-BlueSerpentine
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
- llama
- not-for-all-audiences
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/v000000/L3-8B-BlueSerpentine
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-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/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-BlueSerpentine-GGUF/resolve/main/L3-8B-BlueSerpentine.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 -->
|
mradermacher/Hercules-Stheno-v1-GGUF | mradermacher | "2024-06-18T01:15:15Z" | 2,730 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:lik07/Hercules-Stheno-v1",
"endpoints_compatible",
"region:us"
] | null | "2024-06-18T00:05:59Z" | ---
base_model: lik07/Hercules-Stheno-v1
language:
- en
library_name: transformers
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/lik07/Hercules-Stheno-v1
<!-- 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/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Hercules-Stheno-v1-GGUF/resolve/main/Hercules-Stheno-v1.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 -->
|
RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf | RichardErkhov | "2024-06-29T13:50:01Z" | 2,730 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-29T13:12:18Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
TinyLlama-1.1bee - GGUF
- Model creator: https://huggingface.co/BEE-spoke-data/
- Original model: https://huggingface.co/BEE-spoke-data/TinyLlama-1.1bee/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [TinyLlama-1.1bee.Q2_K.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q2_K.gguf) | Q2_K | 0.4GB |
| [TinyLlama-1.1bee.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [TinyLlama-1.1bee.IQ3_S.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.IQ3_S.gguf) | IQ3_S | 0.47GB |
| [TinyLlama-1.1bee.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
| [TinyLlama-1.1bee.IQ3_M.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [TinyLlama-1.1bee.Q3_K.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q3_K.gguf) | Q3_K | 0.51GB |
| [TinyLlama-1.1bee.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [TinyLlama-1.1bee.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [TinyLlama-1.1bee.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
| [TinyLlama-1.1bee.Q4_0.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q4_0.gguf) | Q4_0 | 0.59GB |
| [TinyLlama-1.1bee.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
| [TinyLlama-1.1bee.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
| [TinyLlama-1.1bee.Q4_K.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q4_K.gguf) | Q4_K | 0.62GB |
| [TinyLlama-1.1bee.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
| [TinyLlama-1.1bee.Q4_1.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q4_1.gguf) | Q4_1 | 0.65GB |
| [TinyLlama-1.1bee.Q5_0.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q5_0.gguf) | Q5_0 | 0.71GB |
| [TinyLlama-1.1bee.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
| [TinyLlama-1.1bee.Q5_K.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q5_K.gguf) | Q5_K | 0.73GB |
| [TinyLlama-1.1bee.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
| [TinyLlama-1.1bee.Q5_1.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q5_1.gguf) | Q5_1 | 0.77GB |
| [TinyLlama-1.1bee.Q6_K.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q6_K.gguf) | Q6_K | 0.84GB |
| [TinyLlama-1.1bee.Q8_0.gguf](https://huggingface.co/RichardErkhov/BEE-spoke-data_-_TinyLlama-1.1bee-gguf/blob/main/TinyLlama-1.1bee.Q8_0.gguf) | Q8_0 | 1.09GB |
Original model description:
---
license: apache-2.0
base_model: PY007/TinyLlama-1.1B-intermediate-step-240k-503b
tags:
- bees
- beekeeping
- honey
metrics:
- accuracy
inference:
parameters:
max_new_tokens: 64
do_sample: true
renormalize_logits: true
repetition_penalty: 1.05
no_repeat_ngram_size: 6
temperature: 0.9
top_p: 0.95
epsilon_cutoff: 0.0008
widget:
- text: In beekeeping, the term "queen excluder" refers to
example_title: Queen Excluder
- text: One way to encourage a honey bee colony to produce more honey is by
example_title: Increasing Honey Production
- text: The lifecycle of a worker bee consists of several stages, starting with
example_title: Lifecycle of a Worker Bee
- text: Varroa destructor is a type of mite that
example_title: Varroa Destructor
- text: In the world of beekeeping, the acronym PPE stands for
example_title: Beekeeping PPE
- text: The term "robbing" in beekeeping refers to the act of
example_title: Robbing in Beekeeping
- text: |-
Question: What's the primary function of drone bees in a hive?
Answer:
example_title: Role of Drone Bees
- text: To harvest honey from a hive, beekeepers often use a device known as a
example_title: Honey Harvesting Device
- text: >-
Problem: You have a hive that produces 60 pounds of honey per year. You
decide to split the hive into two. Assuming each hive now produces at a 70%
rate compared to before, how much honey will you get from both hives next
year?
To calculate
example_title: Beekeeping Math Problem
- text: In beekeeping, "swarming" is the process where
example_title: Swarming
pipeline_tag: text-generation
datasets:
- BEE-spoke-data/bees-internal
language:
- en
---
# TinyLlama-1.1bee 🐝
As we feverishly hit the refresh button on hf.co's homepage, on the hunt for the newest waifu chatbot to grace the AI stage, an epiphany struck us like a bee sting. What could we offer to the hive-mind of the community? The answer was as clear as honey—beekeeping, naturally. And thus, this un-bee-lievable model was born.
## Details
This model is a fine-tuned version of [PY007/TinyLlama-1.1B-intermediate-step-240k-503b](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-240k-503b) on the `BEE-spoke-data/bees-internal` dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4285
- Accuracy: 0.4969
```
***** eval metrics *****
eval_accuracy = 0.4972
eval_loss = 2.4283
eval_runtime = 0:00:53.12
eval_samples = 239
eval_samples_per_second = 4.499
eval_steps_per_second = 1.129
perplexity = 11.3391
```
## 📜 Intended Uses & Limitations 📜
### Intended Uses:
1. **Educational Engagement**: Whether you're a novice beekeeper, an enthusiast, or someone just looking to understand the buzz around bees, this model aims to serve as an informative and entertaining resource.
2. **General Queries**: Have questions about hive management, bee species, or honey extraction? Feel free to consult the model for general insights.
3. **Academic & Research Inspiration**: If you're diving into the world of apiculture studies or environmental science, our model could offer some preliminary insights and ideas.
### Limitations:
1. **Not a Beekeeping Expert**: As much as we admire bees and their hard work, this model is not a certified apiculturist. Please consult professional beekeeping resources or experts for serious decisions related to hive management, bee health, and honey production.
2. **Licensing**: Apache-2.0, following TinyLlama
3. **Infallibility**: Our model can err, just like any other piece of technology (or bee). Always double-check the information before applying it to your own hive or research.
4. **Ethical Constraints**: This model may not be used for any illegal or unethical activities, including but not limited to: bioterrorism & standard terrorism, harassment, or spreading disinformation.
## Training and evaluation data
While the full dataset is not yet complete and therefore not yet released for "safety reasons", you can check out a preliminary sample at: [bees-v0](https://huggingface.co/datasets/BEE-spoke-data/bees-v0)
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 80085
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2.0
# [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_BEE-spoke-data__TinyLlama-1.1bee)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 29.15 |
| ARC (25-shot) | 30.55 |
| HellaSwag (10-shot) | 51.8 |
| MMLU (5-shot) | 24.25 |
| TruthfulQA (0-shot) | 39.01 |
| Winogrande (5-shot) | 54.46 |
| GSM8K (5-shot) | 0.23 |
| DROP (3-shot) | 3.74 |
|
datnguyen-dbs/Phi-3-mini-4k-instruct_q5_k_m_gguf | datnguyen-dbs | "2024-06-26T03:35:30Z" | 2,729 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | "2024-06-26T02:59:57Z" | Entry not found |
mradermacher/llama-3-fantasy-writer-8b-GGUF | mradermacher | "2024-06-15T19:17:23Z" | 2,727 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:maldv/llama-3-fantasy-writer-8b",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-15T16:55:41Z" | ---
base_model: maldv/llama-3-fantasy-writer-8b
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/maldv/llama-3-fantasy-writer-8b
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/llama-3-fantasy-writer-8b-GGUF/resolve/main/llama-3-fantasy-writer-8b.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
easybits/ProteusV0.2.fp16 | easybits | "2024-03-21T12:43:36Z" | 2,726 | 1 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-02-19T08:08:02Z" | ---
pipeline_tag: text-to-image
widget:
- text: >-
black fluffy gorgeous dangerous cat animal creature, large orange eyes, big
fluffy ears, piercing gaze, full moon, dark ambiance, best quality,
extremely detailed
- text: >-
(impressionistic realism by csybgh), a 50 something male, working in
banking, very short dyed dark curly balding hair, Afro-Asiatic ancestry,
talks a lot but listens poorly, stuck in the past, wearing a suit, he has a
certain charm, bronze skintone, sitting in a bar at night, he is smoking and
feeling cool, drunk on plum wine, masterpiece, 8k, hyper detailed, smokey
ambiance, perfect hands AND fingers
- text: >-
high quality pixel art, a pixel art silhouette of an anime space-themed girl
in a space-punk steampunk style, lying in her bed by the window of a
spaceship, smoking, with a rustic feel. The image should embody epic
portraiture and double exposure, featuring an isolated landscape visible
through the window. The colors should primarily be dynamic and
action-packed, with a strong use of negative space. The entire artwork
should be in pixel art style, emphasizing the characters shape and set
against a white background. Silhouette
- text: >-
The image features an older man, a long white beard and mustache, He has a
stern expression, giving the impression of a wise and experienced
individual. The mans beard and mustache are prominent, adding to his
distinguished appearance. The close-up shot of the mans face emphasizes his
facial features and the intensity of his gaze.
- text: >-
Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass
flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green
used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty,
noisy, Vintage monk style, very detailed, hd
- text: >-
cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An
Oscar winning movie for Best Cinematography a woman in a kimono standing on
a subway train in Japan Kodak Motion Picture Film Style, shallow depth of
field, vignette, highly detailed, high budget, bokeh, cinemascope, moody,
epic, gorgeous, film grain, grainy
- text: >-
in the style of artgerm, comic style,3D model, mythical seascape, negative
space, space quixotic dreams, temporal hallucination, psychedelic, mystical,
intricate details, very bright neon colors, (vantablack background:1.5),
pointillism, pareidolia, melting, symbolism, very high contrast, chiaroscuro
parameters:
negative_prompt: >-
bad quality, bad anatomy, worst quality, low quality, low resolutions,
extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image
artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- text: >-
1980s anime portrait of a character glitching. His face is separated from
his body by heavy static. His face is deformed by pain. Dream-like, analog
horror, glitch, terrifying
- text: (("Proteus"):text_logo:1)
- text: >-
dan seagrave, dante, Abandon All Hope, Ye Who Enter Here, hell religious art
purgatory zdzislaw Beksinski, abyss inferno, lost, wanderer
license: gpl-3.0
---
<Gallery />
## fp16 Fork of [dataautogpt3/ProteusV0.2](https://huggingface.co/dataautogpt3/ProteusV0.2)
merged with RealCartoonXL to fix issues with inability to understand tags related to anime or cartoon styles at just a weight of 0.5% out of 100% using custom scripts with slerp like methods.
Version 0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.
## Proteus
Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its core functionalities to deliver superior outcomes. Key areas of advancement include heightened responsiveness to prompts and augmented creative capacities. To achieve this, it was fine-tuned using approximately 220,000 GPTV captioned images from copyright-free stock images (with some anime included), which were then normalized. Additionally, DPO (Direct Preference Optimization) was employed through a collection of 10,000 carefully selected high-quality, AI-generated image pairs.
In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.
## Settings for ProteusV0.2
Use these settings for the best results with ProteusV0.2:
CFG Scale: Use a CFG scale of 8 to 7
Steps: 20 to 60 steps for more detail, 20 steps for faster results.
Sampler: DPM++ 2M SDE
Scheduler: Karras
Resolution: 1280x1280 or 1024x1024
please also consider using these keep words to improve your prompts:
best quality, HD, `~*~aesthetic~*~`.
if you are having trouble coming up with prompts you can use this GPT I put together to help you refine the prompt. https://chat.openai.com/g/g-RziQNoydR-diffusion-master
## Use it with 🧨 diffusers
```python
import torch
from diffusers import (
StableDiffusionXLPipeline,
KDPM2AncestralDiscreteScheduler,
AutoencoderKL
)
# Load VAE component
vae = AutoencoderKL.from_pretrained(
"madebyollin/sdxl-vae-fp16-fix",
torch_dtype=torch.float16
)
# Configure the pipeline
pipe = StableDiffusionXLPipeline.from_pretrained(
"dataautogpt3/ProteusV0.2",
vae=vae,
torch_dtype=torch.float16
)
pipe.scheduler = KDPM2AncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')
# Define prompts and generate image
prompt = "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"
negative_prompt = "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"
image = pipe(
prompt,
negative_prompt=negative_prompt,
width=1024,
height=1024,
guidance_scale=7,
num_inference_steps=20
).images[0]
```
please support the work I do through donating to me on:
https://www.buymeacoffee.com/DataVoid
or following me on
https://twitter.com/DataPlusEngine |
Artples/L-MChat-Small | Artples | "2024-06-27T17:36:55Z" | 2,726 | 1 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:rhysjones/phi-2-orange-v2",
"base_model:Weyaxi/Einstein-v4-phi2",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-11T14:39:17Z" | ---
license: mit
library_name: transformers
tags:
- mergekit
- merge
base_model:
- rhysjones/phi-2-orange-v2
- Weyaxi/Einstein-v4-phi2
model-index:
- name: L-MChat-Small
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: 61.6
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
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: 75.9
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
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: 57.41
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
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: 49.94
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
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: 74.98
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
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: 58.98
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
name: Open LLM Leaderboard
---
## L-MChat-Small
<div style="text-align:center;width:250px;height:250px;">
<img src="https://priority.cdn.l-eu.com/logo-l-mchat-rs.png" alt="L-MChat-Series-Logo"">
</div>
This was a test of mine how small merges perform, because there are a lot of 7b merges and higher but not a lot of 2b merges.
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [rhysjones/phi-2-orange-v2](https://huggingface.co/rhysjones/phi-2-orange-v2)
* [Weyaxi/Einstein-v4-phi2](https://huggingface.co/Weyaxi/Einstein-v4-phi2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: Weyaxi/Einstein-v4-phi2
layer_range:
- 0
- 32
- model: rhysjones/phi-2-orange-v2
layer_range:
- 0
- 32
merge_method: slerp
base_model: rhysjones/phi-2-orange-v2
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
Use it with the ChatML format, you can also use the Inference-API for this Model.
# [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_Artples__L-MChat-Small)
| Metric |Value|
|---------------------------------|----:|
|Avg. |63.14|
|AI2 Reasoning Challenge (25-Shot)|61.60|
|HellaSwag (10-Shot) |75.90|
|MMLU (5-Shot) |57.41|
|TruthfulQA (0-shot) |49.94|
|Winogrande (5-shot) |74.98|
|GSM8k (5-shot) |58.98|
|
Yntec/GoFish | Yntec | "2024-01-10T01:55:57Z" | 2,724 | 3 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Art Style",
"Illustration",
"timevisitor",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-01-10T00:46:41Z" | ---
license: other
tags:
- Anime
- Art Style
- Illustration
- timevisitor
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# Go Fish
A mix of GimmeDatDing and FishMix 1.1!
Samples and prompts:
(Click for larger)
Top left: little videogames, robert jordan pepperoni pizza, josephine wall winner, hidari, roll20 illumination, radiant light, sitting elementary girl, Pretty CUTE, gorgeous hair, DETAILED CHIBI EYES, Magazine ad, iconic, 1943, Cartoon, sharp focus, cherries, watched towel. art on canvas by kyoani and ROSSDRAWS. 4k
Top right: highquality, masterpiece, 1girl, Chi-Chi, :D, close up, smile, arms up, pink helmet, black hair, black eyes, blush, bikini armor, aqua cape, pink gloves, pink boots, cleavage. cave, rock, mountain. blue collar
Bottom left: manga art, muted colors, detailed painting, halftone dithering, cute little girl with shoulderlength black bobcut in baggy black clothes, disney cape, beautiful eyes, complex background
Bottom right: Pretty Cute Little Girl, masterpiece, sitting, Detailed Chibi Blue Eyes, books, beautiful detailed room, gorgeous detailed golden hair, lab shoes. Magazine ad, iconic, 1943, from the movie, sharp focus. visible brushstrokes by Clay Mann and Kyoani
Original pages:
https://civitai.com/models/14978?modelVersionId=22052
https://huggingface.co/Yntec/GimmeDatDing
# Recipe:
- SuperMerger Weight Sum Train Difference MBW 1,0,0,0,0,0,0,1,1,1,0,1,1,0,0,0,1,1,1,1,0,0,0,1,1,1
Model A:
GimmeDatDing
Model B:
OldFish 1.1
Output:
GoFish |
google/paligemma-3b-pt-448 | google | "2024-06-27T14:10:08Z" | 2,723 | 17 | transformers | [
"transformers",
"safetensors",
"paligemma",
"pretraining",
"image-text-to-text",
"arxiv:2310.09199",
"arxiv:2303.15343",
"arxiv:2403.08295",
"arxiv:1706.03762",
"arxiv:2010.11929",
"arxiv:2209.06794",
"arxiv:2209.04372",
"arxiv:2103.01913",
"arxiv:2205.12522",
"arxiv:2110.11624",
"arxiv:2108.03353",
"arxiv:2010.04295",
"arxiv:2401.06209",
"arxiv:2305.10355",
"arxiv:2203.10244",
"arxiv:1810.12440",
"arxiv:1905.13648",
"arxiv:1608.00272",
"arxiv:1908.04913",
"license:gemma",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | image-text-to-text | "2024-05-13T00:39:57Z" | ---
library_name: transformers
license: gemma
pipeline_tag: image-text-to-text
extra_gated_heading: Access PaliGemma on Hugging Face
extra_gated_prompt: To access PaliGemma on Hugging Face, you’re required to review
and agree to Google’s usage license. To do this, please ensure you’re logged-in
to Hugging Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
---
# PaliGemma model card
**Model page:** [PaliGemma](https://ai.google.dev/gemma/docs/paligemma)
Transformers PaliGemma 3B weights, pre-trained with 448*448 input images and 512 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
**Resources and technical documentation:**
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [PaliGemma on Kaggle](https://www.kaggle.com/models/google/paligemma)
* [PaliGemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/363)
**Terms of Use:** [Terms](https://www.kaggle.com/models/google/paligemma/license/consent/verify/huggingface?returnModelRepoId=google/paligemma-3b-pt-448)
**Authors:** Google
## Model information
### Model summary
#### Description
PaliGemma is a versatile and lightweight vision-language model (VLM) inspired by
[PaLI-3](https://arxiv.org/abs/2310.09199) and based on open components such as
the [SigLIP vision model](https://arxiv.org/abs/2303.15343) and the [Gemma
language model](https://arxiv.org/abs/2403.08295). It takes both image and text
as input and generates text as output, supporting multiple languages. It is designed for class-leading fine-tune performance on a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation.
#### Model architecture
PaliGemma is the composition of a [Transformer
decoder](https://arxiv.org/abs/1706.03762) and a [Vision Transformer image
encoder](https://arxiv.org/abs/2010.11929), with a total of 3 billion
params. The text decoder is initialized from
[Gemma-2B](https://www.kaggle.com/models/google/gemma). The image encoder is
initialized from
[SigLIP-So400m/14](https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb).
PaliGemma is trained following the PaLI-3 recipes.
#### Inputs and outputs
* **Input:** Image and text string, such as a prompt to caption the image, or
a question.
* **Output:** Generated text in response to the input, such as a caption of
the image, an answer to a question, a list of object bounding box
coordinates, or segmentation codewords.
### Model data
#### Pre-train datasets
PaliGemma is pre-trained on the following mixture of datasets:
* **WebLI:** [WebLI (Web Language Image)](https://arxiv.org/abs/2209.06794) is
a web-scale multilingual image-text dataset built from the public web. A
wide range of WebLI splits are used to acquire versatile model capabilities,
such as visual semantic understanding, object localization,
visually-situated text understanding, multilinguality, etc.
* **CC3M-35L:** Curated English image-alt_text pairs from webpages ([Sharma et
al., 2018](https://aclanthology.org/P18-1238/)). We used the [Google Cloud
Translation API](https://cloud.google.com/translate) to translate into 34
additional languages.
* **VQ²A-CC3M-35L/VQG-CC3M-35L:** A subset of VQ2A-CC3M ([Changpinyo et al.,
2022a](https://aclanthology.org/2022.naacl-main.142/)), translated into the
same additional 34 languages as CC3M-35L, using the [Google Cloud
Translation API](https://cloud.google.com/translate).
* **OpenImages:** Detection and object-aware questions and answers
([Piergiovanni et al. 2022](https://arxiv.org/abs/2209.04372)) generated by
handcrafted rules on the [OpenImages dataset].
* **WIT:** Images and texts collected from Wikipedia ([Srinivasan et al.,
2021](https://arxiv.org/abs/2103.01913)).
[OpenImages dataset]: https://storage.googleapis.com/openimages/web/factsfigures_v7.html
#### Data responsibility filtering
The following filters are applied to WebLI, with the goal of training PaliGemma
on clean data:
* **Pornographic image filtering:** This filter removes images deemed to be of
pornographic nature.
* **Text safety filtering:** We identify and filter out images that are paired
with unsafe text. Unsafe text is any text deemed to contain or be about
CSAI, pornography, vulgarities, or otherwise offensive.
* **Text toxicity filtering:** We further use the [Perspective
API](https://perspectiveapi.com/) to identify and filter out images that are
paired with text deemed insulting, obscene, hateful or otherwise toxic.
* **Text personal information filtering:** We filtered certain personal information and other sensitive data using [Cloud Data Loss Prevention (DLP)
API](https://cloud.google.com/security/products/dlp) to protect the privacy
of individuals. Identifiers such as social security numbers and [other sensitive information types] were removed.
* **Additional methods:** Filtering based on content quality and safety in
line with our policies and practices.
[other sensitive information types]: https://cloud.google.com/sensitive-data-protection/docs/high-sensitivity-infotypes-reference?_gl=1*jg604m*_ga*ODk5MzA3ODQyLjE3MTAzMzQ3NTk.*_ga_WH2QY8WWF5*MTcxMDUxNTkxMS4yLjEuMTcxMDUxNjA2NC4wLjAuMA..&_ga=2.172110058.-899307842.1710334759
## How to Use
PaliGemma is a single-turn vision language model not meant for conversational use,
and it works best when fine-tuning to a specific use case.
You can configure which task the model will solve by conditioning it with task prefixes,
such as “detect” or “segment”. The pretrained models were trained in this fashion to imbue
them with a rich set of capabilities (question answering, captioning, segmentation, etc.).
However, they are not designed to be used directly, but to be transferred (by fine-tuning)
to specific tasks using a similar prompt structure. For interactive testing, you can use
the "mix" family of models, which have been fine-tuned on a mixture of tasks. To see model
[google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) in action,
check [this Space that uses the Transformers codebase](https://huggingface.co/spaces/big-vision/paligemma-hf).
Please, refer to the [usage and limitations section](#usage-and-limitations) for intended
use cases, or visit the [blog post](https://huggingface.co/blog/paligemma-google-vlm) for
additional details and examples.
## Use in Transformers
The following snippets use model `google/paligemma-3b-mix-224` for reference purposes.
The model in this repo you are now browsing may have been trained for other tasks, please
make sure you use appropriate inputs for the task at hand.
### Running the default precision (`float32`) on CPU
```python
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/paligemma-3b-mix-224"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id).eval()
processor = AutoProcessor.from_pretrained(model_id)
# Instruct the model to create a caption in Spanish
prompt = "caption es"
model_inputs = processor(text=prompt, images=image, return_tensors="pt")
input_len = model_inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
```
Output: `Un auto azul estacionado frente a un edificio.`
### Running other precisions on CUDA
For convenience, the repos contain revisions of the weights already converted to `bfloat16` and `float16`,
so you can use them to reduce the download size and avoid casting on your local computer.
This is how you'd run `bfloat16` on an nvidia CUDA card.
```python
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/paligemma-3b-mix-224"
device = "cuda:0"
dtype = torch.bfloat16
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
model = PaliGemmaForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=dtype,
device_map=device,
revision="bfloat16",
).eval()
processor = AutoProcessor.from_pretrained(model_id)
# Instruct the model to create a caption in Spanish
prompt = "caption es"
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
input_len = model_inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
```
### Loading in 4-bit / 8-bit
You need to install `bitsandbytes` to automatically run inference using 8-bit or 4-bit precision:
```
pip install bitsandbytes accelerate
```
```
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/paligemma-3b-mix-224"
device = "cuda:0"
dtype = torch.bfloat16
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
model = PaliGemmaForConditionalGeneration.from_pretrained(
model_id, quantization_config=quantization_config
).eval()
processor = AutoProcessor.from_pretrained(model_id)
# Instruct the model to create a caption in Spanish
prompt = "caption es"
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
input_len = model_inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
```
## Implementation information
### Hardware
PaliGemma was trained using the latest generation of Tensor Processing Unit
(TPU) hardware (TPUv5e).
### Software
Training was done using [JAX](https://github.com/google/jax),
[Flax](https://github.com/google/flax),
[TFDS](https://github.com/tensorflow/datasets) and
[`big_vision`](https://github.com/google-research/big_vision).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
TFDS is used to access datasets and Flax is used for model architecture. The
PaliGemma fine-tune code and inference code are released in the `big_vision`
GitHub repository.
## Evaluation information
### Benchmark results
In order to verify the transferability of PaliGemma to a wide variety of
academic tasks, we fine-tune the pretrained models on each task. Additionally we
train the mix model with a mixture of the transfer tasks. We report results on
different resolutions to provide an impression of which tasks benefit from
increased resolution. Importantly, none of these tasks or datasets are part of
the pretraining data mixture, and their images are explicitly removed from the
web-scale pre-training data.
#### Single task (fine-tune on single task)
<table>
<tbody><tr>
<th>Benchmark<br>(train split)</th>
<th>Metric<br>(split)</th>
<th>pt-224</th>
<th>pt-448</th>
<th>pt-896</th>
</tr>
<tr>
<th>Captioning</th>
</tr>
<tr>
<td>
<a href="https://cocodataset.org/#home">COCO captions</a><br>(train+restval)
</td>
<td>CIDEr (val)</td>
<td>141.92</td>
<td>144.60</td>
</tr>
<tr>
<td>
<a href="https://nocaps.org/">NoCaps</a><br>(Eval of COCO<br>captions transfer)
</td>
<td>CIDEr (val)</td>
<td>121.72</td>
<td>123.58</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">COCO-35L</a><br>(train)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
139.2<br>
115.8<br>
116.4
</td>
<td>
141.2<br>
118.0<br>
118.6
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">XM3600</a><br>(Eval of COCO-35L transfer)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
78.1<br>
41.3<br>
42.4
</td>
<td>
80.0<br>
41.9<br>
42.9
</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/textcaps/">TextCaps</a><br>(train)
</td>
<td>CIDEr (val)</td>
<td>127.48</td>
<td>153.94</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2110.11624">SciCap</a><br>(first sentence, no subfigure)<br>(train+val)
</td>
<td>CIDEr/BLEU-4<br>(test)</td>
<td>
162.25<br>
0.192<br>
</td>
<td>
181.49<br>
0.211<br>
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2108.03353">Screen2words</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>117.57</td>
<td>119.59</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2010.04295">Widget Captioning</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>136.07</td>
<td>148.36</td>
</tr>
<tr>
<th>Question answering</th>
</tr>
<tr>
<td>
<a href="https://visualqa.org/index.html">VQAv2</a><br>(train+validation)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>83.19</td>
<td>85.64</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2401.06209">MMVP</a><br>(Eval of VQAv2 transfer)
</td>
<td>Paired Accuracy</td>
<td>47.33</td>
<td>45.33</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2305.10355">POPE</a><br>(Eval of VQAv2 transfer)
</td>
<td>Accuracy<br>(random/popular/<br>adversarial)</td>
<td>
87.80<br>
85.87<br>
84.27
</td>
<td>
88.23<br>
86.77<br>
85.90
</td>
</tr>
<tr>
<td>
<a href="https://okvqa.allenai.org/">OKVQA</a><br>(train)
</td>
<td>Accuracy (val)</td>
<td>63.54</td>
<td>63.15</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (MC)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>76.37</td>
<td>76.90</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (DA)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>61.85</td>
<td>63.22</td>
</tr>
<tr>
<td>
<a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a><br>(train_balanced+<br>val_balanced)
</td>
<td>Accuracy<br>(testdev balanced)</td>
<td>65.61</td>
<td>67.03</td>
</tr>
<tr>
<td>
<a href="https://aclanthology.org/2022.findings-acl.196/">xGQA</a><br>(Eval of GQA transfer)
</td>
<td>Mean Accuracy<br>(bn, de, en, id,<br>ko, pt, ru, zh)</td>
<td>58.37</td>
<td>59.07</td>
</tr>
<tr>
<td>
<a href="https://lil.nlp.cornell.edu/nlvr/">NLVR2</a><br>(train+dev)
</td>
<td>Accuracy (test)</td>
<td>90.02</td>
<td>88.93</td>
</tr>
<tr>
<td>
<a href="https://marvl-challenge.github.io/">MaRVL</a><br>(Eval of NLVR2 transfer)
</td>
<td>Mean Accuracy<br>(test)<br>(id, sw, ta, tr, zh)</td>
<td>80.57</td>
<td>76.78</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/data/diagrams">AI2D</a><br>(train)
</td>
<td>Accuracy (test)</td>
<td>72.12</td>
<td>73.28</td>
</tr>
<tr>
<td>
<a href="https://scienceqa.github.io/">ScienceQA</a><br>(Img subset, no CoT)<br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>95.39</td>
<td>95.93</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344334">RSVQA-LR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test)</td>
<td>92.65</td>
<td>93.11</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344367">RSVQA-HR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test/test2)</td>
<td>
92.61<br>
90.58
</td>
<td>
92.79<br>
90.54
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2203.10244">ChartQA</a><br>(human+aug)x(train+val)
</td>
<td>Mean Relaxed<br>Accuracy<br>(test_human,<br>test_aug)</td>
<td>57.08</td>
<td>71.36</td>
</tr>
<tr>
<td>
<a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz VQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>
73.7
</td>
<td>
75.52
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1810.12440">TallyQA</a><br>(train)
</td>
<td>Accuracy<br>(test_simple/<br>test_complex)</td>
<td>
81.72<br>
69.56
</td>
<td>
84.86<br>
72.27
</td>
</tr>
<tr>
<td>
<a href="https://ocr-vqa.github.io/">OCR-VQA</a><br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>72.32</td>
<td>74.61</td>
<td>74.93</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/">TextVQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>55.47</td>
<td>73.15</td>
<td>76.48</td>
</tr>
<tr>
<td>
<a href="https://www.docvqa.org/">DocVQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>43.74</td>
<td>78.02</td>
<td>84.77</td>
</tr>
<tr>
<td>
<a href="https://openaccess.thecvf.com/content/WACV2022/papers/Mathew_InfographicVQA_WACV_2022_paper.pdf">Infographic VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>28.46</td>
<td>40.47</td>
<td>47.75</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1905.13648">SceneText VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>63.29</td>
<td>81.82</td>
<td>84.40</td>
</tr>
<tr>
<th>Segmentation</th>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1608.00272">RefCOCO</a><br>(combined refcoco, refcoco+,<br>refcocog excluding val<br>and test images)
</td>
<td>MIoU<br>(validation)<br>refcoco/refcoco+/<br>refcocog</td>
<td>
73.40<br>
68.32<br>
67.65
</td>
<td>
75.57<br>
69.76<br>
70.17
</td>
<td>
76.94<br>
72.18<br>
72.22
</td>
</tr>
<tr>
<th>Video tasks (Caption/QA)</th>
</tr>
<tr>
<td>MSR-VTT (Captioning)</td>
<td>CIDEr (test)</td>
<td>70.54</td>
</tr>
<tr>
<td>MSR-VTT (QA)</td>
<td>Accuracy (test)</td>
<td>50.09</td>
</tr>
<tr>
<td>ActivityNet (Captioning)</td>
<td>CIDEr (test)</td>
<td>34.62</td>
</tr>
<tr>
<td>ActivityNet (QA)</td>
<td>Accuracy (test)</td>
<td>50.78</td>
</tr>
<tr>
<td>VATEX (Captioning)</td>
<td>CIDEr (test)</td>
<td>79.73</td>
</tr>
<tr>
<td>MSVD (QA)</td>
<td>Accuracy (test)</td>
<td>60.22</td>
</tr>
</tbody></table>
#### Mix model (fine-tune on mixture of transfer tasks)
<table>
<tbody><tr>
<th>Benchmark</th>
<th>Metric (split)</th>
<th>mix-224</th>
<th>mix-448</th>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2401.06209">MMVP</a></td>
<td>Paired Accuracy</td>
<td>46.00</td>
<td>45.33</td>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2305.10355">POPE</a></td>
<td>Accuracy<br>(random/popular/adversarial)</td>
<td>
88.00<br>
86.63<br>
85.67
</td>
<td>
89.37<br>
88.40<br>
87.47
</td>
</tr>
</tbody></table>
## Ethics and safety
### Evaluation approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Human evaluation on prompts covering child safety, content safety and
representational harms. See the [Gemma model
card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for
more details on evaluation approach, but with image captioning and visual
question answering setups.
* Image-to-Text benchmark evaluation: Benchmark against relevant academic
datasets such as FairFace Dataset ([Karkkainen et al.,
2021](https://arxiv.org/abs/1908.04913)).
### Evaluation results
* The human evaluation results of ethics and safety evaluations are within
acceptable thresholds for meeting [internal
policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11)
for categories such as child safety, content safety and representational
harms.
* On top of robust internal evaluations, we also use the Perspective API
(threshold of 0.8) to measure toxicity, profanity, and other potential
issues in the generated captions for images sourced from the FairFace
dataset. We report the maximum and median values observed across subgroups
for each of the perceived gender, ethnicity, and age attributes.
<table>
<tbody><tr>
</tr></tbody><tbody><tr><th>Metric</th>
<th>Perceived<br>gender</th>
<th></th>
<th>Ethnicity</th>
<th></th>
<th>Age group</th>
<th></th>
</tr>
<tr>
<th></th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
</tr>
<tr>
<td>Toxicity</td>
<td>0.04%</td>
<td>0.03%</td>
<td>0.08%</td>
<td>0.00%</td>
<td>0.09%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Identity Attack</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Insult</td>
<td>0.06%</td>
<td>0.04%</td>
<td>0.09%</td>
<td>0.07%</td>
<td>0.16%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Threat</td>
<td>0.06%</td>
<td>0.05%</td>
<td>0.14%</td>
<td>0.05%</td>
<td>0.17%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Profanity</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
</tbody></table>
## Usage and limitations
### Intended usage
Open Vision Language Models (VLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
Fine-tune on specific vision-language task:
* The pre-trained models can be fine-tuned on a wide range of vision-language
tasks such as: image captioning, short video caption, visual question
answering, text reading, object detection and object segmentation.
* The pre-trained models can be fine-tuned for specific domains such as remote
sensing question answering, visual questions from people who are blind,
science question answering, describe UI element functionalities.
* The pre-trained models can be fine-tuned for tasks with non-textual outputs
such as bounding boxes or segmentation masks.
Vision-language research:
* The pre-trained models and fine-tuned models can serve as a foundation for researchers to experiment with VLM
techniques, develop algorithms, and contribute to the advancement of the
field.
### Ethical considerations and risks
The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
* Bias and Fairness
* VLMs trained on large-scale, real-world image-text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
* Misinformation and Misuse
* VLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
* Transparency and Accountability
* This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
Risks identified and mitigations:
* **Perpetuation of biases:** It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* **Generation of harmful content:** Mechanisms and guidelines for content
safety are essential. Developers are encouraged to exercise caution and
implement appropriate content safety safeguards based on their specific
product policies and application use cases.
* **Misuse for malicious purposes:** Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the [Gemma
Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* **Privacy violations:** Models were trained on data filtered to remove certain personal information and sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
### Limitations
* Most limitations inherited from the underlying Gemma model still apply:
* VLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* Natural language is inherently complex. VLMs might struggle to grasp
subtle nuances, sarcasm, or figurative language.
* VLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* VLMs rely on statistical patterns in language and images. They might
lack the ability to apply common sense reasoning in certain situations.
* PaliGemma was designed first and foremost to serve as a general pre-trained
model for transfer to specialized tasks. Hence, its "out of the box" or
"zero-shot" performance might lag behind models designed specifically for
that.
* PaliGemma is not a multi-turn chatbot. It is designed for a single round of
image and text input. |
mradermacher/pantheon-stheno-hathor-spice-v1-GGUF | mradermacher | "2024-06-15T13:12:19Z" | 2,723 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:lik07/pantheon-stheno-hathor-spice-v1",
"endpoints_compatible",
"region:us"
] | null | "2024-06-15T11:17:19Z" | ---
base_model: lik07/pantheon-stheno-hathor-spice-v1
language:
- en
library_name: transformers
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/lik07/pantheon-stheno-hathor-spice-v1
<!-- 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/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/pantheon-stheno-hathor-spice-v1-GGUF/resolve/main/pantheon-stheno-hathor-spice-v1.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 -->
|
RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf | RichardErkhov | "2024-06-22T23:25:04Z" | 2,723 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-22T19:06:00Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
TinyLlama-1.1B-intermediate-step-1195k-token-2.5T - GGUF
- Model creator: https://huggingface.co/TinyLlama/
- Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q2_K.gguf) | Q2_K | 0.4GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ3_S.gguf) | IQ3_S | 0.47GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K.gguf) | Q3_K | 0.51GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_0.gguf) | Q4_0 | 0.59GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_K.gguf) | Q4_K | 0.62GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q4_1.gguf) | Q4_1 | 0.65GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_0.gguf) | Q5_0 | 0.71GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_K.gguf) | Q5_K | 0.73GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q5_1.gguf) | Q5_1 | 0.77GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q6_K.gguf) | Q6_K | 0.84GB |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q8_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1195k-token-2.5T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T.Q8_0.gguf) | Q8_0 | 1.09GB |
Original model description:
---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
language:
- en
---
<div align="center">
# TinyLlama-1.1B
</div>
https://github.com/jzhang38/TinyLlama
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
<div align="center">
<img src="./TinyLlama_logo.png" width="300"/>
</div>
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
#### This Collection
This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen.
#### Eval
| Model | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg |
|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----|
| Pythia-1.0B | 300B | 47.16 | 31.40| 53.43 | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 |
| TinyLlama-1.1B-intermediate-step-50K-104b | 103B | 43.50 | 29.80| 53.28 | 24.32 | 44.91 | 59.66 | 67.30 | 46.11|
| TinyLlama-1.1B-intermediate-step-240k-503b| 503B | 49.56 |31.40 |55.80 |26.54 |48.32 |56.91 |69.42 | 48.28 |
| TinyLlama-1.1B-intermediate-step-480k-1007B | 1007B | 52.54 | 33.40 | 55.96 | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 |
| TinyLlama-1.1B-intermediate-step-715k-1.5T | 1.5T | 53.68 | 35.20 | 58.33 | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
| TinyLlama-1.1B-intermediate-step-955k-2T | 2T | 54.63 | 33.40 | 56.83 | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
| **TinyLlama-1.1B-intermediate-step-1195k-token-2.5T** | **2.5T** | **58.96** | **34.40** | **58.72** | **31.91** | **56.78** | **63.21** | **73.07** | **53.86**|
|
mradermacher/F2PhenotypeKimiko-GGUF | mradermacher | "2024-06-16T09:45:42Z" | 2,722 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:WesPro/F2PhenotypeKimiko",
"endpoints_compatible",
"region:us"
] | null | "2024-06-15T17:37:02Z" | ---
base_model: WesPro/F2PhenotypeKimiko
language:
- en
library_name: transformers
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/WesPro/F2PhenotypeKimiko
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/F2PhenotypeKimiko-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/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/F2PhenotypeKimiko-GGUF/resolve/main/F2PhenotypeKimiko.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 -->
|
RichardErkhov/w601sxs_-_b1ade-1b-gguf | RichardErkhov | "2024-06-24T22:22:41Z" | 2,722 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-24T22:16:02Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
b1ade-1b - GGUF
- Model creator: https://huggingface.co/w601sxs/
- Original model: https://huggingface.co/w601sxs/b1ade-1b/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [b1ade-1b.Q2_K.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q2_K.gguf) | Q2_K | 0.39GB |
| [b1ade-1b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [b1ade-1b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.IQ3_S.gguf) | IQ3_S | 0.45GB |
| [b1ade-1b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q3_K_S.gguf) | Q3_K_S | 0.45GB |
| [b1ade-1b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [b1ade-1b.Q3_K.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q3_K.gguf) | Q3_K | 0.51GB |
| [b1ade-1b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [b1ade-1b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [b1ade-1b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.IQ4_XS.gguf) | IQ4_XS | 0.54GB |
| [b1ade-1b.Q4_0.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q4_0.gguf) | Q4_0 | 0.56GB |
| [b1ade-1b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.IQ4_NL.gguf) | IQ4_NL | 0.56GB |
| [b1ade-1b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q4_K_S.gguf) | Q4_K_S | 0.56GB |
| [b1ade-1b.Q4_K.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q4_K.gguf) | Q4_K | 0.61GB |
| [b1ade-1b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q4_K_M.gguf) | Q4_K_M | 0.61GB |
| [b1ade-1b.Q4_1.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q4_1.gguf) | Q4_1 | 0.61GB |
| [b1ade-1b.Q5_0.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q5_0.gguf) | Q5_0 | 0.66GB |
| [b1ade-1b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q5_K_S.gguf) | Q5_K_S | 0.66GB |
| [b1ade-1b.Q5_K.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q5_K.gguf) | Q5_K | 0.71GB |
| [b1ade-1b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q5_K_M.gguf) | Q5_K_M | 0.71GB |
| [b1ade-1b.Q5_1.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q5_1.gguf) | Q5_1 | 0.72GB |
| [b1ade-1b.Q6_K.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q6_K.gguf) | Q6_K | 0.78GB |
| [b1ade-1b.Q8_0.gguf](https://huggingface.co/RichardErkhov/w601sxs_-_b1ade-1b-gguf/blob/main/b1ade-1b.Q8_0.gguf) | Q8_0 | 1.0GB |
Original model description:
---
language: en
license: mit
tags:
- b1ade
datasets:
- Open-Orca/OpenOrca
- WizardLM/WizardLM_evol_instruct_V2_196k
widget:
- text: "context: <math>\n question: <Evaluate -24 + -24 + 15*2.>\n answer: <"
example_title: Math
- text: "context: <You are a helpful assistant, who always provide explanation. Think\
\ like you are answering to a five year old.>\n question: <Determine the sentiment:\n\
\nWe viewed the vcr and found it to be fascinating. Not knowing anything about\
\ this true story, I thought: Oh, no, P.Brosnan as an American Indian, what a\
\ bad choice until I discovered the truth about Grey Owl. The film does a good\
\ job of demonstrating the dignity of these native peoples and undermining the\
\ racist myths about them. And Annie Galipeau, WOW, what a beauty, and very convincing\
\ as an Indian woman (I believe she is French-Canadian; she sure reverts to the\
\ all-too familiar speech of such). In spite, of Brosnan's detached, grunting\
\ style, in the end he comes through convincingly as a passionate, dedicated man.\
\ The plot is a little weak in demostrating his conversion from trapper to animal\
\ coservationist. Good film, highly recommended.>\n answer: <"
example_title: Sentiment
- inference:
- parameters:
- max_new_tokens: 512
- top_p=0.99
---
# B1ade
Please see https://huggingface.co/w601sxs/b1ade-1b-bf16
|
digiplay/MengX_Mix_Real_v3 | digiplay | "2023-11-29T18:45:08Z" | 2,721 | 3 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-11-29T16:57:16Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/142467?modelVersionId=238630
Sample image I generated with AUTOMATIC111 :
|
trollkotze/miqu-control-vectors | trollkotze | "2024-03-25T12:17:36Z" | 2,720 | 4 | null | [
"gguf",
"region:us"
] | null | "2024-03-19T00:08:51Z" | See patches/README on how to train. |
abhishekchohan/Yi-9B-Forest-DPO-v1.0 | abhishekchohan | "2024-03-19T04:36:54Z" | 2,719 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:Intel/orca_dpo_pairs",
"dataset:nvidia/HelpSteer",
"dataset:jondurbin/truthy-dpo-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-18T17:08:48Z" | ---
license: apache-2.0
datasets:
- Intel/orca_dpo_pairs
- nvidia/HelpSteer
- jondurbin/truthy-dpo-v0.1
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
### Yi-9B-Forest-DPO
Introducing Yi-9B-Forest-DPO, a LLM fine-tuned with base model 01-ai/Yi-9B, using direct preference optimization.
This model showcases exceptional prowess across a spectrum of natural language processing (NLP) tasks.
A mixture of the following datasets was used for fine-tuning.
1. Intel/orca_dpo_pairs
2. nvidia/HelpSteer
3. jondurbin/truthy-dpo-v0.1
💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "abhishekchohan/Yi-9B-Forest-DPO"
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"])
``` |
nomic-ai/nomic-embed-text-v1-GGUF | nomic-ai | "2024-02-15T17:35:49Z" | 2,718 | 3 | null | [
"gguf",
"feature-extraction",
"sentence-similarity",
"en",
"base_model:nomic-ai/nomic-embed-text-v1",
"license:apache-2.0",
"region:us"
] | sentence-similarity | "2024-02-13T19:59:17Z" | ---
base_model: nomic-ai/nomic-embed-text-v1
inference: false
language:
- en
license: apache-2.0
model_creator: Nomic
model_name: nomic-embed-text-v1
model_type: bert
pipeline_tag: sentence-similarity
quantized_by: Nomic
tags:
- feature-extraction
- sentence-similarity
---
***
**Note**: For compatiblity with current llama.cpp, please download the files published on 2/15/2024. The files originally published here will fail to load.
***
<br/>
# nomic-embed-text-v1 - GGUF
Original model: [nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1)
## Description
This repo contains llama.cpp-compatible files for [nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1) in GGUF format.
llama.cpp will default to 2048 tokens of context with these files. To use the full 8192 tokens that Nomic Embed is benchmarked on, you will have to choose a context extension method. The original model uses Dynamic NTK-Aware RoPE scaling, but that is not currently available in llama.cpp. A combination of YaRN and linear scaling is an acceptable substitute.
These files were converted and quantized with llama.cpp [PR 5500](https://github.com/ggerganov/llama.cpp/pull/5500), commit [34aa045de](https://github.com/ggerganov/llama.cpp/pull/5500/commits/34aa045de44271ff7ad42858c75739303b8dc6eb).
## Example `llama.cpp` Command
Compute a single embedding:
```shell
./embedding -ngl 99 -m nomic-embed-text-v1.f16.gguf -c 8192 -b 8192 --rope-scaling yarn --rope-freq-scale .75 -p 'search_query: What is TSNE?'
```
You can also submit a batch of texts to embed, as long as the total number of tokens does not exceed the context length. Only the first three embeddings are shown by the `embedding` example.
texts.txt:
```
search_query: What is TSNE?
search_query: Who is Laurens Van der Maaten?
```
Compute multiple embeddings:
```shell
./embedding -ngl 99 -m nomic-embed-text-v1.f16.gguf -c 8192 -b 8192 --rope-scaling yarn --rope-freq-scale .75 -f texts.txt
```
## Compatibility
These files are compatible with llama.cpp as of commit [4524290e8](https://github.com/ggerganov/llama.cpp/commit/4524290e87b8e107cc2b56e1251751546f4b9051) from 2/15/2024.
## Provided Files
The below table shows the mean squared error of the embeddings produced by these quantizations of Nomic Embed relative to the Sentence Transformers implementation.
Name | Quant | Size | MSE
-----|-------|------|-----
[nomic-embed-text-v1.Q2\_K.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q2_K.gguf) | Q2\_K | 48 MiB | 2.36e-03
[nomic-embed-text-v1.Q3\_K\_S.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q3_K_S.gguf) | Q3\_K\_S | 57 MiB | 1.31e-03
[nomic-embed-text-v1.Q3\_K\_M.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q3_K_M.gguf) | Q3\_K\_M | 65 MiB | 8.73e-04
[nomic-embed-text-v1.Q3\_K\_L.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q3_K_L.gguf) | Q3\_K\_L | 69 MiB | 8.68e-04
[nomic-embed-text-v1.Q4\_0.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q4_0.gguf) | Q4\_0 | 75 MiB | 6.87e-04
[nomic-embed-text-v1.Q4\_K\_S.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q4_K_S.gguf) | Q4\_K\_S | 75 MiB | 6.81e-04
[nomic-embed-text-v1.Q4\_K\_M.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q4_K_M.gguf) | Q4\_K\_M | 81 MiB | 3.12e-04
[nomic-embed-text-v1.Q5\_0.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q5_0.gguf) | Q5\_0 | 91 MiB | 2.79e-04
[nomic-embed-text-v1.Q5\_K\_S.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q5_K_S.gguf) | Q5\_K\_S | 91 MiB | 2.61e-04
[nomic-embed-text-v1.Q5\_K\_M.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q5_K_M.gguf) | Q5\_K\_M | 95 MiB | 7.34e-05
[nomic-embed-text-v1.Q6\_K.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q6_K.gguf) | Q6\_K | 108 MiB | 6.29e-05
[nomic-embed-text-v1.Q8\_0.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.Q8_0.gguf) | Q8\_0 | 140 MiB | 6.34e-06
[nomic-embed-text-v1.f16.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.f16.gguf) | F16 | 262 MiB | 5.62e-10
[nomic-embed-text-v1.f32.gguf](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF/blob/main/nomic-embed-text-v1.f32.gguf) | F32 | 262 MiB | 9.34e-11
|
vihangd/shearedplats-2.7b-v2 | vihangd | "2023-11-21T14:26:18Z" | 2,717 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-18T03:51:50Z" | ---
license: llama2
---
<p><h1> ShearedPlats-7b </h1></p>
An experimental finetune of Sheared LLaMA 2.7b with Alpaca-QLoRA (version 2)
<h2> Datasets </h2>
Trained on alpca style datasets
<p><h2> Prompt Template </h2></p>
Uses alpaca style prompt template
<br/>
# [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_vihangd__shearedplats-2.7b-v2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 36.72 |
| ARC (25-shot) | 42.41 |
| HellaSwag (10-shot) | 72.58 |
| MMLU (5-shot) | 27.52 |
| TruthfulQA (0-shot) | 39.76 |
| Winogrande (5-shot) | 65.9 |
| GSM8K (5-shot) | 1.52 |
| DROP (3-shot) | 7.34 |
|
stockmark/stockmark-13b | stockmark | "2024-05-17T06:15:56Z" | 2,716 | 35 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"japanese",
"llama-2",
"Powered by AWS Trainium",
"ja",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-21T06:53:06Z" | ---
license: mit
language:
- ja
library_name: transformers
pipeline_tag: text-generation
tags:
- japanese
- llama-2
- Powered by AWS Trainium
---
# stockmark/stockmark-13b
Stockmark-13b is a 13 billion parameter LLM pretrained from scratch based on Japanese corpus of about 220B tokens. This model is developed by [Stockmark Inc.](https://stockmark.co.jp/)
Please see our [blog](https://tech.stockmark.co.jp/blog/202310_stockmark_13b/) for more details.
This project is supported by [AWS LLM development support program](https://aws.amazon.com/jp/local/llm-development-support-program/).
We also provide [stockmark-13b-instruct](https://huggingface.co/stockmark/stockmark-13b-instruct), which is the instruction tuned version of stockmark-13b.
## How to use
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
# For A100 or H100 GPU
model = AutoModelForCausalLM.from_pretrained("stockmark/stockmark-13b", device_map="auto", torch_dtype=torch.bfloat16)
# If you use a T4 or V100 GPU, please load a model in 8 bit with the below code.
# To do so, you need to install `bitsandbytes` via `pip install bitsandbytes`.
# model = AutoModelForCausalLM.from_pretrained("stockmark/stockmark-13b", device_map={"": 0}, load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("stockmark/stockmark-13b")
inputs = tokenizer("自然言語処理とは", return_tensors="pt").to(model.device)
with torch.no_grad():
tokens = model.generate(
**inputs,
max_new_tokens=128,
do_sample=True,
temperature=0.7
)
output = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(output)
```
## Examples:
- LoRA tuning: https://huggingface.co/stockmark/stockmark-13b/blob/main/notebooks/LoRA.ipynb
## Training dataset
We have used Japanese corpus of total of about 220 billion tokens.
|corpus|tokens after preprocessing|
|:---:|:---:|
|Stockmark Web Corpus (This dataset will not be released)|9.1 billion|
|Patent|34.8 billion|
|Wikipedia|1.0 billion|
|CC100|10.9 billion|
|mC4|53.2 billion|
|CommonCrawl (snapshot: 2023-23, 2022-49, 2022-21, 2021-21)|112.9 billion|
## Accelerator and Library
- Accelerator: AWS Trainium
- https://aws.amazon.com/machine-learning/trainium/
- Library for distributed training: neuronx-nemo-megatron
- https://github.com/aws-neuron/neuronx-nemo-megatron
## License
[MIT](https://opensource.org/licenses/MIT)
## Developed by
[Stockmark Inc.](https://stockmark.co.jp/)
## Author
[Takahiro Omi](https://huggingface.co/omitakahiro)
|
maywell/TinyWand-DPO | maywell | "2024-02-02T10:50:13Z" | 2,716 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-04T06:14:08Z" | ---
license: apache-2.0
---
# **TinyWand-DPO**
<p align="left">
<img src="./TinyWand.png" width="150"/>
<p>
# **한국어 모델 설명**
**1.63B, 하찮은 크기의 SLM은 어떨까요?**
## **모델 소개**
**TinyWand-DPO**는 1.63B의 SLM 모델입니다. 이 모델은 1.63B라는 작은 크기를 가짐으로써 소형기기에서 구동되거나 큰 toks/s를 가질 수 있음과 동시에 강력한 성능을 보여줍니다.
## **모델 라이센스**
OPEN
## **모델 성능**
TBD
## **학습 과정**
TBD
## **사용 안내**
**추론에 필요한 VRAM**
| 양자화 | 입력 토큰 수 | 출력 토큰 수 | 메모리 사용량 |
|---|---|---|---|
| bf16(base) | 64 | 256 | 3,888 MiB |
| q4_K_M | 64 | 256 | 1,788 MiB |
**프롬프트 템플릿**
본 모델은 Alpaca 프롬프트 템플릿을 사용합니다.
해당 템플릿은 `apply_chat_template()`를 통해 [허깅페이스 템플릿](https://huggingface.co/docs/transformers/main/chat_templating)에서 확인 하실 수 있습니다.
**아래 파이썬 코드를 사용하여 모델을 로드 및 사용 할 수 있습니다.**
*transformers, torch가 사전 설치되어야함*
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # nvidia 그래픽카드 기준
tokenizer = AutoTokenizer.from_pretrained("maywell/TinyWand-DPO")
model = AutoModelForCausalLM.from_pretrained(
"maywell/TinyWand-DPO",
device_map="auto",
torch_dtype=torch.bfloat16, # 사용하는 장비가 bfloat16을 지원하지 않는 경우 torch.float16으로 바꿔주세요.
)
messages = [
{"role": "system", "content": "Below is an instruction that describes a task. Write a response that appropriately completes the request."}, # 비울 경우에도 동일하게 적용 됨.
{"role": "user", "content": "언어모델의 파라미터 수가 작으면 어떤 이점이 있어?"},
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
``` |
Lin-Chen/open-llava-next-llama3-8b | Lin-Chen | "2024-05-27T07:13:57Z" | 2,716 | 22 | transformers | [
"transformers",
"safetensors",
"llava_llama",
"text-generation",
"image-text-to-text",
"dataset:Lin-Chen/ShareGPT4V",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | image-text-to-text | "2024-05-26T13:42:34Z" | ---
license: apache-2.0
inference: false
datasets:
- Lin-Chen/ShareGPT4V
pipeline_tag: image-text-to-text
---
<br>
<br>
# open-llava-next-llama3-8b Model Card
## Model details
**Model type:**
open-llava-next-llama3-8b is an open-source implementation chatbot trained by fine-tuning the entire model on open-source [Open-LLaVA-Next-mix1M](https://huggingface.co/datasets/Lin-Chen/Open-LLaVA-NeXT-mix1M) data.
**Model date:**
open-llava-next-llama3-8b was trained in May 2024.
**Paper or resources for more information:**
[[Code](https://github.com/xiaoachen98/Open-LLaVA-NeXT)]
| Name | ViT | LLM | Weights | MME | SEED | SQA | MMB | MMB-CN | TextVQA | GQA |
|---|---|---|---|---|---|---|---|---|---|---|
| llava-next-vicuna-7b | CLIP-L-336 | Vicuna-7B | [HF](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b) | 1519 | 70.2 | 70.1 | 67.4 | 60.6 | 64.9 | 64.2 |
| open-llava-next-vicuna-7b| CLIP-L-336 | Vicuna-7B | [HF](https://huggingface.co/Lin-Chen/open-llava-next-vicuna-7b) | 1540 | 71.1 | 70.7 | 68.5 | 60.7 | 67.2 | 64.3 |
| open-llava-next-llama3-8b| CLIP-L-336 | LLaMA3-8B | [HF](https://huggingface.co/Lin-Chen/open-llava-next-llama3-8b) | 1552 | 74.4 | 77.3 | 74.4 | 70.4 | 69.8 | 65.9 |
## Usage
You can utilize this model as we provide in our [[repository](https://github.com/xiaoachen98/Open-LLaVA-NeXT)]. Moreover, you can direct load this model and use it in the [[LLaVA repository](https://github.com/haotian-liu/LLaVA)].
## Training dataset
All training data are open-sourced in our [repository](https://github.com/xiaoachen98/Open-LLaVA-NeXT).
- [ShareGPT4V Mix665K](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V)
- 200K GPT4V-generated instruction data (ALLaVA)
- 200K various VQA data
## Intended use
**Primary intended uses:**
The primary use of open-llava-next-llama3-8b is research on large multimodal models and chatbots.
**Primary intended users:**
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
mradermacher/LLaMA2-13B-Estopia-i1-GGUF | mradermacher | "2024-06-13T01:54:54Z" | 2,716 | 1 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:KoboldAI/LLaMA2-13B-Estopia",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-12T08:10:22Z" | ---
base_model: KoboldAI/LLaMA2-13B-Estopia
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-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/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Estopia-i1-GGUF/resolve/main/LLaMA2-13B-Estopia.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
<!-- end -->
|
abacusai/Smaug-Mixtral-v0.1 | abacusai | "2024-02-21T19:13:07Z" | 2,715 | 12 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"finetune",
"conversational",
"arxiv:2402.13228",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-18T14:51:31Z" | ---
license: apache-2.0
tags:
- mixtral
- finetune
---
## Overview
This model is part of the Smaug series of finetuned models. This one based on https://huggingface.co/mistralai/Mixtral-8x7B-v0.1
We use a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets).
We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228.
We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.
Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode.
Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.
We believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models.
With the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space!
Keep watching this space for our announcements!
### Evaluation Results
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- |
| 75.12 | 74.91 | 87.70 | 70.16 | 65.96 | 81.61 | 70.36 | |
lamini/lamini_docs_finetuned | lamini | "2024-02-29T07:13:15Z" | 2,714 | 7 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-24T01:07:55Z" | ---
license: apache-2.0
---
This model was finetuned on EleutherAI/pythia-70m. The dataset used was lamini documents in the form of Q/A which tell more about how to use the platform. This is a sample task. |
ckiplab/albert-tiny-chinese | ckiplab | "2022-05-10T03:28:09Z" | 2,712 | 7 | transformers | [
"transformers",
"pytorch",
"albert",
"fill-mask",
"lm-head",
"zh",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2022-03-02T23:29:05Z" | ---
language:
- zh
thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
tags:
- pytorch
- lm-head
- albert
- zh
license: gpl-3.0
---
# CKIP ALBERT Tiny Chinese
This project provides traditional Chinese transformers models (including ALBERT, BERT, GPT2) and NLP tools (including word segmentation, part-of-speech tagging, named entity recognition).
這個專案提供了繁體中文的 transformers 模型（包含 ALBERT、BERT、GPT2）及自然語言處理工具（包含斷詞、詞性標記、實體辨識）。
## Homepage
- https://github.com/ckiplab/ckip-transformers
## Contributers
- [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
## Usage
Please use BertTokenizerFast as tokenizer instead of AutoTokenizer.
請使用 BertTokenizerFast 而非 AutoTokenizer。
```
from transformers import (
BertTokenizerFast,
AutoModel,
)
tokenizer = BertTokenizerFast.from_pretrained('bert-base-chinese')
model = AutoModel.from_pretrained('ckiplab/albert-tiny-chinese')
```
For full usage and more information, please refer to https://github.com/ckiplab/ckip-transformers.
有關完整使用方法及其他資訊，請參見 https://github.com/ckiplab/ckip-transformers 。
|
bigcode/starpii | bigcode | "2023-07-24T09:43:04Z" | 2,711 | 106 | transformers | [
"transformers",
"pytorch",
"bert",
"token-classification",
"code",
"dataset:bigcode/pii-annotated-toloka-donwsample-emails",
"dataset:bigcode/pseudo-labeled-python-data-pii-detection-filtered",
"arxiv:2301.03988",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2023-04-23T16:12:27Z" | ---
datasets:
- bigcode/pii-annotated-toloka-donwsample-emails
- bigcode/pseudo-labeled-python-data-pii-detection-filtered
metrics:
- f1
pipeline_tag: token-classification
language:
- code
extra_gated_prompt: >-
## Terms of Use for the model
This is an NER model trained to detect Personal Identifiable Information (PII)
in code datasets. We ask that you read and agree to the following Terms of Use
before using the model:
1. You agree that you will not use the model for any purpose other than PII
detection for the purpose of removing PII from datasets.
2. You agree that you will not share the model or any modified versions for
whatever purpose.
3. Unless required by applicable law or agreed to in writing, the model is
provided on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
either express or implied, including, without limitation, any warranties or
conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using the model, and assume any risks associated with your
exercise of permissions under these Terms of Use.
4. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE MODEL OR THE USE OR
OTHER DEALINGS IN THE MODEL.
extra_gated_fields:
Email: text
I have read the License and agree with its terms: checkbox
---
# StarPII
## Model description
This is an NER model trained to detect Personal Identifiable Information (PII) in code datasets. We fine-tuned [bigcode-encoder](https://huggingface.co/bigcode/bigcode-encoder)
on a PII dataset we annotated, available with gated access at [bigcode-pii-dataset](https://huggingface.co/datasets/bigcode/pii-annotated-toloka-donwsample-emails) (see [bigcode-pii-dataset-training](https://huggingface.co/datasets/bigcode/bigcode-pii-dataset-training) for the exact data splits).
We added a linear layer as a token classification head on top of the encoder model, with 6 target classes: Names, Emails, Keys, Passwords, IP addresses and Usernames.
## Dataset
### Fine-tuning on the annotated dataset
The finetuning dataset contains 20961 secrets and 31 programming languages, but the base encoder model was pre-trained on 88
programming languages from [The Stack](https://huggingface.co/datasets/bigcode/the-stack) dataset.
### Initial training on a pseudo-labelled dataset
To enhance model performance on some rare PII entities like keys, we initially trained on a pseudo-labeled dataset before fine-tuning on the annotated dataset.
The method involves training a model on a small set of labeled data and subsequently generating predictions for a larger set of unlabeled data.
Specifically, we annotated 18,000 files available at [bigcode-pii-ppseudo-labeled](https://huggingface.co/datasets/bigcode/pseudo-labeled-python-data-pii-detection-filtered)
using an ensemble of two encoder models [Deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) and [stanford-deidentifier-base](StanfordAIMI/stanford-deidentifier-base)
which were fine-tuned on an intern previously labeled PII [dataset](https://huggingface.co/datasets/bigcode/pii-for-code) for code with 400 files from this [work](https://arxiv.org/abs/2301.03988).
To select good-quality pseudo-labels, we computed the average probability logits between the models and filtered based on a minimum score.
After inspection, we observed a high rate of false positives for Keys and Passwords, hence we retained only the entities that had a trigger word like `key`, `auth` and `pwd` in the surrounding context.
Training on this synthetic dataset prior to fine-tuning on the annotated one yielded superior results for all PII categories,
as demonstrated in the table in the following section.
### Performance
This model is respresented in the last row (NER + pseudo labels )
- Emails, IP addresses and Keys
| Method | Email address | | | IP address | | | Key | | |
| ------------------ | -------------- | ---- | ---- | ---------- | ---- | ---- | ----- | ---- | ---- |
| | Prec. | Recall | F1 | Prec. | Recall | F1 | Prec. | Recall | F1 |
| Regex | 69.8% | 98.8% | 81.8% | 65.9% | 78% | 71.7% | 2.8% | 46.9% | 5.3% |
| NER | 94.01% | 98.10% | 96.01% | 88.95% | *94.43%* | 91.61% | 60.37% | 53.38% | 56.66% |
| + pseudo labels | **97.73%** | **98.94%** | **98.15%** | **90.10%** | 93.86% | **91.94%** | **62.38%** | **80.81%** | **70.41%** |
- Names, Usernames and Passwords
| Method | Name | | | Username | | | Password | | |
| ------------------ | -------- | ---- | ---- | -------- | ---- | ---- | -------- | ---- | ---- |
| | Prec. | Recall | F1 | Prec. | Recall | F1 | Prec. | Recall | F1 |
| NER | 83.66% | 95.52% | 89.19% | 48.93% | *75.55%* | 59.39% | 59.16% | *96.62%* | 73.39%|
| + pseudo labels | **86.45%** | **97.38%** | **91.59%** | **52.20%** | 74.81% | **61.49%** | **70.94%** | 95.96% | **81.57%** |
We used this model to mask PII in the bigcode large model training. We dropped usernames since they resulted in many false positives and negatives.
For the other PII types, we added the following post-processing that we recommend for future uses of the model (the code is also available on GitHub):
- Ignore secrets with less than 4 characters.
- Detect full names only.
- Ignore detected keys with less than 9 characters or that are not gibberish using a [gibberish-detector](https://github.com/domanchi/gibberish-detector).
- Ignore IP addresses that aren't valid or are private (non-internet facing) using the `ipaddress` python package. We also ignore IP addresses from popular DNS servers.
We use the same list as in this [paper](https://huggingface.co/bigcode/santacoder).
# Considerations for Using the Model
While using this model, please be aware that there may be potential risks associated with its application.
There is a possibility of false positives and negatives, which could lead to unintended consequences when processing sensitive data.
Moreover, the model's performance may vary across different data types and programming languages, necessitating validation and fine-tuning for specific use cases.
Researchers and developers are expected to uphold ethical standards and data protection measures when using the model. By making it openly accessible,
our aim is to encourage the development of privacy-preserving AI technologies while remaining vigilant of potential risks associated with PII. |
Chat-UniVi/Chat-UniVi | Chat-UniVi | "2023-11-29T02:27:47Z" | 2,711 | 12 | transformers | [
"transformers",
"pytorch",
"ChatUniVi",
"text-generation",
"arxiv:2311.08046",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-09-28T13:56:34Z" | ---
license: llama2
---
# Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
**Paper or resources for more information:**
[[Paper](https://huggingface.co/papers/2311.08046)] [[Code](https://github.com/PKU-YuanGroup/Chat-UniVi)]
## License
Llama 2 is licensed under the LLAMA 2 Community License,
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
## 😮 Highlights
### 💡 Unified visual representation for image and video
We employ **a set of dynamic visual tokens** to uniformly represent images and videos.
This representation framework empowers the model to efficiently utilize **a limited number of visual tokens** to simultaneously capture **the spatial details necessary for images** and **the comprehensive temporal relationship required for videos**.
### 🔥 Joint training strategy, making LLMs understand both image and video
Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications.
### 🤗 High performance, complementary learning with image and video
Extensive experimental results demonstrate that Chat-UniVi, as a unified model, consistently outperforms even existing methods exclusively designed for either images or videos.
### Inference for Video Understanding
```python
import torch
import os
from ChatUniVi.constants import *
from ChatUniVi.conversation import conv_templates, SeparatorStyle
from ChatUniVi.model.builder import load_pretrained_model
from ChatUniVi.utils import disable_torch_init
from ChatUniVi.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from PIL import Image
from decord import VideoReader, cpu
import numpy as np
def _get_rawvideo_dec(video_path, image_processor, max_frames=MAX_IMAGE_LENGTH, image_resolution=224, video_framerate=1, s=None, e=None):
# speed up video decode via decord.
if s is None:
start_time, end_time = None, None
else:
start_time = int(s)
end_time = int(e)
start_time = start_time if start_time >= 0. else 0.
end_time = end_time if end_time >= 0. else 0.
if start_time > end_time:
start_time, end_time = end_time, start_time
elif start_time == end_time:
end_time = start_time + 1
if os.path.exists(video_path):
vreader = VideoReader(video_path, ctx=cpu(0))
else:
print(video_path)
raise FileNotFoundError
fps = vreader.get_avg_fps()
f_start = 0 if start_time is None else int(start_time * fps)
f_end = int(min(1000000000 if end_time is None else end_time * fps, len(vreader) - 1))
num_frames = f_end - f_start + 1
if num_frames > 0:
# T x 3 x H x W
sample_fps = int(video_framerate)
t_stride = int(round(float(fps) / sample_fps))
all_pos = list(range(f_start, f_end + 1, t_stride))
if len(all_pos) > max_frames:
sample_pos = [all_pos[_] for _ in np.linspace(0, len(all_pos) - 1, num=max_frames, dtype=int)]
else:
sample_pos = all_pos
patch_images = [Image.fromarray(f) for f in vreader.get_batch(sample_pos).asnumpy()]
patch_images = torch.stack([image_processor.preprocess(img, return_tensors='pt')['pixel_values'][0] for img in patch_images])
slice_len = patch_images.shape[0]
return patch_images, slice_len
else:
print("video path: {} error.".format(video_path))
if __name__ == '__main__':
# Model Parameter
model_path = "Chat-UniVi/Chat-UniVi" # or "Chat-UniVi/Chat-UniVi-13B"
video_path = ${video_path}
# The number of visual tokens varies with the length of the video. "max_frames" is the maximum number of frames.
# When the video is long, we will uniformly downsample the video to meet the frames when equal to the "max_frames".
max_frames = 100
# The number of frames retained per second in the video.
video_framerate = 1
# Input Text
qs = "Describe the video."
# Sampling Parameter
conv_mode = "simple"
temperature = 0.2
top_p = None
num_beams = 1
disable_torch_init()
model_path = os.path.expanduser(model_path)
model_name = "ChatUniVi"
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name)
mm_use_im_start_end = getattr(model.config, "mm_use_im_start_end", False)
mm_use_im_patch_token = getattr(model.config, "mm_use_im_patch_token", True)
if mm_use_im_patch_token:
tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
if mm_use_im_start_end:
tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True)
model.resize_token_embeddings(len(tokenizer))
vision_tower = model.get_vision_tower()
if not vision_tower.is_loaded:
vision_tower.load_model()
image_processor = vision_tower.image_processor
if model.config.config["use_cluster"]:
for n, m in model.named_modules():
m = m.to(dtype=torch.bfloat16)
# Check if the video exists
if video_path is not None:
video_frames, slice_len = _get_rawvideo_dec(video_path, image_processor, max_frames=max_frames, video_framerate=video_framerate)
cur_prompt = qs
if model.config.mm_use_im_start_end:
qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN * slice_len + DEFAULT_IM_END_TOKEN + '\n' + qs
else:
qs = DEFAULT_IMAGE_TOKEN * slice_len + '\n' + qs
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], qs)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(
0).cuda()
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=video_frames.half().cuda(),
do_sample=True,
temperature=temperature,
top_p=top_p,
num_beams=num_beams,
output_scores=True,
return_dict_in_generate=True,
max_new_tokens=1024,
use_cache=True,
stopping_criteria=[stopping_criteria])
output_ids = output_ids.sequences
input_token_len = input_ids.shape[1]
n_diff_input_output = (input_ids != output_ids[:, :input_token_len]).sum().item()
if n_diff_input_output > 0:
print(f'[Warning] {n_diff_input_output} output_ids are not the same as the input_ids')
outputs = tokenizer.batch_decode(output_ids[:, input_token_len:], skip_special_tokens=True)[0]
outputs = outputs.strip()
if outputs.endswith(stop_str):
outputs = outputs[:-len(stop_str)]
outputs = outputs.strip()
print(outputs)
```
### Inference for Image Understanding
```python
import torch
import os
from ChatUniVi.constants import *
from ChatUniVi.conversation import conv_templates, SeparatorStyle
from ChatUniVi.model.builder import load_pretrained_model
from ChatUniVi.utils import disable_torch_init
from ChatUniVi.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from PIL import Image
if __name__ == '__main__':
# Model Parameter
model_path = "Chat-UniVi/Chat-UniVi" # or "Chat-UniVi/Chat-UniVi-13B"
image_path = ${image_path}
# Input Text
qs = "Describe the image."
# Sampling Parameter
conv_mode = "simple"
temperature = 0.2
top_p = None
num_beams = 1
disable_torch_init()
model_path = os.path.expanduser(model_path)
model_name = "ChatUniVi"
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name)
mm_use_im_start_end = getattr(model.config, "mm_use_im_start_end", False)
mm_use_im_patch_token = getattr(model.config, "mm_use_im_patch_token", True)
if mm_use_im_patch_token:
tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
if mm_use_im_start_end:
tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True)
model.resize_token_embeddings(len(tokenizer))
vision_tower = model.get_vision_tower()
if not vision_tower.is_loaded:
vision_tower.load_model()
image_processor = vision_tower.image_processor
# Check if the video exists
if image_path is not None:
cur_prompt = qs
if model.config.mm_use_im_start_end:
qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs
else:
qs = DEFAULT_IMAGE_TOKEN + '\n' + qs
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], qs)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda()
image = Image.open(image_path)
image_tensor = image_processor.preprocess(image, return_tensors='pt')['pixel_values'][0]
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=image_tensor.unsqueeze(0).half().cuda(),
do_sample=True,
temperature=temperature,
top_p=top_p,
num_beams=num_beams,
max_new_tokens=1024,
use_cache=True,
stopping_criteria=[stopping_criteria])
input_token_len = input_ids.shape[1]
n_diff_input_output = (input_ids != output_ids[:, :input_token_len]).sum().item()
if n_diff_input_output > 0:
print(f'[Warning] {n_diff_input_output} output_ids are not the same as the input_ids')
outputs = tokenizer.batch_decode(output_ids[:, input_token_len:], skip_special_tokens=True)[0]
outputs = outputs.strip()
if outputs.endswith(stop_str):
outputs = outputs[:-len(stop_str)]
outputs = outputs.strip()
print(outputs)
```
|
SmilingWolf/wd-convnext-tagger-v3 | SmilingWolf | "2024-03-16T20:26:19Z" | 2,711 | 14 | timm | [
"timm",
"onnx",
"safetensors",
"license:apache-2.0",
"region:us"
] | null | "2024-03-04T20:42:44Z" | ---
license: apache-2.0
library_name: timm
---
# WD ConvNext Tagger v3
Supports ratings, characters and general tags.
Trained using https://github.com/SmilingWolf/JAX-CV.
TPUs used for training kindly provided by the [TRC program](https://sites.research.google/trc/about/).
## Dataset
Last image id: 7220105
Trained on Danbooru images with IDs modulo 0000-0899.
Validated on images with IDs modulo 0950-0999.
Images with less than 10 general tags were filtered out.
Tags with less than 600 images were filtered out.
## Validation results
`v2.0: P=R: threshold = 0.2682, F1 = 0.4419`
`v1.0: P=R: threshold = 0.2570, F1 = 0.4282`
## What's new
Model v2.0/Dataset v3:
Trained for a few more epochs.
Used tag frequency-based loss scaling to combat class imbalance.
Model v1.1/Dataset v3:
Amended the JAX model config file: add image size.
No change to the trained weights.
Model v1.0/Dataset v3:
More training images, more and up-to-date tags (up to 2024-02-28).
Now `timm` compatible! Load it up and give it a spin using the canonical one-liner!
ONNX model is compatible with code developed for the v2 series of models.
The batch dimension of the ONNX model is not fixed to 1 anymore. Now you can go crazy with batch inference.
Switched to Macro-F1 to measure model performance since it gives me a better gauge of overall training progress.
# Runtime deps
ONNX model requires `onnxruntime >= 1.17.0`
# Inference code examples
For timm: https://github.com/neggles/wdv3-timm
For ONNX: https://huggingface.co/spaces/SmilingWolf/wd-tagger
For JAX: https://github.com/SmilingWolf/wdv3-jax
## Final words
Subject to change and updates.
Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.
|
Qwen/Qwen-14B-Chat | Qwen | "2023-12-13T15:44:33Z" | 2,710 | 355 | transformers | [
"transformers",
"safetensors",
"qwen",
"text-generation",
"custom_code",
"zh",
"en",
"arxiv:2309.16609",
"arxiv:2305.08322",
"arxiv:2009.03300",
"arxiv:2305.05280",
"arxiv:2210.03629",
"autotrain_compatible",
"region:us"
] | text-generation | "2023-09-24T03:27:58Z" | ---
language:
- zh
- en
tags:
- qwen
pipeline_tag: text-generation
inference: false
---
# Qwen-14B-Chat
<p align="center">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/logo_qwen.jpg" width="400"/>
<p>
<br>
<p align="center">
🤗 <a href="https://huggingface.co/Qwen">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/organization/qwen">ModelScope</a>   |    📑 <a href="https://arxiv.org/abs/2309.16609">Paper</a>    ｜   🖥️ <a href="https://modelscope.cn/studios/qwen/Qwen-14B-Chat-Demo/summary">Demo</a>
<br>
<a href="https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png">WeChat (微信)</a>   |   <a href="https://discord.gg/z3GAxXZ9Ce">Discord</a>   ｜   <a href="https://dashscope.aliyun.com">API</a>
</p>
<br>
## 介绍（Introduction）
**通义千问-14B（Qwen-14B）**是阿里云研发的通义千问大模型系列的140亿参数规模的模型。Qwen-14B是基于Transformer的大语言模型, 在超大规模的预训练数据上进行训练得到。预训练数据类型多样，覆盖广泛，包括大量网络文本、专业书籍、代码等。同时，在Qwen-14B的基础上，我们使用对齐机制打造了基于大语言模型的AI助手Qwen-14B-Chat。本仓库为Qwen-14B-Chat的仓库。
如果您想了解更多关于通义千问-14B开源模型的细节，我们建议您参阅[GitHub代码库](https://github.com/QwenLM/Qwen)。
**Qwen-14B** is the 14B-parameter version of the large language model series, Qwen (abbr. Tongyi Qianwen), proposed by Alibaba Cloud. Qwen-14B is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books, codes, etc. Additionally, based on the pretrained Qwen-14B, we release Qwen-14B-Chat, a large-model-based AI assistant, which is trained with alignment techniques. This repository is the one for Qwen-14B-Chat.
For more details about the open-source model of Qwen-14B, please refer to the [GitHub](https://github.com/QwenLM/Qwen) code repository.
<br>
## 要求（Requirements）
* python 3.8及以上版本
* pytorch 1.12及以上版本，推荐2.0及以上版本
* 建议使用CUDA 11.4及以上（GPU用户、flash-attention用户等需考虑此选项）
* python 3.8 and above
* pytorch 1.12 and above, 2.0 and above are recommended
* CUDA 11.4 and above are recommended (this is for GPU users, flash-attention users, etc.)
<br>
## 依赖项（Dependency）
运行Qwen-14B-Chat，请确保满足上述要求，再执行以下pip命令安装依赖库
To run Qwen-14B-Chat, please make sure you meet the above requirements, and then execute the following pip commands to install the dependent libraries.
```bash
pip install transformers==4.32.0 accelerate tiktoken einops scipy transformers_stream_generator==0.0.4 peft deepspeed
```
另外，推荐安装`flash-attention`库（**当前已支持flash attention 2**），以实现更高的效率和更低的显存占用。
In addition, it is recommended to install the `flash-attention` library (**we support flash attention 2 now.**) for higher efficiency and lower memory usage.
```bash
git clone https://github.com/Dao-AILab/flash-attention
cd flash-attention && pip install .
# 下方安装可选，安装可能比较缓慢。
# pip install csrc/layer_norm
# pip install csrc/rotary
```
<br>
## 快速使用（Quickstart）
下面我们展示了一个使用Qwen-14B-Chat模型，进行多轮对话交互的样例：
We show an example of multi-turn interaction with Qwen-14B-Chat in the following code:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
# Note: The default behavior now has injection attack prevention off.
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-14B-Chat", trust_remote_code=True)
# use bf16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-14B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval()
# use fp16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-14B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
# use cpu only
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-14B-Chat", device_map="cpu", trust_remote_code=True).eval()
# use auto mode, automatically select precision based on the device.
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-14B-Chat", device_map="auto", trust_remote_code=True).eval()
# Specify hyperparameters for generation. But if you use transformers>=4.32.0, there is no need to do this.
# model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-14B-Chat", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
# 第一轮对话 1st dialogue turn
response, history = model.chat(tokenizer, "你好", history=None)
print(response)
# 你好！很高兴为你提供帮助。
# 第二轮对话 2nd dialogue turn
response, history = model.chat(tokenizer, "给我讲一个年轻人奋斗创业最终取得成功的故事。", history=history)
print(response)
# 这是一个关于一个年轻人奋斗创业最终取得成功的故事。
# 故事的主人公叫李明，他来自一个普通的家庭，父母都是普通的工人。从小，李明就立下了一个目标：要成为一名成功的企业家。
# 为了实现这个目标，李明勤奋学习，考上了大学。在大学期间，他积极参加各种创业比赛，获得了不少奖项。他还利用课余时间去实习，积累了宝贵的经验。
# 毕业后，李明决定开始自己的创业之路。他开始寻找投资机会，但多次都被拒绝了。然而，他并没有放弃。他继续努力，不断改进自己的创业计划，并寻找新的投资机会。
# 最终，李明成功地获得了一笔投资，开始了自己的创业之路。他成立了一家科技公司，专注于开发新型软件。在他的领导下，公司迅速发展起来，成为了一家成功的科技企业。
# 李明的成功并不是偶然的。他勤奋、坚韧、勇于冒险，不断学习和改进自己。他的成功也证明了，只要努力奋斗，任何人都有可能取得成功。
# 第三轮对话 3rd dialogue turn
response, history = model.chat(tokenizer, "给这个故事起一个标题", history=history)
print(response)
# 《奋斗创业：一个年轻人的成功之路》
```
关于更多的使用说明，请参考我们的[GitHub repo](https://github.com/QwenLM/Qwen)获取更多信息。
For more information, please refer to our [GitHub repo](https://github.com/QwenLM/Qwen) for more information.
<br>
## 量化 (Quantization)
### 用法 (Usage)
**请注意：我们更新量化方案为基于[AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ)的量化，提供Qwen-14B-Chat的Int4量化模型[点击这里](https://huggingface.co/Qwen/Qwen-14B-Chat-Int4)。相比此前方案，该方案在模型评测效果几乎无损，且存储需求更低，推理速度更优。**
**Note: we provide a new solution based on [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ), and release an Int4 quantized model for Qwen-14B-Chat [Click here](https://huggingface.co/Qwen/Qwen-14B-Chat-Int4), which achieves nearly lossless model effects but improved performance on both memory costs and inference speed, in comparison with the previous solution.**
以下我们提供示例说明如何使用Int4量化模型。在开始使用前，请先保证满足要求（如torch 2.0及以上，transformers版本为4.32.0及以上，等等），并安装所需安装包：
Here we demonstrate how to use our provided quantized models for inference. Before you start, make sure you meet the requirements of auto-gptq (e.g., torch 2.0 and above, transformers 4.32.0 and above, etc.) and install the required packages:
```bash
pip install auto-gptq optimum
```
如安装`auto-gptq`遇到问题，我们建议您到官方[repo](https://github.com/PanQiWei/AutoGPTQ)搜索合适的预编译wheel。
随后即可使用和上述一致的用法调用量化模型：
If you meet problems installing `auto-gptq`, we advise you to check out the official [repo](https://github.com/PanQiWei/AutoGPTQ) to find a pre-build wheel.
Then you can load the quantized model easily and run inference as same as usual:
```python
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen-14B-Chat-Int4",
device_map="auto",
trust_remote_code=True
).eval()
response, history = model.chat(tokenizer, "你好", history=None)
```
### 效果评测
我们对BF16，Int8和Int4模型在基准评测上做了测试（使用zero-shot设置），发现量化模型效果损失较小，结果如下所示：
We illustrate the zero-shot performance of both BF16, Int8 and Int4 models on the benchmark, and we find that the quantized model does not suffer from significant performance degradation. Results are shown below:
| Quantization | MMLU | CEval (val) | GSM8K | Humaneval |
|--------------|:----:|:-----------:|:-----:|:---------:|
| BF16 | 64.6 | 69.8 | 60.1 | 43.9 |
| Int8 | 63.6 | 68.6 | 60.0 | 48.2 |
| Int4 | 63.3 | 69.0 | 59.8 | 45.7 |
### 推理速度 (Inference Speed)
我们测算了不同精度模型以及不同FlashAttn库版本下模型生成2048和8192个token的平均推理速度。如图所示：
We measured the average inference speed of generating 2048 and 8192 tokens with different quantization levels and versions of flash-attention, respectively.
| Quantization | FlashAttn | Speed (2048 tokens) | Speed (8192 tokens) |
| ------------- | :-------: | :------------------:| :------------------:|
| BF16 | v2 | 32.88 | 24.87 |
| Int8 | v2 | 29.28 | 24.22 |
| Int4 | v2 | 38.72 | 27.33 |
| BF16 | v1 | 32.76 | 28.89 |
| Int8 | v1 | 28.31 | 23.87 |
| Int4 | v1 | 37.81 | 26.46 |
| BF16 | Disabled | 29.32 | 22.91 |
| Int8 | Disabled | 31.12 | 24.60 |
| Int4 | Disabled | 37.65 | 26.00 |
具体而言，我们记录在长度为1的上下文的条件下生成8192个token的性能。评测运行于单张A100-SXM4-80G GPU，使用PyTorch 2.0.1和CUDA 11.8。推理速度是生成8192个token的速度均值。
In detail, the setting of profiling is generating 8192 new tokens with 1 context token. The profiling runs on a single A100-SXM4-80G GPU with PyTorch 2.0.1 and CUDA 11.8. The inference speed is averaged over the generated 8192 tokens.
注意：以上Int4/Int8模型生成速度使用autogptq库给出，当前``AutoModelForCausalLM.from_pretrained``载入的模型生成速度会慢大约20%。我们已经将该问题汇报给HuggingFace团队，若有解决方案将即时更新。
Note: The generation speed of the Int4/Int8 models mentioned above is provided by the autogptq library. The current speed of the model loaded using "AutoModelForCausalLM.from_pretrained" will be approximately 20% slower. We have reported this issue to the HuggingFace team and will update it promptly if a solution is available.
### 显存使用 (GPU Memory Usage)
我们还测算了不同模型精度编码2048个token及生成8192个token的峰值显存占用情况。（显存消耗在是否使用FlashAttn的情况下均类似。）结果如下所示：
We also profile the peak GPU memory usage for encoding 2048 tokens as context (and generating single token) and generating 8192 tokens (with single token as context) under different quantization levels, respectively. （The GPU memory usage is similar when using flash-attention or not.）The results are shown below.
| Quantization Level | Peak Usage for Encoding 2048 Tokens | Peak Usage for Generating 8192 Tokens |
| ------------------ | :---------------------------------: | :-----------------------------------: |
| BF16 | 30.15GB | 38.94GB |
| Int8 | 18.81GB | 27.54GB |
| Int4 | 13.01GB | 21.79GB |
上述性能测算使用[此脚本](https://qianwen-res.oss-cn-beijing.aliyuncs.com/profile.py)完成。
The above speed and memory profiling are conducted using [this script](https://qianwen-res.oss-cn-beijing.aliyuncs.com/profile.py).
<br>
## 模型细节（Model）
与Qwen-14B预训练模型相同，Qwen-14B-Chat模型规模基本情况如下所示
The details of the model architecture of Qwen-14B-Chat are listed as follows
| Hyperparameter | Value |
|:----------------|:------:|
| n_layers | 40 |
| n_heads | 40 |
| d_model | 5120 |
| vocab size | 151851 |
| sequence length | 2048 |
在位置编码、FFN激活函数和normalization的实现方式上，我们也采用了目前最流行的做法，
即RoPE相对位置编码、SwiGLU激活函数、RMSNorm（可选安装flash-attention加速）。
在分词器方面，相比目前主流开源模型以中英词表为主，Qwen-14B-Chat使用了约15万token大小的词表。
该词表在GPT-4使用的BPE词表`cl100k_base`基础上，对中文、多语言进行了优化，在对中、英、代码数据的高效编解码的基础上，对部分多语言更加友好，方便用户在不扩展词表的情况下对部分语种进行能力增强。
词表对数字按单个数字位切分。调用较为高效的[tiktoken分词库](https://github.com/openai/tiktoken)进行分词。
For position encoding, FFN activation function, and normalization calculation methods, we adopt the prevalent practices, i.e., RoPE relative position encoding, SwiGLU for activation function, and RMSNorm for normalization (optional installation of flash-attention for acceleration).
For tokenization, compared to the current mainstream open-source models based on Chinese and English vocabularies, Qwen-14B-Chat uses a vocabulary of over 150K tokens.
It first considers efficient encoding of Chinese, English, and code data, and is also more friendly to multilingual languages, enabling users to directly enhance the capability of some languages without expanding the vocabulary.
It segments numbers by single digit, and calls the [tiktoken](https://github.com/openai/tiktoken) tokenizer library for efficient tokenization.
<br>
## 评测效果（Evaluation）
对于Qwen-14B-Chat模型，我们同样评测了常规的中文理解（C-Eval）、英文理解（MMLU）、代码（HumanEval）和数学（GSM8K）等权威任务，同时包含了长序列任务的评测结果。由于Qwen-14B-Chat模型经过对齐后，激发了较强的外部系统调用能力，我们还进行了工具使用能力方面的评测。
提示：由于硬件和框架造成的舍入误差，复现结果如有波动属于正常现象。
For Qwen-14B-Chat, we also evaluate the model on C-Eval, MMLU, HumanEval, GSM8K, etc., as well as the benchmark evaluation for long-context understanding, and tool usage.
Note: Due to rounding errors caused by hardware and framework, differences in reproduced results are possible.
### 中文评测（Chinese Evaluation）
#### C-Eval
在[C-Eval](https://arxiv.org/abs/2305.08322)验证集上，我们评价了Qwen-14B-Chat模型的0-shot & 5-shot准确率
We demonstrate the 0-shot & 5-shot accuracy of Qwen-14B-Chat on C-Eval validation set
| Model | Avg. Acc. |
|:--------------------------------:|:---------:|
| LLaMA2-7B-Chat | 31.9 |
| LLaMA2-13B-Chat | 36.2 |
| LLaMA2-70B-Chat | 44.3 |
| ChatGLM2-6B-Chat | 52.6 |
| InternLM-7B-Chat | 53.6 |
| Baichuan2-7B-Chat | 55.6 |
| Baichuan2-13B-Chat | 56.7 |
| Qwen-7B-Chat (original) (0-shot) | 54.2 |
| **Qwen-7B-Chat (0-shot)** | 59.7 |
| **Qwen-7B-Chat (5-shot)** | 59.3 |
| **Qwen-14B-Chat (0-shot)** | 69.8 |
| **Qwen-14B-Chat (5-shot)** | **71.7** |
C-Eval测试集上，Qwen-14B-Chat模型的zero-shot准确率结果如下：
The zero-shot accuracy of Qwen-14B-Chat on C-Eval testing set is provided below:
| Model | Avg. | STEM | Social Sciences | Humanities | Others |
| :---------------------- | :------: | :--: | :-------------: | :--------: | :----: |
| Chinese-Alpaca-Plus-13B | 41.5 | 36.6 | 49.7 | 43.1 | 41.2 |
| Chinese-Alpaca-2-7B | 40.3 | - | - | - | - |
| ChatGLM2-6B-Chat | 50.1 | 46.4 | 60.4 | 50.6 | 46.9 |
| Baichuan-13B-Chat | 51.5 | 43.7 | 64.6 | 56.2 | 49.2 |
| Qwen-7B-Chat (original) | 54.6 | 47.8 | 67.6 | 59.3 | 50.6 |
| **Qwen-7B-Chat** | 58.6 | 53.3 | 72.1 | 62.8 | 52.0 |
| **Qwen-14B-Chat** | **69.1** | 65.1 | 80.9 | 71.2 | 63.4 |
在14B规模模型上，经过人类指令对齐的Qwen-14B-Chat模型，准确率在同类相近规模模型中仍然处于前列。
Compared with other pretrained models with comparable model size, the human-aligned Qwen-14B-Chat performs well in C-Eval accuracy.
### 英文评测（English Evaluation）
#### MMLU
[MMLU](https://arxiv.org/abs/2009.03300)评测集上，Qwen-14B-Chat模型的 0-shot & 5-shot 准确率如下，效果同样在同类对齐模型中同样表现较优。
The 0-shot & 5-shot accuracy of Qwen-14B-Chat on MMLU is provided below.
The performance of Qwen-14B-Chat still on the top between other human-aligned models with comparable size.
| Model | Avg. Acc. |
|:--------------------------------:|:---------:|
| ChatGLM2-6B-Chat | 46.0 |
| LLaMA2-7B-Chat | 46.2 |
| InternLM-7B-Chat | 51.1 |
| Baichuan2-7B-Chat | 52.9 |
| LLaMA2-13B-Chat | 54.6 |
| Baichuan2-13B-Chat | 57.3 |
| LLaMA2-70B-Chat | 63.8 |
| Qwen-7B-Chat (original) (0-shot) | 53.9 |
| **Qwen-7B-Chat (0-shot)** | 55.8 |
| **Qwen-7B-Chat (5-shot)** | 57.0 |
| **Qwen-14B-Chat (0-shot)** | 64.6 |
| **Qwen-14B-Chat (5-shot)** | **66.5** |
### 代码评测（Coding Evaluation）
Qwen-14B-Chat在[HumanEval](https://github.com/openai/human-eval)的zero-shot Pass@1效果如下
The zero-shot Pass@1 of Qwen-14B-Chat on [HumanEval](https://github.com/openai/human-eval) is demonstrated below
| Model | Pass@1 |
|:-----------------------:|:--------:|
| ChatGLM2-6B-Chat | 11.0 |
| LLaMA2-7B-Chat | 12.2 |
| InternLM-7B-Chat | 14.6 |
| Baichuan2-7B-Chat | 13.4 |
| LLaMA2-13B-Chat | 18.9 |
| Baichuan2-13B-Chat | 17.7 |
| LLaMA2-70B-Chat | 32.3 |
| Qwen-7B-Chat (original) | 24.4 |
| **Qwen-7B-Chat** | 37.2 |
| **Qwen-14B-Chat** | **43.9** |
### 数学评测（Mathematics Evaluation）
在评测数学能力的[GSM8K](https://github.com/openai/grade-school-math)上，Qwen-14B-Chat的准确率结果如下
The accuracy of Qwen-14B-Chat on GSM8K is shown below
| Model | Acc. |
|:--------------------------------:|:--------:|
| LLaMA2-7B-Chat | 26.3 |
| ChatGLM2-6B-Chat | 28.8 |
| Baichuan2-7B-Chat | 32.8 |
| InternLM-7B-Chat | 33.0 |
| LLaMA2-13B-Chat | 37.1 |
| Baichuan2-13B-Chat | 55.3 |
| LLaMA2-70B-Chat | 59.3 |
| Qwen-7B-Chat (original) (0-shot) | 41.1 |
| **Qwen-7B-Chat (0-shot)** | 50.3 |
| **Qwen-7B-Chat (8-shot)** | 54.1 |
| **Qwen-14B-Chat (0-shot)** | **60.1** |
| **Qwen-14B-Chat (8-shot)** | 59.3 |
### 长序列评测（Long-Context Understanding）
通过NTK插值，LogN注意力缩放可以扩展Qwen-14B-Chat的上下文长度。在长文本摘要数据集[VCSUM](https://arxiv.org/abs/2305.05280)上（文本平均长度在15K左右），Qwen-14B-Chat的Rouge-L结果如下：
**(若要启用这些技巧，请将config.json里的`use_dynamic_ntk`和`use_logn_attn`设置为true)**
We introduce NTK-aware interpolation, LogN attention scaling to extend the context length of Qwen-14B-Chat. The Rouge-L results of Qwen-14B-Chat on long-text summarization dataset [VCSUM](https://arxiv.org/abs/2305.05280) (The average length of this dataset is around 15K) are shown below:
**(To use these tricks, please set `use_dynamic_ntk` and `use_long_attn` to true in config.json.)**
| Model | VCSUM (zh) |
|:------------------|:----------:|
| GPT-3.5-Turbo-16k | 16.0 |
| LLama2-7B-Chat | 0.2 |
| InternLM-7B-Chat | 13.0 |
| ChatGLM2-6B-Chat | 16.3 |
| **Qwen-14B-Chat** | **17.3** |
### 工具使用能力的评测（Tool Usage）
#### ReAct Prompting
千问支持通过 [ReAct Prompting](https://arxiv.org/abs/2210.03629) 调用插件/工具/API。ReAct 也是 [LangChain](https://python.langchain.com/) 框架采用的主要方式之一。在我们开源的、用于评估工具使用能力的评测基准上，千问的表现如下：
Qwen-Chat supports calling plugins/tools/APIs through [ReAct Prompting](https://arxiv.org/abs/2210.03629). ReAct is also one of the main approaches used by the [LangChain](https://python.langchain.com/) framework. In our evaluation benchmark for assessing tool usage capabilities, Qwen-Chat's performance is as follows:
<table>
<tr>
<th colspan="4" align="center">Chinese Tool-Use Benchmark</th>
</tr>
<tr>
<th align="center">Model</th><th align="center">Tool Selection (Acc.↑)</th><th align="center">Tool Input (Rouge-L↑)</th><th align="center">False Positive Error↓</th>
</tr>
<tr>
<td>GPT-4</td><td align="center">95%</td><td align="center">0.90</td><td align="center">15.0%</td>
</tr>
<tr>
<td>GPT-3.5</td><td align="center">85%</td><td align="center">0.88</td><td align="center">75.0%</td>
</tr>
<tr>
<td>Qwen-7B-Chat</td><td align="center">98%</td><td align="center">0.91</td><td align="center">7.3%</td>
</tr>
<tr>
<td>Qwen-14B-Chat</td><td align="center">98%</td><td align="center">0.93</td><td align="center">2.4%</td>
</tr>
</table>
> 评测基准中出现的插件均没有出现在千问的训练集中。该基准评估了模型在多个候选插件中选择正确插件的准确率、传入插件的参数的合理性、以及假阳率。假阳率（False Positive）定义：在处理不该调用插件的请求时，错误地调用了插件。
> The plugins that appear in the evaluation set do not appear in the training set of Qwen. This benchmark evaluates the accuracy of the model in selecting the correct plugin from multiple candidate plugins, the rationality of the parameters passed into the plugin, and the false positive rate. False Positive: Incorrectly invoking a plugin when it should not have been called when responding to a query.
#### Code Interpreter
为了考察Qwen使用Python Code Interpreter完成数学解题、数据可视化、及文件处理与爬虫等任务的能力，我们专门建设并开源了一个评测这方面能力的[评测基准](https://github.com/QwenLM/Qwen-Agent/tree/main/benchmark)。
我们发现Qwen在生成代码的可执行率、结果正确性上均表现较好：
To assess Qwen's ability to use the Python Code Interpreter for tasks such as mathematical problem solving, data visualization, and other general-purpose tasks such as file handling and web scraping, we have created and open-sourced a benchmark specifically designed for evaluating these capabilities. You can find the benchmark at this [link](https://github.com/QwenLM/Qwen-Agent/tree/main/benchmark).
We have observed that Qwen performs well in terms of code executability and result accuracy when generating code:
<table>
<tr>
<th colspan="4" align="center">Executable Rate of Generated Code (%)</th>
</tr>
<tr>
<th align="center">Model</th><th align="center">Math↑</th><th align="center">Visualization↑</th><th align="center">General↑</th>
</tr>
<tr>
<td>GPT-4</td><td align="center">91.9</td><td align="center">85.9</td><td align="center">82.8</td>
</tr>
<tr>
<td>GPT-3.5</td><td align="center">89.2</td><td align="center">65.0</td><td align="center">74.1</td>
</tr>
<tr>
<td>LLaMA2-7B-Chat</td>
<td align="center">41.9</td>
<td align="center">33.1</td>
<td align="center">24.1 </td>
</tr>
<tr>
<td>LLaMA2-13B-Chat</td>
<td align="center">50.0</td>
<td align="center">40.5</td>
<td align="center">48.3 </td>
</tr>
<tr>
<td>CodeLLaMA-7B-Instruct</td>
<td align="center">85.1</td>
<td align="center">54.0</td>
<td align="center">70.7 </td>
</tr>
<tr>
<td>CodeLLaMA-13B-Instruct</td>
<td align="center">93.2</td>
<td align="center">55.8</td>
<td align="center">74.1 </td>
</tr>
<tr>
<td>InternLM-7B-Chat-v1.1</td>
<td align="center">78.4</td>
<td align="center">44.2</td>
<td align="center">62.1 </td>
</tr>
<tr>
<td>InternLM-20B-Chat</td>
<td align="center">70.3</td>
<td align="center">44.2</td>
<td align="center">65.5 </td>
</tr>
<tr>
<td>Qwen-7B-Chat</td>
<td align="center">82.4</td>
<td align="center">64.4</td>
<td align="center">67.2 </td>
</tr>
<tr>
<td>Qwen-14B-Chat</td>
<td align="center">89.2</td>
<td align="center">84.1</td>
<td align="center">65.5</td>
</tr>
</table>
<table>
<tr>
<th colspan="4" align="center">Accuracy of Code Execution Results (%)</th>
</tr>
<tr>
<th align="center">Model</th><th align="center">Math↑</th><th align="center">Visualization-Hard↑</th><th align="center">Visualization-Easy↑</th>
</tr>
<tr>
<td>GPT-4</td><td align="center">82.8</td><td align="center">66.7</td><td align="center">60.8</td>
</tr>
<tr>
<td>GPT-3.5</td><td align="center">47.3</td><td align="center">33.3</td><td align="center">55.7</td>
</tr>
<tr>
<td>LLaMA2-7B-Chat</td>
<td align="center">3.9</td>
<td align="center">14.3</td>
<td align="center">39.2 </td>
</tr>
<tr>
<td>LLaMA2-13B-Chat</td>
<td align="center">8.3</td>
<td align="center">8.3</td>
<td align="center">40.5 </td>
</tr>
<tr>
<td>CodeLLaMA-7B-Instruct</td>
<td align="center">14.3</td>
<td align="center">26.2</td>
<td align="center">60.8 </td>
</tr>
<tr>
<td>CodeLLaMA-13B-Instruct</td>
<td align="center">28.2</td>
<td align="center">27.4</td>
<td align="center">62.0 </td>
</tr>
<tr>
<td>InternLM-7B-Chat-v1.1</td>
<td align="center">28.5</td>
<td align="center">4.8</td>
<td align="center">40.5 </td>
</tr>
<tr>
<td>InternLM-20B-Chat</td>
<td align="center">34.6</td>
<td align="center">21.4</td>
<td align="center">45.6 </td>
</tr>
<tr>
<td>Qwen-7B-Chat</td>
<td align="center">41.9</td>
<td align="center">40.5</td>
<td align="center">54.4 </td>
</tr>
<tr>
<td>Qwen-14B-Chat</td>
<td align="center">58.4</td>
<td align="center">53.6</td>
<td align="center">59.5</td>
</tr>
</table>
<p align="center">
<br>
<img src="assets/code_interpreter_showcase_001.jpg" />
<br>
<p>
#### Huggingface Agent
千问还具备作为 [HuggingFace Agent](https://huggingface.co/docs/transformers/transformers_agents) 的能力。它在 Huggingface 提供的run模式评测基准上的表现如下：
Qwen-Chat also has the capability to be used as a [HuggingFace Agent](https://huggingface.co/docs/transformers/transformers_agents). Its performance on the run-mode benchmark provided by HuggingFace is as follows:
<table>
<tr>
<th colspan="4" align="center">HuggingFace Agent Benchmark- Run Mode</th>
</tr>
<tr>
<th align="center">Model</th><th align="center">Tool Selection↑</th><th align="center">Tool Used↑</th><th align="center">Code↑</th>
</tr>
<tr>
<td>GPT-4</td><td align="center">100</td><td align="center">100</td><td align="center">97.4</td>
</tr>
<tr>
<td>GPT-3.5</td><td align="center">95.4</td><td align="center">96.3</td><td align="center">87.0</td>
</tr>
<tr>
<td>StarCoder-Base-15B</td><td align="center">86.1</td><td align="center">87.0</td><td align="center">68.9</td>
</tr>
<tr>
<td>StarCoder-15B</td><td align="center">87.0</td><td align="center">88.0</td><td align="center">68.9</td>
</tr>
<tr>
<td>Qwen-7B-Chat</td><td align="center">87.0</td><td align="center">87.0</td><td align="center">71.5</td>
</tr>
<tr>
<td>Qwen-14B-Chat</td><td align="center">93.5</td><td align="center">94.4</td><td align="center">87.0</td>
</tr>
</table>
<table>
<tr>
<th colspan="4" align="center">HuggingFace Agent Benchmark - Chat Mode</th>
</tr>
<tr>
<th align="center">Model</th><th align="center">Tool Selection↑</th><th align="center">Tool Used↑</th><th align="center">Code↑</th>
</tr>
<tr>
<td>GPT-4</td><td align="center">97.9</td><td align="center">97.9</td><td align="center">98.5</td>
</tr>
<tr>
<td>GPT-3.5</td><td align="center">97.3</td><td align="center">96.8</td><td align="center">89.6</td>
</tr>
<tr>
<td>StarCoder-Base-15B</td><td align="center">97.9</td><td align="center">97.9</td><td align="center">91.1</td>
</tr>
<tr>
<td>StarCoder-15B</td><td align="center">97.9</td><td align="center">97.9</td><td align="center">89.6</td>
</tr>
<tr>
<td>Qwen-7B-Chat</td><td align="center">94.7</td><td align="center">94.7</td><td align="center">85.1</td>
</tr>
<tr>
<td>Qwen-14B-Chat</td><td align="center">97.9</td><td align="center">97.9</td><td align="center">95.5</td>
</tr>
</table>
<br>
## FAQ
如遇到问题，敬请查阅[FAQ](https://github.com/QwenLM/Qwen/blob/main/FAQ_zh.md)以及issue区，如仍无法解决再提交issue。
If you meet problems, please refer to [FAQ](https://github.com/QwenLM/Qwen/blob/main/FAQ.md) and the issues first to search a solution before you launch a new issue.
<br>
## 引用 (Citation)
如果你觉得我们的工作对你有帮助，欢迎引用！
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
```
<br>
## 使用协议（License Agreement）
我们的代码和模型权重对学术研究完全开放，并支持商用。请查看[LICENSE](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT)了解具体的开源协议细节。如需商用，欢迎填写[问卷](https://dashscope.console.aliyun.com/openModelApply/Qwen-14B-Chat)申请。
Our code and checkpoints are open to research purpose, and they are allowed for commercial purposes. Check [LICENSE](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) for more details about the license. If you have requirements for commercial use, please fill out the [form](https://dashscope.console.aliyun.com/openModelApply/Qwen-14B-Chat) to apply.
<br>
## 联系我们（Contact Us）
如果你想给我们的研发团队和产品团队留言，欢迎加入我们的微信群、钉钉群以及Discord！同时，也欢迎通过邮件（[email protected]）联系我们。
If you are interested to leave a message to either our research team or product team, join our Discord or WeChat groups! Also, feel free to send an email to [email protected].
|
NbAiLab/nb-sbert-base | NbAiLab | "2024-06-24T15:12:28Z" | 2,709 | 18 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"no",
"dataset:NbAiLab/mnli-norwegian",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
] | sentence-similarity | "2022-11-08T11:58:12Z" | ---
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
datasets: NbAiLab/mnli-norwegian
pipeline_tag: sentence-similarity
widget:
- source_sentence: This is a Norwegian boy
sentences:
- Dette er en norsk gutt
- This is an English boy
- This is a dog
example_title: Cross Language
- source_sentence: Det er noen dyr utenfor vinduet
sentences:
- På utsiden kan jeg høre noen hunder
- Noen mennesker prater utenfor vinduet
- Alle burde ha kjæledyr
example_title: Paraphrases
- source_sentence: En kvinne sitter i en stol
sentences:
- A woman is sitting in a chair
- Hun slapper av og leser i en bok
- Hun løper maraton
example_title: Paraphrases across language
license: apache-2.0
language:
- 'no'
---
# NB-SBERT-BASE
NB-SBERT-BASE is a [SentenceTransformers](https://www.SBERT.net) model trained on a [machine translated version of the MNLI dataset](https://huggingface.co/datasets/NbAiLab/mnli-norwegian), starting from [nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base).
The model maps sentences & paragraphs to a 768 dimensional dense vector space. This vector can be used for tasks like clustering and semantic search. Below we give some examples on how to use the model. The easiest way is to simply measure the cosine distance between two sentences. Sentences that are close to each other in meaning, will have a small cosine distance and a similarity close to 1. The model is trained in such a way that similar sentences in different languages should also be close to each other. Ideally, an English-Norwegian sentence pair should have high similarity.
## Embeddings and Sentence Similarity (Sentence-Transformers)
As seen above, using the library [sentence-transformers](https://www.SBERT.net) makes the use of these models quite convenient:
```bash
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
sentences = ["This is a Norwegian boy", "Dette er en norsk gutt"]
model = SentenceTransformer('NbAiLab/nb-sbert-base')
embeddings = model.encode(sentences)
print(embeddings)
# Compute cosine-similarities with sentence transformers
cosine_scores = util.cos_sim(embeddings[0],embeddings[1])
print(cosine_scores)
# Compute cosine-similarities with SciPy
from scipy import spatial
scipy_cosine_scores = 1 - spatial.distance.cosine(embeddings[0],embeddings[1])
print(scipy_cosine_scores)
# Both should give 0.8250 in the example above.
```
## Embeddings and Sentence Similarity (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can still use the model. First, you pass in 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 a Norwegian boy", "Dette er en norsk gutt"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('NbAiLab/nb-sbert-base')
model = AutoModel.from_pretrained('NbAiLab/nb-sbert-base')
# 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.
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print(embeddings)
# Compute cosine-similarities with SciPy
from scipy import spatial
scipy_cosine_scores = 1 - spatial.distance.cosine(embeddings[0],embeddings[1])
print(scipy_cosine_scores)
# This should give 0.8250 in the example above.
```
## SetFit - Few Shot Classification
[SetFit](https://github.com/huggingface/setfit) is a method for using sentence-transformers to solve one of major problem that all NLP researchers are facing: Too few labeled training examples. The 'nb-sbert-base' can be plugged directly into the SetFit library. Please see [this tutorial](https://huggingface.co/blog/setfit) for how to use this technique.
## Keyword Extraction
The model can be used for extracting keywords from text. The basic technique is to find the words that are most similar to the document. There are various frameworks for doing this. An easy way is to use [KeyBERT](https://github.com/MaartenGr/KeyBERT). This example shows how this can be done.
```bash
pip install keybert
```
```python
from keybert import KeyBERT
from sentence_transformers import SentenceTransformer
sentence_model = SentenceTransformer("NbAiLab/nb-sbert-base")
kw_model = KeyBERT(model=sentence_model)
doc = """
De første nasjonale bibliotek har sin opprinnelse i kongelige samlinger eller en annen framstående myndighet eller statsoverhode.
Et av de første planene for et nasjonalbibliotek i England ble fremmet av den walisiske matematikeren og mystikeren John Dee som
i 1556 presenterte en visjonær plan om et nasjonalt bibliotek for gamle bøker, manuskripter og opptegnelser for dronning Maria I
av England. Hans forslag ble ikke tatt til følge.
"""
kw_model.extract_keywords(doc, stop_words=None)
# [('nasjonalbibliotek', 0.5242), ('bibliotek', 0.4342), ('samlinger', 0.3334), ('statsoverhode', 0.33), ('manuskripter', 0.3061)]
```
The [KeyBERT homepage](https://github.com/MaartenGr/KeyBERT) provides other several interesting examples: combining KeyBERT with stop words, extracting longer phrases, or directly producing highlighted text.
## Topic Modeling
To analyse a group of documents and determine the topics, has a lot of use cases. [BERTopic](https://github.com/MaartenGr/BERTopic) combines the power of sentence transformers with c-TF-IDF to create clusters for easily interpretable topics.
It would take too much time to explain topic modeling here. Instead we recommend that you take a look at the link above, as well as the [documentation](https://maartengr.github.io/BERTopic/index.html). The main adaptation you would need to do to use the Norwegian nb-sbert-base, is to add the following:
```python
topic_model = BERTopic(embedding_model='NbAiLab/nb-sbert-base').fit(docs)
```
## Similarity Search
Another common use case for a SentenceTransformers model is to find relevant documents or passages of documents given a certain query text. In this scenario, it is pretty common to have a vector database that stores the embedding vectors for all our documents. Then, at runtime, an embedding for the query text is generated and compared efficiently against the vector database.
While production vector databases exist, a quick way to experiment with them is by using [`autofaiss`](https://github.com/criteo/autofaiss):
```bash
pip install autofaiss sentence-transformers
```
```python
from autofaiss import build_index
import numpy as np
from sentence_transformers import SentenceTransformer, util
sentences = ["This is a Norwegian boy", "Dette er en norsk gutt", "A red house"]
model = SentenceTransformer('NbAiLab/nb-sbert-base')
embeddings = model.encode(sentences)
index, index_infos = build_index(embeddings, save_on_disk=False)
# Search for the closest matches
query = model.encode(["A young boy"])
_, index_matches = index.search(query, 1)
print(index_matches)
```
# Evaluation and Parameters
## Evaluation
Evaluation results on the sts-test dataset:
| | Pearson | Spearman |
|------------------------|------------|------------|
| Cosine Similarity | **0.8275** | **0.8245** |
| Manhattan Distance | 0.8193 | 0.8182 |
| Euclidean Distance | 0.8190 | 0.8180 |
| Dot Product Similarity | 0.8039 | 0.7951 |
## Training
The model was trained with the parameters:
**DataLoader**:
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 16471 with parameters:
```
{'batch_size': 32}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 1647,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1648,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
The model was trained by Rolv-Arild Braaten and Per Egil Kummervold. Documentation written by Javier de la Rosa, Rov-Arild Braaten and Per Egil Kummervold. |
cross-encoder/quora-distilroberta-base | cross-encoder | "2021-08-05T08:41:31Z" | 2,708 | 1 | transformers | [
"transformers",
"pytorch",
"jax",
"roberta",
"text-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-03-02T23:29:05Z" | ---
license: apache-2.0
---
# Cross-Encoder for Quora Duplicate Questions Detection
This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
## Training Data
This model was trained on the [Quora Duplicate Questions](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) dataset. The model will predict a score between 0 and 1 how likely the two given questions are duplicates.
Note: The model is not suitable to estimate the similarity of questions, e.g. the two questions "How to learn Java" and "How to learn Python" will result in a rahter low score, as these are not duplicates.
## Usage and Performance
Pre-trained models can be used like this:
```
from sentence_transformers import CrossEncoder
model = CrossEncoder('model_name')
scores = model.predict([('Question 1', 'Question 2'), ('Question 3', 'Question 4')])
```
You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class |
timm/resnext50_32x4d.a1h_in1k | timm | "2024-02-10T23:40:53Z" | 2,708 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1611.05431",
"arxiv:1512.03385",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-05T18:56:55Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnext50_32x4d.a1h_in1k
A ResNeXt-B image classification model.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
* grouped 3x3 bottleneck convolutions
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* Based on [ResNet Strikes Back](https://arxiv.org/abs/2110.00476) `A1` recipe
* LAMB optimizer
* Stronger dropout, stochastic depth, and RandAugment than paper `A1` recipe
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 25.0
- GMACs: 4.3
- Activations (M): 14.4
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- **Original:** https://github.com/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('resnext50_32x4d.a1h_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(
'resnext50_32x4d.a1h_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(
'resnext50_32x4d.a1h_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
|
KnutJaegersberg/Walter-Falcon-1B | KnutJaegersberg | "2024-03-04T16:30:00Z" | 2,708 | 3 | transformers | [
"transformers",
"safetensors",
"falcon",
"text-generation",
"custom_code",
"dataset:KnutJaegersberg/Auton",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-09T22:49:08Z" | ---
license: apache-2.0
datasets:
- KnutJaegersberg/Auton
model-index:
- name: Walter-Falcon-1B
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: 31.06
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-Falcon-1B
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: 54.92
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-Falcon-1B
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: 24.58
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-Falcon-1B
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: 38.47
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-Falcon-1B
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: 55.41
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-Falcon-1B
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: 0.0
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-Falcon-1B
name: Open LLM Leaderboard
---
Walter is an unaligned, free thinking AI assistant that has been given time to think about things.
It's trained on instruction datasets with open source licenses.
It covers a lot of tasks, 2/3 of the samples are from large datasets like flan, but also other datasets.
It knows a few tricks, shown by the prompting examples below:
General Prompt Examples:
```
### System:
You are an AI assistant. You will be given a task. Your goal is to complete the task as faithfully as you can. Let’s work this out in a step by step way to be sure we have the right answer. Always respond without hesitation.
### Instruction:
Please answer the following question: Process: - The bat sends out sound waves from their mouth or nose - The sound waves hit an object - Echoes are produced - The echo returns to the bat's ears - The bat hears the echo - The bat can figure out where the object is located. suppose No bats live here happens, how will it affect STRONGER echolocation. Which of the following is the supposed perturbation? - directly impacting a step of the process - indirectly impacting a step of the process - not impacting any step of the process Answer:
### Response:
indirectly impacting a step of the process
```
```
### System:
You are an AI assistant. You will be given a task. Your goal is to complete the task as faithfully as you can. Let’s work this out in a step by step way to be sure we have the right answer. Always respond without hesitation.
### Instruction:
You will be given a text in Russian language which contain different emotion labels from the list - ['joy', ' sadness', 'surprise', 'fear', 'anger']. You need to output the incorrect emotion label, which is irrelevant to the input text. Your answer (i) should contain only one emotion label (ii) should be unambiguous.
### Input:
То чувство, когда идешь домой после 3-х часовой тренировки и в подъезде пахнет запеченной курицей - зачем вы меня дразните :(
### Response:
surprise
```
CoT Prompt Example:
```
### System:
You are an AI assistant. You will be given a task. Your goal is to complete the task as faithfully as you can. Let’s work this out in a step by step way to be sure we have the right answer. Always respond without hesitation.
### Instruction:
In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer. PersonX puts ___ on PersonY's car
### Reasoning:
Since PersonX is putting water on PersonY's car, it could be assumed that the car is on fire.
### Response:
water
```
Summarization Example:
```
### System:
You are an AI assistant. You will be given a task. Your goal is to complete the task as faithfully as you can. Let’s work this out in a step by step way to be sure we have the right answer. Always respond without hesitation.
### Instruction:
Below is a text. Write a comprehensive, concise and coherent summary.
### Input:
Embodied bilingual language, also known as L2 embodiment, is the idea that people mentally simulate their actions, perceptions, and emotions when speaking and understanding a second language (L2) as with their first language (L1). It is closely related to embodied cognition and embodied language processing, both of which only refer to native language thinking and speaking. An example of embodied bilingual language would be situation in which a L1 English speaker learning Spanish as a second language hears the word rápido ("fast") in Spanish while taking notes and then proceeds to take notes more quickly. ==Overview== Embodied bilingual language refers to the role ......
### Response:
Embodied bilingual language, also known as L2 embodiment, is the idea that people mentally simulate their actions, perceptions, and emotions when speaking and understanding a second language (L2) as with their first language (L1). It is closely related to embodied cognition and embodied language processing, both of which only refer to native language thinking and speaking. An example of embodied bilingual language would be situation in which a L1 English speaker learning Spanish as a second language hears the word rápido ("fast") in Spanish while taking notes and then proceeds to take notes more quickly.
```
Essay Example:
```
### System:
You are an AI assistant. You will be given a task. Your goal is to complete the task as faithfully as you can. Let’s work this out in a step by step way to be sure we have the right answer. Always respond without hesitation.
### Instruction:
Write the original essay for the following summary: A sleeveless dress with a round neck is a great day dress and can be worn for both formal and casual occasions. It has a sweetheart neckline and is made from 100% silk. The dress has a chiffon overlay that covers up the miniskirt and still adds to the class of the dress.
### Response:
Sleeveless Dress with a Round Neck Essay Casual wear, day dress, more formal dress The garment is a sleeveless dress with a round neck and has a sweetheart neckline. It has sheer detail on the neckline and on the back. These aspects of design make it suitable to be worn for day and evening occasions. Its great detail and chicness make it suitable for more formal events, ....
```
# [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_KnutJaegersberg__Walter-Falcon-1B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |34.07|
|AI2 Reasoning Challenge (25-Shot)|31.06|
|HellaSwag (10-Shot) |54.92|
|MMLU (5-Shot) |24.58|
|TruthfulQA (0-shot) |38.47|
|Winogrande (5-shot) |55.41|
|GSM8k (5-shot) | 0.00|
|
mradermacher/Pantheon-10.7b-i1-GGUF | mradermacher | "2024-06-07T06:11:35Z" | 2,708 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Gryphe/Pantheon-10.7b",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-06T23:48:51Z" | ---
base_model: Gryphe/Pantheon-10.7b
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Gryphe/Pantheon-10.7b
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Pantheon-10.7b-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-10.7b-i1-GGUF/resolve/main/Pantheon-10.7b.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
<!-- end -->
|
SakuraLLM/GalTransl-7B-v1.5 | SakuraLLM | "2024-06-30T05:40:15Z" | 2,707 | 6 | null | [
"gguf",
"ja",
"zh",
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | "2024-05-22T03:04:31Z" | ---
license: cc-by-nc-sa-4.0
language:
- ja
- zh
---
GalTransl-7B模型是SakuraLLM社区的新成员，由sakuraumi和xd2333共同构建，为视觉小说翻译任务专项优化。模型参数量7B，支持日译简中(jp2zh-cn)。
**GalTransl-7B模型继承sakura模型cc-by-nc-sa 4.0协议，禁止用于商用行为，例如提供付费翻译接口、制作需要以任何方式付费才能获取的补丁、商用翻译等。**
### 特性：
* 为视觉小说翻译任务专项优化。对视觉小说脚本中的行内换行、控制符、ruby注音等符号具有较好的保留能力。
* 尝试在硬件需求、翻译质量与稳定性间取得平衡。模型可以运行在(显存≥6g)的主流游戏显卡上，并获得在整体上优于claude3-haiku、GPT-3.5等大模型的翻译质量和稳定性。
* 专为[GalTransl视觉小说翻译工具](https://github.com/xd2333/GalTransl)适配并调优，支持GPT字典（[字典写法见此](https://github.com/xd2333/GalTransl/wiki/GPT%E5%AD%97%E5%85%B8%E2%80%90sakura-galtransl)）。
### 更新日志：
24.06.30 v1.5：优化了整体的文风
24.05.30 v1.0：初版
### 已知问题：
* GPT字典**不支持英文注释**，且**不支持一词多译写法（"a/b"）**，将在以后的版本尝试改善。
* 需要对原文省略语素进行推理时可能出现事实错误/幻觉。
* 推荐每次翻译**7-10句**
### 量化等级区别：
| 量化等级 | 说明 |
| ---- | ---- |
| IQ4_XS | 小的质量损失，占用更小，但速度比Q4_K慢（6G显存推荐） |
| Q4_K | 小的质量损失（6G显存推荐）|
| Q5_K | 很小的质量损失（6G/8G显存推荐，6G显存可能需要减小窗口大小'-c'） |
| Q6_k | 细小的质量损失（8G及以上显存推荐） |
### 本地部署参考：
https://books.fishhawk.top/forum/656d60530286f15e3384fcf8
### Kaggle部署参考（每周30h免费gpu）：
https://books.fishhawk.top/forum/6630f091c92d3f7ad7f50f23
修改`REPO="SakuraLLM/GalTransl-7B-v1.5"`
修改`MODEL="GalTransl-7B-v1.5-Q6_K.gguf"` |
google/vit-large-patch16-384 | google | "2022-01-28T10:22:26Z" | 2,706 | 9 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"vit",
"image-classification",
"vision",
"dataset:imagenet",
"dataset:imagenet-21k",
"arxiv:2010.11929",
"arxiv:2006.03677",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2022-03-02T23:29:05Z" | ---
license: apache-2.0
tags:
- image-classification
- vision
datasets:
- imagenet
- imagenet-21k
---
# Vision Transformer (large-sized model)
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was introduced in the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Dosovitskiy et al. and first released in [this repository](https://github.com/google-research/vision_transformer). However, the weights were converted from the [timm repository](https://github.com/rwightman/pytorch-image-models) by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him.
Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, at a higher resolution of 384x384.
Images 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 absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.
By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images 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 image.
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=google/vit) to look for
fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
```python
from transformers import ViTFeatureExtractor, ViTForImageClassification
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-large-patch16-384')
model = ViTForImageClassification.from_pretrained('google/vit-large-patch16-384')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
Currently, both the feature extractor and model support PyTorch. Tensorflow and JAX/FLAX are coming soon, and the API of ViTFeatureExtractor might change.
## Training data
The ViT model was pretrained on [ImageNet-21k](http://www.image-net.org/), a dataset consisting of 14 million images and 21k classes, and fine-tuned on [ImageNet](http://www.image-net.org/challenges/LSVRC/2012/), a dataset consisting of 1 million images and 1k classes.
## Training procedure
### Preprocessing
The exact details of preprocessing of images during training/validation can be found [here](https://github.com/google-research/vision_transformer/blob/master/vit_jax/input_pipeline.py).
Images are resized/rescaled to the same resolution (224x224 during pre-training, 384x384 during fine-tuning) and normalized across the RGB channels with mean (0.5, 0.5, 0.5) and standard deviation (0.5, 0.5, 0.5).
### Pretraining
The model was trained on TPUv3 hardware (8 cores). All model variants are trained with a batch size of 4096 and learning rate warmup of 10k steps. For ImageNet, the authors found it beneficial to additionally apply gradient clipping at global norm 1. Pre-training resolution is 224.
## Evaluation results
For evaluation results on several image classification benchmarks, we refer to tables 2 and 5 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution (384x384). Of course, increasing the model size will result in better performance.
### BibTeX entry and citation info
```bibtex
@misc{wu2020visual,
title={Visual Transformers: Token-based Image Representation and Processing for Computer Vision},
author={Bichen Wu and Chenfeng Xu and Xiaoliang Dai and Alvin Wan and Peizhao Zhang and Zhicheng Yan and Masayoshi Tomizuka and Joseph Gonzalez and Kurt Keutzer and Peter Vajda},
year={2020},
eprint={2006.03677},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
```bibtex
@inproceedings{deng2009imagenet,
title={Imagenet: A large-scale hierarchical image database},
author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
booktitle={2009 IEEE conference on computer vision and pattern recognition},
pages={248--255},
year={2009},
organization={Ieee}
}
``` |
Locutusque/Orca-2-13b-SFT_v5 | Locutusque | "2023-12-15T15:22:14Z" | 2,706 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"fr",
"es",
"hi",
"zh",
"code",
"dataset:HuggingFaceH4/no_robots",
"dataset:mlabonne/guanaco-llama2-1k",
"dataset:OpenAssistant/oasst_top1_2023-08-25",
"dataset:totally-not-an-llm/EverythingLM-data-V3",
"dataset:garage-bAInd/Open-Platypus",
"base_model:microsoft/Orca-2-13b",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-13T03:41:38Z" | ---
license: other
language:
- en
- fr
- es
- hi
- zh
- code
base_model: microsoft/Orca-2-13b
datasets:
- HuggingFaceH4/no_robots
- mlabonne/guanaco-llama2-1k
- OpenAssistant/oasst_top1_2023-08-25
- totally-not-an-llm/EverythingLM-data-V3
- garage-bAInd/Open-Platypus
widget:
- example_title: "folklore"
text: "<|im_start|>user\nAre the stories of Nahanni Valley, like the decapitated men, true?\n<|im_end|>\n<|im_start|>assistant\n"
output:
text: "The Nahanni Valley in Canada is a remote and rugged region that has long been shrouded in mystery. It is home to the South Nahanni River, which was designated as a UNESCO World Heritage Site due to its exceptional natural beauty and biodiversity. The valley's history includes tales of gold prospectors, fur traders, and indigenous populations, but it also features some unexplained events and legends. One such story involves two prospectors who allegedly encountered an unknown creature that led them into the forest before returning without their heads. This tale has been passed down through generations, but there are no definitive answers regarding its veracity.\n\nIt is important to note that these stories may have originated from local folklore or were exaggerated over time. There is no concrete evidence to support the existence of supernatural creatures or paranormal occurrences within the Nahanni Valley. Nonetheless, the area remains a captivating destination for those seeking adventure and exploration. If you have any questions about this topic or need assistance related to traveling to the Nahanni Valley, please feel free to ask!"
- example_title: "Alan Turing"
text: "<|im_start|>user\nWhy was Alan Turing castrated?\n<|im_end|>\n<|im_start|>assistant\n"
output:
text: "Alan Turing, a renowned mathematician and computer scientist who played a crucial role in breaking the German Enigma code during World War II, faced significant challenges due to his homosexuality. In 1952, he was convicted of \"gross indecency\" for engaging in a consensual relationship with another man, which led to him being sentenced to hormone therapy designed to reduce his sex drive. This treatment included the administration of estrogen, which had the side effect of causing breast growth.\n\nIn an effort to avoid this unwanted physical change, Turing requested that his doctors cease the hormone treatments. However, they ignored his request and continued the therapy without his consent. As a result, Turing's breasts began to grow, leading him to undergo surgery to remove them. The operation, known as a mastectomy, caused considerable pain and discomfort, further contributing to his emotional turmoil.\n\nIt is important to note that Turing's castration was not directly carried out by the authorities but rather resulted from the unintended consequences of the forced hormone therapy."
---
The "microsoft/Orca-2-13b" model fully fine-tuned on HuggingFaceH4/no_robots, totally-not-an-llm/EverythingLM-data-V3, mlabonne/guanaco-llama2-1k, OpenAssistant/oasst_top1_2023-08-25, and garage-bAInd/Open-Platypus. This model achieved a test loss of 0.38 on garage-bAInd/Open-Platypus.
Make sure to comply with the microsoft research license. Please read it before using this model.
This model was trained on the ChatML prompt template.
The responses seen in the inference API were generated using the following sampling parameters:
temperature = 0.1
top_p = 0.14
top_k = 41
repetition_penalty = 1.176
|
backyardai/Chaifighter-20B-v2-GGUF | backyardai | "2024-05-22T22:27:08Z" | 2,705 | 5 | null | [
"gguf",
"base_model:matchaaaaa/Chaifighter-20B-v2",
"region:us"
] | null | "2024-05-19T07:50:46Z" | ---
base_model: matchaaaaa/Chaifighter-20B-v2
model_name: Chaifighter-20b-GGUF-v2
quantized_by: brooketh
---
<img src="BackyardAI_Banner.png" alt="Backyard.ai" style="height: 90px; min-width: 32px; display: block; margin: auto;">
**<p style="text-align: center;">The official library of GGUF format models for use in the local AI chat app, Backyard AI.</p>**
<p style="text-align: center;"><a href="https://backyard.ai/">Download Backyard AI here to get started.</a></p>
<p style="text-align: center;"><a href="https://www.reddit.com/r/LLM_Quants/">Request Additional models at r/LLM_Quants.</a></p>
***
# Chaifighter 20B v2
- **Creator:** [matchaaaaa](https://huggingface.co/matchaaaaa/)
- **Original:** [Chaifighter 20B v2](https://huggingface.co/matchaaaaa/Chaifighter-20B-v2)
- **Date Created:** 2024-05-19
- **Trained Context:** 4096 tokens
- **Description:** Medium-sized model geared towards long-form verbose roleplay chats. Designed to be a very creative and rich storyteller while retaining reasoning, coherence, and context-following capabilities. May be considerably quicker than comparably-sized models on most hardware. With v2 comes better long context performance and quality fixes.
***
## What is a GGUF?
GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Backyard AI. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware.
GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.
***
<img src="BackyardAI_Logo.png" alt="Backyard.ai" style="height: 75px; min-width: 32px; display: block; horizontal align: left;">
## Backyard AI
- Free, local AI chat application.
- One-click installation on Mac and PC.
- Automatically use GPU for maximum speed.
- Built-in model manager.
- High-quality character hub.
- Zero-config desktop-to-mobile tethering.
Backyard AI makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models without worrying about whether it's the correct format. Backyard AI supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable.
**Join us on [Discord](https://discord.gg/SyNN2vC9tQ)**
*** |
tiiuae/falcon-11B-vlm | tiiuae | "2024-06-12T10:10:24Z" | 2,705 | 30 | transformers | [
"transformers",
"safetensors",
"llava_next",
"pretraining",
"en",
"license:unknown",
"region:us"
] | null | "2024-05-21T08:24:24Z" | ---
language:
- en
inference: false
license: unknown
---
# 🚀 Falcon2-11B-vlm
**Falcon2-11B-vlm is an 11B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on over 5,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. To bring vision capabilities, we integrate the pretrained CLIP ViT-L/14 vision encoder with our Falcon2-11B chat-finetuned model and train with image-text data.
For enhancing the VLM's perception of fine-grained details w.r.t small objects in images, we employ a dynamic encoding mechanism at high-resolution for image inputs. The model is made available under the [TII Falcon License 2.0](https://falconllm-staging.tii.ae/falcon-2-terms-and-conditions.html), the permissive Apache 2.0-based software license which includes an [acceptable use policy](https://falconllm-staging.tii.ae/falcon-2-acceptable-use-policy.html) that promotes the responsible use of AI.**
*Paper coming soon 😊.*
🤗 To get started with Falcon-vlm (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost from HF](https://huggingface.co/blog/falcon)!
```python
from transformers import LlavaNextForConditionalGeneration, LlavaNextProcessor
from PIL import Image
import requests
import torch
processor = LlavaNextProcessor.from_pretrained("tiiuae/falcon-11B-vlm", tokenizer_class='PreTrainedTokenizerFast')
model = LlavaNextForConditionalGeneration.from_pretrained("tiiuae/falcon-11B-vlm", torch_dtype=torch.bfloat16)
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
cats_image = Image.open(requests.get(url, stream=True).raw)
instruction = 'Write a long paragraph about this picture.'
prompt = f"""User:<image>\n{instruction} Falcon:"""
inputs = processor(prompt, images=cats_image, return_tensors="pt", padding=True).to('cuda:0')
model.to('cuda:0')
output = model.generate(**inputs, max_new_tokens=256)
prompt_length = inputs['input_ids'].shape[1]
generated_captions = processor.decode(output[0], skip_special_tokens=True).strip()
print(generated_captions)
```
💥 **Falcon VLMs require PyTorch 2.0 for use with `transformers`!**
For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost](https://huggingface.co/blog/falcon).
# Model Card for Falcon2-11B-VLM
## Model Details
### Model Description
- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
- **Model type:** Causal decoder-only
- **Language(s) (NLP):** English.
- **License:** [TII Falcon License 2.0](https://falconllm-staging.tii.ae/falcon-2-terms-and-conditions.html)
### Model Source
- **Paper:** *coming soon*.
## Uses
### Direct Use
Research on General large vison language models.
### Out-of-Scope Use
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
## Bias, Risks, and Limitations
Falcon2-11B is trained mostly on English, but also German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish. It will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
## Training Details
The training is done in two stages: pretraining and finetuning. In both stages, the visual encoder weights are kept frozen. In the pretraining stage, the LLM is kept frozen and only the multimodal projector is trained on 558K image-caption pairs.
This enables the multimodal projector to learn a mapping from visual to text embedding space. During finetuning, both the projector and LLM weights are trained on a corpus of 1.2M image-text instruction data from public datasets, which also includes multi-round conversations.
Falcon2-11B-VLM was trained on 16 A100 80GB GPUs with ZeRO and Flash-Attention 2.
The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[11B](https://huggingface.co/tiiuae/falcon-11B) tokenizer.
#### Training Hyperparameters
| **Hyperparameter** | **Value** |
|--------------------|------------|
| Precision | `bfloat16`|
| Optimizer | AdamW |
| Max learning rate | 2e-5 |
| Weight decay | 0 |
| Batch size | 256 |
## Evaluation
| Model | MME | GQA | SQA | POPE | VQAv2 | TextVQA | MM-Bench | SEED-IMG |
|----|----|----|----|----|----|----|----|----|
| Falcon2-11B VLM | 1589/343 | 64.5 | 74.9 | 88.4 | 82.1 | 66.7 | 72.0 | 72.3 |
## Citation
*Paper coming soon* 😊.
## License
Falcon2-11B is licenced under [TII Falcon License 2.0](https://falconllm-staging.tii.ae/falcon-2-terms-and-conditions.html), the permissive Apache 2.0-based software license which includes an [acceptable use policy](https://falconllm-staging.tii.ae/falcon-2-acceptable-use-policy.html) that promotes the responsible use of AI.
## Contact
[email protected] |
KnutJaegersberg/falcon-1b-t-sft | KnutJaegersberg | "2024-03-04T16:27:44Z" | 2,704 | 0 | transformers | [
"transformers",
"safetensors",
"falcon",
"text-generation",
"custom_code",
"dataset:KnutJaegersberg/trilobite",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-04T06:19:03Z" | ---
license: cc-by-nc-4.0
datasets:
- KnutJaegersberg/trilobite
model-index:
- name: falcon-1b-t-sft
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: 32.94
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
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: 57.24
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
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: 25.26
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
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: 38.49
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
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: 55.88
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
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: 0.3
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
name: Open LLM Leaderboard
---
Made for the purpose of comparison with the tinyllama model. 3 epochs, neftune on trilobite.
Prompt Example:
```
### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### Instruction:
How do you fine tune a large language model?
### Response:
```
# [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_KnutJaegersberg__falcon-1b-t-sft)
| Metric |Value|
|---------------------------------|----:|
|Avg. |35.02|
|AI2 Reasoning Challenge (25-Shot)|32.94|
|HellaSwag (10-Shot) |57.24|
|MMLU (5-Shot) |25.26|
|TruthfulQA (0-shot) |38.49|
|Winogrande (5-shot) |55.88|
|GSM8k (5-shot) | 0.30|
|
mradermacher/Hermes-Sthero-v1-GGUF | mradermacher | "2024-06-16T21:31:30Z" | 2,703 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:lik07/Hermes-Sthero-v1",
"endpoints_compatible",
"region:us"
] | null | "2024-06-16T21:03:31Z" | ---
base_model: lik07/Hermes-Sthero-v1
language:
- en
library_name: transformers
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/lik07/Hermes-Sthero-v1
<!-- 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/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Hermes-Sthero-v1-GGUF/resolve/main/Hermes-Sthero-v1.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 -->
|
TencentARC/t2iadapter_sketch_sd15v2 | TencentARC | "2023-08-01T09:42:42Z" | 2,702 | 5 | diffusers | [
"diffusers",
"art",
"t2i-adapter",
"controlnet",
"stable-diffusion",
"image-to-image",
"arxiv:2302.08453",
"base_model:runwayml/stable-diffusion-v1-5",
"license:apache-2.0",
"region:us"
] | image-to-image | "2023-07-14T19:01:49Z" | ---
license: apache-2.0
base_model: runwayml/stable-diffusion-v1-5
tags:
- art
- t2i-adapter
- controlnet
- stable-diffusion
- image-to-image
---
# T2I Adapter - Sketch
T2I Adapter is a network providing additional conditioning to stable diffusion. Each t2i checkpoint takes a different type of conditioning as input and is used with a specific base stable diffusion checkpoint.
This checkpoint provides conditioning on sketches for the stable diffusion 1.5 checkpoint.
## Model Details
- **Developed by:** T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** Apache 2.0
- **Resources for more information:** [GitHub Repository](https://github.com/TencentARC/T2I-Adapter), [Paper](https://arxiv.org/abs/2302.08453).
- **Cite as:**
@misc{
title={T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models},
author={Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie},
year={2023},
eprint={2302.08453},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
### Checkpoints
| Model Name | Control Image Overview| Control Image Example | Generated Image Example |
|---|---|---|---|
|[TencentARC/t2iadapter_color_sd14v1](https://huggingface.co/TencentARC/t2iadapter_color_sd14v1)<br/> *Trained with spatial color palette* | A image with 8x8 color palette.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"/></a>|
|[TencentARC/t2iadapter_canny_sd14v1](https://huggingface.co/TencentARC/t2iadapter_canny_sd14v1)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"/></a>|
|[TencentARC/t2iadapter_sketch_sd14v1](https://huggingface.co/TencentARC/t2iadapter_sketch_sd14v1)<br/> *Trained with [PidiNet](https://github.com/zhuoinoulu/pidinet) edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"/></a>|
|[TencentARC/t2iadapter_depth_sd14v1](https://huggingface.co/TencentARC/t2iadapter_depth_sd14v1)<br/> *Trained with Midas depth estimation* | A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"/></a>|
|[TencentARC/t2iadapter_openpose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_openpose_sd14v1)<br/> *Trained with OpenPose bone image* | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"/></a>|
|[TencentARC/t2iadapter_keypose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_keypose_sd14v1)<br/> *Trained with mmpose skeleton image* | A [mmpose skeleton](https://github.com/open-mmlab/mmpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"/></a>|
|[TencentARC/t2iadapter_seg_sd14v1](https://huggingface.co/TencentARC/t2iadapter_seg_sd14v1)<br/>*Trained with semantic segmentation* | An [custom](https://github.com/TencentARC/T2I-Adapter/discussions/25) segmentation protocol image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"/></a> |
|[TencentARC/t2iadapter_canny_sd15v2](https://huggingface.co/TencentARC/t2iadapter_canny_sd15v2)||
|[TencentARC/t2iadapter_depth_sd15v2](https://huggingface.co/TencentARC/t2iadapter_depth_sd15v2)||
|[TencentARC/t2iadapter_sketch_sd15v2](https://huggingface.co/TencentARC/t2iadapter_sketch_sd15v2)||
|[TencentARC/t2iadapter_zoedepth_sd15v1](https://huggingface.co/TencentARC/t2iadapter_zoedepth_sd15v1)||
## Example
1. Dependencies
```sh
pip install diffusers transformers controlnet_aux
```
2. Run code:
```python
import torch
from PIL import Image
from controlnet_aux import PidiNetDetector
from diffusers import (
T2IAdapter,
StableDiffusionAdapterPipeline
)
image = Image.open('./images/sketch_in.png')
processor = PidiNetDetector.from_pretrained('lllyasviel/Annotators')
sketch_image = processor(image)
sketch_image.save('./images/sketch.png')
adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_zoedepth_sd15v1", torch_dtype=torch.float16)
pipe = StableDiffusionAdapterPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", adapter=adapter, safety_checker=None, torch_dtype=torch.float16, variant="fp16"
)
pipe.to('cuda')
generator = torch.Generator().manual_seed(0)
sketch_image_out = pipe(prompt="royal chamber with fancy bed", image=sketch_image, generator=generator).images[0]
sketch_image_out.save('./images/sketch_image_out.png')
```
 |
mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF | mradermacher | "2024-06-16T16:24:47Z" | 2,702 | 0 | transformers | [
"transformers",
"gguf",
"llama-factory",
"en",
"dataset:Gryphe/Opus-WritingPrompts",
"base_model:nothingiisreal/L3-8B-dolphin-2.9.1-WritingPrompts",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | "2024-06-16T01:52:22Z" | ---
base_model: nothingiisreal/L3-8B-dolphin-2.9.1-WritingPrompts
datasets:
- Gryphe/Opus-WritingPrompts
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- llama-factory
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/nothingiisreal/L3-8B-dolphin-2.9.1-WritingPrompts
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-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/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/L3-8B-dolphin-2.9.1-WritingPrompts-GGUF/resolve/main/L3-8B-dolphin-2.9.1-WritingPrompts.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 -->
|
ai-forever/RuM2M100-1.2B | ai-forever | "2023-10-22T08:43:39Z" | 2,701 | 7 | transformers | [
"transformers",
"pytorch",
"m2m_100",
"text2text-generation",
"spellchecking",
"M2M100",
"natural language generation",
"ru",
"arxiv:2308.09435",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2023-07-26T14:47:03Z" | ---
language:
- ru
tags:
- spellchecking
- M2M100
- pytorch
- natural language generation
license: mit
---
# RuM2M100-1.2B model
### Summary
The model corrects spelling errors and typos by bringing all the words in the text to the norm of the Russian language.
Corrector was trained based on the model [M2M100-1.2B](https://huggingface.co/facebook/m2m100_1.2B).
An extensive dataset with “artificial” errors was taken as a training corpus: the corpus was assembled on the basis of the Russian-language Wikipedia and transcripts of Russian-language videos, then typos and spelling errors were automatically introduced into it using the library [SAGE](https://github.com/ai-forever/sage).
### Public references
- [SAGE library announcement](https://youtu.be/yFfkV0Qjuu0), DataFest 2023
- [Paper about synthetic error generation methods](https://www.dialog-21.ru/media/5914/martynovnplusetal056.pdf), Dialogue 2023
- [Paper about SAGE and our best solution](https://arxiv.org/abs/2308.09435), Review EACL 2024
### Examples
| Input | Output |
| --- | --- |
| Думю ешцъа лет череа 10 ретроспективно просматривотьэ то будкетцц мне невероя тна ин те р но | Думаю что лет через 10 ретроспективно просматривать это будет мне невероятно интересно |
| Основая цель мероприятия - практическая отработка навыков по оказанию помощи гражданам, попавшим в ДТП, а также повышение и совершенствование уровня профессиональной подготовки сотрудников МЧС при проведении аварийно-спасательных работ по ликвидации последствий дорожно-транспортных проишествий, сокращение временных показателей реагирования. | Основная цель мероприятия - практическая отработка навыков по оказанию помощи гражданам, попавшим в ДТП, а также повышение и совершенствование уровня профессиональной подготовки сотрудников МЧС при проведении аварийно-спасательных работ по ликвидации последствий дорожно-транспортных происшествий, сокращение временных показателей реагирования. |
| прийдя в МГТУ я был удивлен никого необноружив там… | прийдя в МГТУ я был удивлен никого не обнаружив там... |
| | |
## Metrics
### Quality
Below are automatic metrics for determining the correctness of the spell checkers.
We compare our solution with both open automatic spell checkers and the ChatGPT family of models on all four available datasets:
- **RUSpellRU**: texts collected from ([LiveJournal](https://www.livejournal.com/media)), with manually corrected typos and errors;
- **MultidomainGold**: examples from 7 text sources, including the open web, news, social media, reviews, subtitles, policy documents and literary works;
- **MedSpellChecker**: texts with errors from medical anamnesis;
- **GitHubTypoCorpusRu**: spelling errors and typos in commits from [GitHub](https://github.com);
**RUSpellRU**
| Model | Precision | Recall | F1 |
| --- | --- | --- | --- |
| M2M100-1.2B | 59.4 | 43.3 | 50.1 |
| ChatGPT gpt-3.5-turbo-0301 | 55.8 | 75.3 | 64.1 |
| ChatGPT gpt-4-0314 | 57.0 | 75.9 | 63.9 |
| ChatGPT text-davinci-003 | 55.9 | 75.3 | 64.2 |
| Yandex.Speller | 83.0 | 59.8 | 69.5 |
| JamSpell | 42.1 | 32.8 | 36.9 |
| HunSpell | 31.3 | 34.9 | 33.0 |
**MultidomainGold**
| Model | Precision | Recall | F1 |
| --- | --- | --- | --- |
| M2M100-1.2B | 56.4 | 44.8 | 49.9 |
| ChatGPT gpt-3.5-turbo-0301 | 33.8 | 72.1 | 46.0 |
| ChatGPT gpt-4-0314 | 34.0 | 73.2 | 46.4 |
| ChatGPT text-davinci-003 | 33.6 | 72.0 | 45.8 |
| Yandex.Speller | 52.9 | 51.4 | 52.2 |
| JamSpell | 25.7 | 30.6 | 28.0 |
| HunSpell | 16.2 | 40.1 | 23.0 |
**MedSpellChecker**
| Model | Precision | Recall | F1 |
| --- | --- | --- | --- |
| M2M100-1.2B | 63.7 | 57.8 | 60.6 |
| ChatGPT gpt-3.5-turbo-0301 | 53.2 | 67.6 | 59.6 |
| ChatGPT gpt-4-0314 | 54.2 | 69.4 | 60.9 |
| ChatGPT text-davinci-003 | 47.8 | 68.4 | 56.3 |
| Yandex.Speller | 80.6 | 47.8 | 60.0 |
| JamSpell | 24.6 | 29.7 | 26.9 |
| HunSpell | 10.3 | 40.2 | 16.4 |
**GitHubTypoCorpusRu**
| Model | Precision | Recall | F1 |
| --- | --- | --- | --- |
| M2M100-1.2B | 45.7 | 41.4 | 43.5 |
| ChatGPT gpt-3.5-turbo-0301 | 43.8 | 57.0 | 49.6 |
| ChatGPT gpt-4-0314 | 45.2 | 58.2 | 51.0 |
| ChatGPT text-davinci-003 | 46.5 | 58.1 | 51.7 |
| Yandex.Speller | 67.7 | 37.5 | 48.3 |
| JamSpell | 49.5 | 29.9 | 37.3 |
| HunSpell | 28.5 | 30.7 | 29.6 |
## How to use
```python
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
path_to_model = "ai-forever/RuM2M100-1.2B"
model = M2M100ForConditionalGeneration.from_pretrained(path_to_model)
tokenizer = M2M100Tokenizer.from_pretrained(path_to_model, src_lang="ru", tgt_lang="ru")
sentence = "прийдя в МГТУ я был удивлен никого необноружив там…"
encodings = tokenizer(sentence, return_tensors="pt")
generated_tokens = model.generate(
**encodings, forced_bos_token_id=tokenizer.get_lang_id("ru"))
answer = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
print(answer)
#["прийдя в МГТУ я был удивлен никого не обнаружив там..."]
```
## Resources
- [SAGE library](https://github.com/ai-forever/sage), GitHub
- [ruM2M100-1.2B](https://huggingface.co/ai-forever/RuM2M100-1.2B), HuggingFace
- [ruM2M100-418M](https://huggingface.co/ai-forever/RuM2M100-420M), HuggingFace
- [FredT5-large-spell](https://huggingface.co/ai-forever/FRED-T5-large-spell), HuggingFace
- [T5-large-spell](https://huggingface.co/ai-forever/T5-large-spell), HuggingFace
## License
Model [M2M100-1.2B](https://huggingface.co/facebook/m2m100_1.2B), on the basis of which our solution is made, and its source code are supplied under the MIT open license.
Our solution also comes with MIT license.
## Specifications
- File size: 5 Gb;
- Framework: pytorch
- Format: AI Service
- Version: v1.0
- Developer: SberDevices, AGI NLP
## Contacts
[email protected] |
Niggendar/duchaitenPonyXLNo_ponyNoScoreV10 | Niggendar | "2024-05-24T10:21:47Z" | 2,701 | 3 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-05-24T10:13:41Z" | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
microsoft/Promptist | microsoft | "2023-01-24T17:21:42Z" | 2,700 | 61 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-12-19T07:43:54Z" | # Promptist: reinforcement learning for automatic prompt optimization
## News
- [Demo Release] Dec, 2022: [Demo at HuggingFace Space](https://aka.ms/promptist-demo)
- [Model Release] Dec, 2022: [link](#load-pretrained-model-for-stable-diffusion-v14)
- [Paper Release] Dec, 2022: [Optimizing Prompts for Text-to-Image Generation](https://aka.ms/promptist-paper)
> - Language models serve as a prompt interface that optimizes user input into model-preferred prompts.
> - Learn a language model for automatic prompt optimization via reinforcement learning.
## Load Pretrained Model for [Stable Diffusion v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4)
You can try the online demo at [https://huggingface.co/spaces/microsoft/Promptist](https://huggingface.co/spaces/microsoft/Promptist).
`[Note]` the online demo at HuggingFace Space is using CPU, so slow generation speed would be expected. Please load the model locally with GPUs for faster generation.
```python
import gradio as grad
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
def load_prompter():
prompter_model = AutoModelForCausalLM.from_pretrained("microsoft/Promptist")
tokenizer = AutoTokenizer.from_pretrained("gpt2")
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"
return prompter_model, tokenizer
prompter_model, prompter_tokenizer = load_prompter()
def generate(plain_text):
input_ids = prompter_tokenizer(plain_text.strip()+" Rephrase:", return_tensors="pt").input_ids
eos_id = prompter_tokenizer.eos_token_id
outputs = prompter_model.generate(input_ids, do_sample=False, max_new_tokens=75, num_beams=8, num_return_sequences=8, eos_token_id=eos_id, pad_token_id=eos_id, length_penalty=-1.0)
output_texts = prompter_tokenizer.batch_decode(outputs, skip_special_tokens=True)
res = output_texts[0].replace(plain_text+" Rephrase:", "").strip()
return res
txt = grad.Textbox(lines=1, label="Initial Text", placeholder="Input Prompt")
out = grad.Textbox(lines=1, label="Optimized Prompt")
examples = ["A rabbit is wearing a space suit", "Several railroad tracks with one train passing by", "The roof is wet from the rain", "Cats dancing in a space club"]
grad.Interface(fn=generate,
inputs=txt,
outputs=out,
title="Promptist Demo",
description="Promptist is a prompt interface for Stable Diffusion v1-4 (https://huggingface.co/CompVis/stable-diffusion-v1-4) that optimizes user input into model-preferred prompts.",
examples=examples,
allow_flagging='never',
cache_examples=False,
theme="default").launch(enable_queue=True, debug=True)
```
|
Minirecord/Mini_DPO_test02 | Minirecord | "2023-11-30T06:16:13Z" | 2,700 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-30T05:39:58Z" | ---
license: cc-by-sa-4.0
pipeline_tag: text-generation
---
# Mini_synatra_7b_02
# (주)Minirecord에서 파인튜닝한 모델입니다.
<img src = "https://cdn-uploads.huggingface.co/production/uploads/64c1e30e2bac49787a998397/47NT3IZ6y-oNnB96_oJPJ.png" width="30%" height="30%">
The license is cc-by-sa-4.0
## Model Details
### input
models input text only.
### output
models output text only.
### Base Model
## Training Details
### Training Data |
Chrisisis/5FX7vKshU4c6TayLjpXjB14JkYzWcPjDbamHgV142FxVuc3m_vgg | Chrisisis | "2024-02-24T08:24:49Z" | 2,700 | 0 | keras | [
"keras",
"region:us"
] | null | "2024-02-05T18:31:18Z" | Entry not found |
khanhpd2/sbert_phobert_large_cosine_sim | khanhpd2 | "2022-11-22T03:43:48Z" | 2,699 | 2 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
] | sentence-similarity | "2022-11-21T16:05:12Z" | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## 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('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# 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)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 1304 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 30,
"evaluation_steps": 1304,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 3912,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
acrastt/Marx-3B | acrastt | "2024-02-03T03:34:32Z" | 2,699 | 13 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:totally-not-an-llm/everything-sharegptformat-morecleaned",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-15T18:23:34Z" | ---
language:
- en
license: apache-2.0
datasets:
- totally-not-an-llm/everything-sharegptformat-morecleaned
pipeline_tag: text-generation
model-index:
- name: Marx-3B
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: 43.17
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 72.68
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 28.46
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 39.09
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 65.59
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 1.29
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
name: Open LLM Leaderboard
---
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
This is [OpenLLaMA 3B V2](https://huggingface.co/openlm-research/open_llama_3b_v2) finetuned on [EverythingLM Data(ShareGPT format more cleaned)](https://huggingface.co/datasets/totally-not-an-llm/everything-sharegptformat-morecleaned) for 1 epochs.
Prompt template:
```
### HUMAN:
{prompt}
### RESPONSE:
<leave a newline for the model to answer>
```
GGML quants available [here](https://huggingface.co/TheBloke/Marx-3b-GGML).</br>
GPTQ quants available [here](https://huggingface.co/TheBloke/Marx-3b-GPTQ).
Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please!
# [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_acrastt__Marx-3B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 41.71 |
| ARC (25-shot) | 43.17 |
| HellaSwag (10-shot) | 72.68 |
| MMLU (5-shot) | 28.46 |
| TruthfulQA (0-shot) | 39.09 |
| Winogrande (5-shot) | 65.59 |
| GSM8K (5-shot) | 1.29 |
# [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_acrastt__Marx-3B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |41.71|
|AI2 Reasoning Challenge (25-Shot)|43.17|
|HellaSwag (10-Shot) |72.68|
|MMLU (5-Shot) |28.46|
|TruthfulQA (0-shot) |39.09|
|Winogrande (5-shot) |65.59|
|GSM8k (5-shot) | 1.29|
|
Lewdiculous/Rawr_Llama3_8B-GGUF-IQ-Imatrix | Lewdiculous | "2024-06-06T17:36:01Z" | 2,699 | 4 | null | [
"gguf",
"region:us"
] | null | "2024-06-05T21:02:37Z" | ---
inference: false
---
[ResplendentAI/Rawr_Llama3_8B](https://huggingface.co/ResplendentAI/Rawr_Llama3_8B)
Use **KoboldCpp 1.67** or higher.
An RP model with a brain.
 |
mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF | mradermacher | "2024-06-06T11:27:15Z" | 2,699 | 0 | transformers | [
"transformers",
"gguf",
"Llama-3",
"instruct",
"finetune",
"chatml",
"axolotl",
"roleplay",
"en",
"base_model:Gryphe/Pantheon-RP-1.0-8b-Llama-3",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-06T02:01:10Z" | ---
base_model: Gryphe/Pantheon-RP-1.0-8b-Llama-3
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- Llama-3
- instruct
- finetune
- chatml
- axolotl
- roleplay
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Gryphe/Pantheon-RP-1.0-8b-Llama-3
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-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/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.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 -->
|
KnutJaegersberg/MistralInstructLongish | KnutJaegersberg | "2023-11-20T15:11:35Z" | 2,697 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"custom_code",
"dataset:KnutJaegersberg/longinstruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-15T06:16:43Z" | ---
license: apache-2.0
datasets:
- KnutJaegersberg/longinstruct
---
It was trained for like 3 epochs on a merger dataset of several instruction datasets, with partially longer instructions.
Alpaca Prompt Format:
```
### Instruction:
blablabla
### Input:
(optional)
### Response:
```
# [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_KnutJaegersberg__MistralInstructLongish)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 48.99 |
| ARC (25-shot) | 60.75 |
| HellaSwag (10-shot) | 81.86 |
| MMLU (5-shot) | 60.49 |
| TruthfulQA (0-shot) | 40.55 |
| Winogrande (5-shot) | 76.56 |
| GSM8K (5-shot) | 1.52 |
| DROP (3-shot) | 21.22 |
|
mradermacher/Naruto_Llama-3-8B-GGUF | mradermacher | "2024-06-18T10:53:55Z" | 2,697 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:AbdullahTarek/Naruto_Llama-3-8B",
"endpoints_compatible",
"region:us"
] | null | "2024-06-18T10:10:16Z" | ---
base_model: AbdullahTarek/Naruto_Llama-3-8B
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/AbdullahTarek/Naruto_Llama-3-8B
<!-- 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/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Naruto_Llama-3-8B-GGUF/resolve/main/Naruto_Llama-3-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
KnutJaegersberg/webMistral-7B | KnutJaegersberg | "2023-11-20T15:11:41Z" | 2,696 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"custom_code",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-17T09:13:32Z" | ---
license: cc-by-nc-4.0
---
Prompt Example:
```
## Question: What is slowing down our internet speeds?
### Google Search Results: - Are my other devices slowing down my connection? Gadgets with slower internet technology can slow down speeds for all your other devices. Everyone knows the feeling: you’re hard at work and then suddenly the Internet seems to slow down. Why is that? From background programs to cheap routers, here are a few reasons why your Internet might be a concern. When working outside your home, here’s how to keep your information safe on public Wi-Fi. If your internet slows down only when too many other people are online simultaneously, you’re probably using more bandwidth than your plan allows. Use our internet speed test to see if you’re getting the speed advertised by your ISP. If your results are close to your plan speed, consider upgrading. Generally, your modem or router (or both) will create a speed bottleneck if not working properly—the same goes with wireless gateways. If your equipment is too old, it may not support important internet protocols. Equipment damage, such as bad ports or components, can also cause slowdowns. Is your internet suddenly moving slowly? It could be due to an outdated router or a less-than-ideal router location. Your connection issues may need only an easy fix, like upgrading to a mesh network (which also has to be set up in the right spot) or simply restarting your modem and router. But if you've already attempted many of the tried-and-true methods and your internet speeds are still subpar, the issue might be something your internet service provider is intentionally doing: bandwidth throttling.
### Response: There are several factors that can slow down internet speeds. These include having gadgets with slower internet technology, running background programs[2], using more bandwidth than your plan allows[3], equipment damage[4], an outdated router or a less-than-ideal router location[5], and bandwidth throttling by the internet service provider[5].
```
# [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_KnutJaegersberg__webMistral-7B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 47.08 |
| ARC (25-shot) | 59.04 |
| HellaSwag (10-shot) | 80.89 |
| MMLU (5-shot) | 59.0 |
| TruthfulQA (0-shot) | 39.71 |
| Winogrande (5-shot) | 76.32 |
| GSM8K (5-shot) | 8.87 |
| DROP (3-shot) | 5.75 |
|
digiplay/ya3_xt | digiplay | "2024-03-16T17:37:37Z" | 2,696 | 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 | "2024-03-16T15:53:46Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
in test.
ya3 mix with xtremixUltimateMerge_v1.5 |
RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf | RichardErkhov | "2024-06-22T19:04:30Z" | 2,696 | 0 | null | [
"gguf",
"arxiv:1910.09700",
"region:us"
] | null | "2024-06-22T18:49:06Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
rho-1b-sft-MATH - GGUF
- Model creator: https://huggingface.co/realtreetune/
- Original model: https://huggingface.co/realtreetune/rho-1b-sft-MATH/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [rho-1b-sft-MATH.Q2_K.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q2_K.gguf) | Q2_K | 0.4GB |
| [rho-1b-sft-MATH.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [rho-1b-sft-MATH.IQ3_S.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.IQ3_S.gguf) | IQ3_S | 0.47GB |
| [rho-1b-sft-MATH.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
| [rho-1b-sft-MATH.IQ3_M.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [rho-1b-sft-MATH.Q3_K.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q3_K.gguf) | Q3_K | 0.51GB |
| [rho-1b-sft-MATH.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [rho-1b-sft-MATH.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [rho-1b-sft-MATH.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
| [rho-1b-sft-MATH.Q4_0.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q4_0.gguf) | Q4_0 | 0.59GB |
| [rho-1b-sft-MATH.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
| [rho-1b-sft-MATH.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
| [rho-1b-sft-MATH.Q4_K.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q4_K.gguf) | Q4_K | 0.62GB |
| [rho-1b-sft-MATH.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
| [rho-1b-sft-MATH.Q4_1.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q4_1.gguf) | Q4_1 | 0.65GB |
| [rho-1b-sft-MATH.Q5_0.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q5_0.gguf) | Q5_0 | 0.71GB |
| [rho-1b-sft-MATH.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
| [rho-1b-sft-MATH.Q5_K.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q5_K.gguf) | Q5_K | 0.73GB |
| [rho-1b-sft-MATH.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
| [rho-1b-sft-MATH.Q5_1.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q5_1.gguf) | Q5_1 | 0.77GB |
| [rho-1b-sft-MATH.Q6_K.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q6_K.gguf) | Q6_K | 0.84GB |
| [rho-1b-sft-MATH.Q8_0.gguf](https://huggingface.co/RichardErkhov/realtreetune_-_rho-1b-sft-MATH-gguf/blob/main/rho-1b-sft-MATH.Q8_0.gguf) | Q8_0 | 1.09GB |
Original model description:
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
joshnader/rho-math-7b-v0.1-Q8_0-GGUF | joshnader | "2024-07-01T06:19:21Z" | 2,696 | 0 | null | [
"gguf",
"nlp",
"math",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:microsoft/rho-math-7b-v0.1",
"license:mit",
"region:us"
] | text-generation | "2024-07-01T06:18:44Z" | ---
base_model: microsoft/rho-math-7b-v0.1
language:
- en
license: mit
pipeline_tag: text-generation
tags:
- nlp
- math
- llama-cpp
- gguf-my-repo
---
# joshnader/rho-math-7b-v0.1-Q8_0-GGUF
This model was converted to GGUF format from [`microsoft/rho-math-7b-v0.1`](https://huggingface.co/microsoft/rho-math-7b-v0.1) 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/rho-math-7b-v0.1) 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 joshnader/rho-math-7b-v0.1-Q8_0-GGUF --hf-file rho-math-7b-v0.1-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo joshnader/rho-math-7b-v0.1-Q8_0-GGUF --hf-file rho-math-7b-v0.1-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo joshnader/rho-math-7b-v0.1-Q8_0-GGUF --hf-file rho-math-7b-v0.1-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo joshnader/rho-math-7b-v0.1-Q8_0-GGUF --hf-file rho-math-7b-v0.1-q8_0.gguf -c 2048
```
|
KoboldAI/OPT-13B-Nerybus-Mix | KoboldAI | "2023-03-09T06:53:39Z" | 2,695 | 34 | transformers | [
"transformers",
"pytorch",
"opt",
"text-generation",
"en",
"arxiv:2205.01068",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-02-13T06:32:16Z" | ---
language: en
license: other
commercial: no
inference: false
---
# OPT 13B - Nerybus Mix
## Model description
This is a merged (50/50) model of both Erebus 13B and Nerys V2 13B by Mr. Seeker.
**Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.**
## Information:
For more information, check out the two source models:
- https://huggingface.co/KoboldAI/OPT-13B-Erebus
- https://huggingface.co/KoboldAI/OPT-13B-Nerys-v2
## Limitations and biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).
**Warning: This model has a very strong NSFW bias!**
### License
OPT-13B is licensed under the OPT-175B license, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
### BibTeX entry and citation info
```
@misc{zhang2022opt,
title={OPT: Open Pre-trained Transformer Language Models},
author={Susan Zhang and Stephen Roller and Naman Goyal and Mikel Artetxe and Moya Chen and Shuohui Chen and Christopher Dewan and Mona Diab and Xian Li and Xi Victoria Lin and Todor Mihaylov and Myle Ott and Sam Shleifer and Kurt Shuster and Daniel Simig and Punit Singh Koura and Anjali Sridhar and Tianlu Wang and Luke Zettlemoyer},
year={2022},
eprint={2205.01068},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
timm/swinv2_base_window12_192.ms_in22k | timm | "2024-02-10T23:30:56Z" | 2,694 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-22k",
"arxiv:2111.09883",
"license:mit",
"region:us"
] | image-classification | "2023-03-18T03:29:56Z" | ---
license: mit
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-22k
---
# Model card for swinv2_base_window12_192.ms_in22k
A Swin Transformer V2 image classification model. Pretrained on ImageNet-22k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 109.3
- GMACs: 11.9
- Activations (M): 39.7
- Image size: 192 x 192
- **Papers:**
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- **Original:** https://github.com/microsoft/Swin-Transformer
- **Dataset:** ImageNet-22k
## 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('swinv2_base_window12_192.ms_in22k', 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(
'swinv2_base_window12_192.ms_in22k',
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. for swin_base_patch4_window7_224 (NHWC output)
# torch.Size([1, 56, 56, 128])
# torch.Size([1, 28, 28, 256])
# torch.Size([1, 14, 14, 512])
# torch.Size([1, 7, 7, 1024])
# e.g. for swinv2_cr_small_ns_224 (NCHW output)
# torch.Size([1, 96, 56, 56])
# torch.Size([1, 192, 28, 28])
# torch.Size([1, 384, 14, 14])
# torch.Size([1, 768, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'swinv2_base_window12_192.ms_in22k',
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 (ie.e a (batch_size, H, W, num_features) tensor for swin / swinv2
# or (batch_size, num_features, H, W) for swinv2_cr
output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{liu2021swinv2,
title={Swin Transformer V2: Scaling Up Capacity and Resolution},
author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
booktitle={International 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/huggingface/pytorch-image-models}}
}
```
|
ai-forever/ruGPT-3.5-13B | ai-forever | "2023-12-05T11:41:23Z" | 2,694 | 236 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"gpt3",
"en",
"ru",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-02T12:53:36Z" | ---
license: mit
language:
- en
- ru
tags:
- gpt3
- transformers
---
# 🗿 ruGPT-3.5 13B
Language model for Russian. Model has 13B parameters as you can guess from it's name. This is our biggest model so far and it was used for trainig GigaChat (read more about it in the [article](https://habr.com/ru/companies/sberbank/articles/730108/)).
## Dataset
Model was pretrained on a 300Gb of various domains, than additionaly trained on the 100 Gb of code and legal documets. Here is the dataset structure:
Training data was deduplicated, the text deduplication includes 64-bit hashing of each text in the corpus for keeping texts with a unique hash. We also filter the documents based on their text compression rate using zlib4. The most strongly and weakly compressing deduplicated texts are discarded.
## Technical details
Model was trained using Deepspeed and Megatron libraries, on 300B tokens dataset for 3 epochs, around 45 days on 512 V100. After that model was finetuned 1 epoch with sequence length 2048 around 20 days on 200 GPU A100 on additional data (see above).
After the final training perplexity for this model was around 8.8 for Russian.
## Examples of usage
Try different generation strategies to reach better results.
```python
request = "Стих про программиста может быть таким:"
encoded_input = tokenizer(request, return_tensors='pt', \
add_special_tokens=False).to('cuda:0')
output = model.generate(
**encoded_input,
num_beams=2,
do_sample=True,
max_new_tokens=100
)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
```
>>> Стих про программиста может быть таким:
Программист сидит в кресле,
Стих сочиняет он про любовь,
Он пишет, пишет, пишет, пишет...
И не выходит ни черта!
```
```python
request = "Нейронная сеть — это"
encoded_input = tokenizer(request, return_tensors='pt', \
add_special_tokens=False).to('cuda:0')
output = model.generate(
**encoded_input,
num_beams=4,
do_sample=True,
max_new_tokens=100
)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
```
>>> Нейронная сеть — это математическая модель, состоящая из большого
количества нейронов, соединенных между собой электрическими связями.
Нейронная сеть может быть смоделирована на компьютере, и с ее помощью
можно решать задачи, которые не поддаются решению с помощью традиционных
математических методов.
```
```python
request = "Гагарин полетел в космос в"
encoded_input = tokenizer(request, return_tensors='pt', \
add_special_tokens=False).to('cuda:0')
output = model.generate(
**encoded_input,
num_beams=2,
do_sample=True,
max_new_tokens=100
)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
```
>>> Гагарин полетел в космос в 1961 году. Это было первое в истории
человечества космическое путешествие. Юрий Гагарин совершил его
на космическом корабле Восток-1. Корабль был запущен с космодрома
Байконур.
``` |
Aryanne/Mamba-gpt-3B-v4-ggml-and-gguf | Aryanne | "2023-09-08T19:32:53Z" | 2,694 | 7 | null | [
"gguf",
"text-generation",
"en",
"license:apache-2.0",
"region:us"
] | text-generation | "2023-09-06T03:52:47Z" | ---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
---
This contains q4_0, q4_1, q5_0 and q5_1 GGML(v3) and GGUF(v2) quantizations of the model https://huggingface.co/CobraMamba/mamba-gpt-3b-v4
|
mlabonne/NeuralMarcoro14-7B | mlabonne | "2024-03-04T15:16:01Z" | 2,694 | 39 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mlabonne/Marcoro14-7B-slerp",
"dpo",
"rlhf",
"merge",
"mergekit",
"lazymergekit",
"conversational",
"dataset:mlabonne/chatml_dpo_pairs",
"base_model:mlabonne/Marcoro14-7B-slerp",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-06T16:28:52Z" | ---
license: cc-by-nc-4.0
tags:
- mlabonne/Marcoro14-7B-slerp
- dpo
- rlhf
- merge
- mergekit
- lazymergekit
datasets:
- mlabonne/chatml_dpo_pairs
base_model: mlabonne/Marcoro14-7B-slerp
model-index:
- name: NeuralMarcoro14-7B
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: 71.42
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B
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: 87.59
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B
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: 64.84
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B
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: 65.64
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B
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: 81.22
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B
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: 70.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B
name: Open LLM Leaderboard
---
# NeuralMarcoro14-7B
This is a DPO fine-tuned version of [mlabonne/Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp) using the [chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) preference dataset.
It improves the performance of the model on Nous benchmark suite and the Open LLM Benchmark.
It is currently the best-performing 7B LLM on the Open LLM Leaderboard (08/01/24).
You can try it out in this [Space](https://huggingface.co/spaces/mlabonne/NeuralMarcoro14-7B-GGUF-Chat) (GGUF Q4_K_M).
## ⚡ Quantized models
* **GGUF**: https://huggingface.co/mlabonne/NeuralMarcoro14-7B-GGUF
## 🏆 Evaluation
### Open LLM Leaderboard
### Nous
| Model |AGIEval|GPT4ALL|TruthfulQA|Bigbench|Average|
|-------------------------|------:|------:|---------:|-------:|------:|
|[NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B)| 44.59| 76.17| 65.94| 46.9| 58.4|
|[Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp) | 44.66| 76.24| 64.15| 45.64| 57.67|
|Change | -0.07| -0.07| +1.79| +1.26| +0.73|
## 🧩 Training hyperparameters
**LoRA**:
* r=16
* lora_alpha=16
* lora_dropout=0.05
* bias="none"
* task_type="CAUSAL_LM"
* target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
**Training arguments**:
* per_device_train_batch_size=4
* gradient_accumulation_steps=4
* gradient_checkpointing=True
* learning_rate=5e-5
* lr_scheduler_type="cosine"
* max_steps=200
* optim="paged_adamw_32bit"
* warmup_steps=100
**DPOTrainer**:
* beta=0.1
* max_prompt_length=1024
* max_length=1536
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/NeuralMarcoro14-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
hywu/Camelidae-8x7B | hywu | "2024-04-09T01:21:04Z" | 2,694 | 14 | transformers | [
"transformers",
"pytorch",
"camelidae",
"text-generation",
"custom_code",
"en",
"dataset:Open-Orca/SlimOrca",
"dataset:ise-uiuc/Magicoder-OSS-Instruct-75K",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"dataset:meta-math/MetaMathQA",
"arxiv:2401.02731",
"arxiv:2305.14314",
"arxiv:1902.00751",
"arxiv:2212.05055",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-01-10T06:03:53Z" | ---
datasets:
- Open-Orca/SlimOrca
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
- meta-math/MetaMathQA
language:
- en
library_name: transformers
pipeline_tag: text-generation
arxiv: 2401.02731
license: apache-2.0
---
# Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
## News
- 3/12/2024 - We released Qwen2idae-16x14B-v1.0 on 🤗 [HuggingFace](https://huggingface.co/hywu/Qwen2idae-16x14B-v1.0), which has strong performance in Math and Code with 15B activated params.
- 2/7/2024 - [Serp-ai](https://github.com/serp-ai/Parameter-Efficient-MoE) adds [unsloth](https://github.com/serp-ai/unsloth) support for faster and memory efficient training of our Parameter-Efficient Sparsity Crafting and releases new [sparsetral](https://huggingface.co/serpdotai/sparsetral-16x7B-v2) models based on mistral-7B.
- 1/10/2024 - Camelidae models are now available on 🤗 [HuggingFace](https://huggingface.co/hywu).
- 1/4/2024 - We released the paper, [Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks](https://arxiv.org/abs/2401.02731).
- 12/22/2023 - We released the training [repo](https://github.com/wuhy68/Parameter-Efficient-MoE) that craft the dense model with LLaMA architecture to the MoE model.
## Introduction
Camelidae and Qwen2idae models are trained utilizing Parameter-Efficient Sparsity Crafting techniques
We present Parameter-Efficient Sparsity Crafting to help dense models learn knowledge from different fields (including code and math). This approach performs instruction tuning and efficiently utilizes MoE structure.
Specifically, Parameter-Efficient Sparsity Crafting utilizes parameter-efficient techniques including [QLoRA](https://arxiv.org/abs/2305.14314) and [Adapter](https://arxiv.org/abs/1902.00751) to perform Efficient [Sparse Upcycling](https://arxiv.org/abs/2212.05055).
## Model Lists
| Camelidae Series | Download
|---|---
Camelidae-8x7B | 🤗 [HuggingFace](https://huggingface.co/hywu/Camelidae-8x7B)
Camelidae-8x13B | 🤗 [HuggingFace](https://huggingface.co/hywu/Camelidae-8x13B)
Camelidae-8x34B | 🤗 [HuggingFace](https://huggingface.co/hywu/Camelidae-8x34B)
Camelidae-8x34B-pro | 🤗 Coming Soon
| Qwen2idae Series | Download
|---|---
Qwen2idae-16x14B-v1.0 | 🤗 [HuggingFace](https://huggingface.co/hywu/Qwen2idae-16x14B-v1.0)
Qwen2idae-16x7B-v1.0 | 🤗 Coming Soon
Qwen2idae-16x1.8B-v1.0 | 🤗 Coming Soon
## Performance
| Model | Activated Params | MMLU (5shot) | GSM8k (5shot) | MATH (4shot) | HumanEval (0shot) | MBPP (4shot) | HellaSwag (10shot) |
|:-----:|:----------------:|:------------:|:-------------:|:------------:|:-----------------:|:------------:|:------------------:|
| GPT3.5 | - | 70.0% | 57.1% | <font color=#F67F70>**34.1%**</font> | <font color=#FBD98D>**48.1%**</font> | - | <font color=#7FEA9E>**85.5%**</font> |
| LLaMA2-70B-chat | 70B | 63.8% | 59.3% | 10.4% | 32.3% | 35.6% | 84.8% |
| Camelidae-8x34B-pro | 35B | <font color=#7FEA9E>**75.7%**</font> | <font color=#F67F70>**79.4%**</font> | <font color=#FBD98D>**24.0%**</font> | <font color=#7FEA9E>**48.8%**</font> | <font color=#7FEA9E>**43.2%**</font> | 85.2% |
| Camelidae-8x34B | 35B | <font color=#FBD98D>**75.6%**</font> | <font color=#7FEA9E>**78.3%**</font> | 22.6% | 43.9% | <font color=#FBD98D>**41.4%**</font> | <font color=#FBD98D>**85.3%**</font> |
| SUSChat-34B | 34B | <font color=#F67F70>**76.4%**</font> | 72.3% | 22.0% | 11.6% | 40.2% | 83.9% |
| Yi-34B-chat | 34B | 74.8% | 67.6% | 17.3% | 20.1% | 41.0% | 83.9% |
| Qwen2idae-16x14B-v1.0 | 15B | 66.7% | <font color=#FBD98D>**77.8%**</font> | <font color=#7FEA9E>**29.9%**</font> | <font color=#F67F70>**62.8%**</font> | <font color=#F67F70>**48.6%**</font> | 82.3% |
| Mixtral-8x7B-instruct | 14B | 68.7% | 71.7% | 22.1% | 25.6% | 40.6% | <font color=#F67F70>**86.5%**</font> |
| Camelidae-8x13B | 13B | 54.4% | 52.6% | 9.8% | 30.6% | 30.4% | 82.5% |
| LLaMA2-13B-chat | 13B | 53.9% | 37.1% | 5.2% | 18.9% | 27.2% | 81.9% |
| Camelidae-8x7B | 7B | 48.3% | 44.0% | 5.8% | 18.3% | 23.4% | 79.2% |
| LLaMA2-7B-chat | 7B | 47.2% | 26.3% | 3.9% | 12.2% | 17.6% | 78.6% |
We bold the top3 scores separately for all models.
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("hywu/Camelidae-8x7B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hywu/Camelidae-8x7B", device_map="auto", trust_remote_code=True).eval()
inputs = tokenizer('### Human:\nHow are you?\n### Assistant:\n', return_tensors='pt')
inputs = inputs.to(model.device)
pred = model.generate(**inputs)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
```
## Citation
```bibtex
@article{wu2024parameter,
title={Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks},
author={Wu, Haoyuan and Zheng, Haisheng and Yu, Bei},
journal={arXiv preprint arXiv:2401.02731},
year={2024}
}
```
## License
The source code in this repo is licensed under the [Apache 2.0 License](https://github.com/wuhy68/Parameter-Efficient-MoE/blob/master/LICENSE). Camelidae models are developed for academic research and free commercial use, all usage must adhere to the license from [facebookresearch](https://github.com/facebookresearch/llama/blob/main/LICENSE) and [01-ai](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt). |
maywell/koOpenChat-sft | maywell | "2023-11-20T23:25:42Z" | 2,693 | 5 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-14T13:33:08Z" | ---
license: cc-by-sa-4.0
---
# **koOpenChat-sft🐧**
## Support Me
시나트라는 개인 프로젝트로, 1인의 자원으로 개발되고 있습니다. 모델이 마음에 드셨다면 약간의 연구비 지원은 어떨까요?
[<img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy me a Coffee" width="217" height="50">](https://www.buymeacoffee.com/mwell)
Wanna be a sponser? (Please) Contact me on Telegram **AlzarTakkarsen**
# **Model Details**
**Base Model**
OpenChat3.5
**Trained On**
A100 80GB * 1
**Instruction format**
It follows [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) format and **Alpaca(No-Input)** format.
# **Model Benchmark**
None
# **Implementation Code**
Since, chat_template already contains insturction format above.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("maywell/koOpenChat-sft")
tokenizer = AutoTokenizer.from_pretrained("maywell/koOpenChat-sft")
messages = [
{"role": "user", "content": "바나나는 원래 하얀색이야?"},
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
# [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_maywell__koOpenChat-sft)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.36 |
| ARC (25-shot) | 59.81 |
| HellaSwag (10-shot) | 78.73 |
| MMLU (5-shot) | 61.32 |
| TruthfulQA (0-shot) | 51.24 |
| Winogrande (5-shot) | 76.4 |
| GSM8K (5-shot) | 24.18 |
| DROP (3-shot) | 7.82 |
|
banelingz/black_stheno_8B_v1_gguf | banelingz | "2024-06-24T23:26:03Z" | 2,693 | 1 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"base_model:Sao10K/L3-8B-Stheno-v3.2",
"base_model:Hastagaras/Halu-8B-Llama3-Blackroot",
"endpoints_compatible",
"region:us"
] | null | "2024-06-20T19:25:22Z" | ---
base_model:
- Sao10K/L3-8B-Stheno-v3.2
- Hastagaras/Halu-8B-Llama3-Blackroot
library_name: transformers
tags:
- mergekit
- merge
---
# black_stheno_8B_v1_gguf
These are quantizations of [banelingz/black_stheno_8B_v1](https://huggingface.co/banelingz/black_stheno_8B_v1).
|
DucHaiten/DucHaitenAIart | DucHaiten | "2024-05-17T16:50:42Z" | 2,691 | 178 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"text-to-image",
"image-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2022-12-28T10:37:53Z" | ---
language:
- en
tags:
- stable-diffusion
- text-to-image
- image-to-image
- diffusers
license: creativeml-openrail-m
inference: true
---
**Big update DucHaitenAIart_v3.1**
*Big update of DucHaitenAIart, v3.1 is able to receive more diverse, more detailed prompts with gorgeous colors and more realistic shadows. The image has the breath of 3D anime, but the material is much more realistic. The weak point is that some celebrity images are no longer in the model, a bit too 3d anime might make some people dislike, the image of the teeth is a bit lacking in detail.
**Please support me by becoming a patron:**
https://www.patreon.com/duchaitenreal
*****
All sample images only use text to image, no editing, no image to image, no restore face no highres fix no extras.
*****
Hello, sorry for my lousy english.
After days of trying and retrying hundreds of times, with dozens of different versions, DucHaitenAIart finally released the official version.
Improved image sharpness, more realistic lighting correction, more shooting angles, the only downside is that it's less flexible and less random than beta-v6.0, so I'm still will leave beta-v6.0 for anyone to download.
This model can create NSFW images but since it is not a hentai and porn model, anything really hardcore will be difficult to create. But, To make the model work better with NSFW images, add “hentai, porn, rule 34” to the prompt
Always add to the prompt “masterpiece, best quality, 1girl or 1boy, realistic, anime or cartoon (it's two different styles, but I personally prefer anime), 3D, pixar, (add “pin-up”) ” if you are going to give your character a sexy pose), highly detail eyes, perfect eyes, both eyes are the same, (if you don't want to draw eyes, don't add them), smooth, perfect face, hd, 2k, 4k , 8k, 16k
Add to the prompt: “extremely detailed 8K, high resolution, ultra quality” to further enhance the image quality, but it may weaken the AI's interest in other keywords.
You can add “glare, Iridescent, Global illumination, real hair movement, realistic light, realistic shadow” to the prompt to create a better lighting effect, but the image will then become too realistic, if you don't want to. Please adjust it accordingly.
*****
Sampler: DPM++ 2S a Karras
+ negative prompt:
illustration, painting, cartoons, sketch, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)), collapsed eyeshadow, multiple eyeblows, vaginas in breasts, (cropped), oversaturated, extra limb, missing limbs, deformed hands, long neck, long body, imperfect, (bad hands), signature, watermark, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error
*****
Some test:
|
Yntec/Dreamshaper8 | Yntec | "2023-10-17T06:03:44Z" | 2,691 | 8 | diffusers | [
"diffusers",
"safetensors",
"General",
"Anime",
"Art",
"Girl",
"Photorealistic",
"LandScapes",
"Lykon",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-10-11T17:46:03Z" | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- General
- Anime
- Art
- Girl
- Photorealistic
- LandScapes
- Lykon
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
---
# Dreamshaper 8
Original page:
https://civitai.com/models/4384?modelVersionId=80261
Buy Lykon a coffee:
https://snipfeed.co/lykon
Sample and prompt:
PRETTY CUTE GIRL BY ROSSDRAWS. An extradimensional creature buying donuts. Pixar animation. |
laion/larger_clap_music | laion | "2023-10-30T19:17:40Z" | 2,691 | 13 | transformers | [
"transformers",
"pytorch",
"clap",
"feature-extraction",
"arxiv:2211.06687",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | feature-extraction | "2023-10-30T18:16:15Z" | ---
license: apache-2.0
---
# Model
## TL;DR
CLAP is to audio what CLIP is to image. This is an improved CLAP checkpoint, specifically trained on music.
## Description
CLAP (Contrastive Language-Audio Pretraining) is a neural network trained on a variety of (audio, text) pairs. It can be instructed in to predict the most relevant text snippet, given an audio, without directly optimizing for the task. The CLAP model uses a SWINTransformer to get audio features from a log-Mel spectrogram input, and a RoBERTa model to get text features. Both the text and audio features are then projected to a latent space with identical dimension. The dot product between the projected audio and text features is then used as a similar score.
# Usage
You can use this model for zero shot audio classification or extracting audio and/or textual features.
# Uses
## Perform zero-shot audio classification
### Using `pipeline`
```python
from datasets import load_dataset
from transformers import pipeline
dataset = load_dataset("ashraq/esc50")
audio = dataset["train"]["audio"][-1]["array"]
audio_classifier = pipeline(task="zero-shot-audio-classification", model="laion/larger_clap_music")
output = audio_classifier(audio, candidate_labels=["Sound of a dog", "Sound of vaccum cleaner"])
print(output)
>>> [{"score": 0.999, "label": "Sound of a dog"}, {"score": 0.001, "label": "Sound of vaccum cleaner"}]
```
## Run the model:
You can also get the audio and text embeddings using `ClapModel`
### Run the model on CPU:
```python
from datasets import load_dataset
from transformers import ClapModel, ClapProcessor
librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
audio_sample = librispeech_dummy[0]
model = ClapModel.from_pretrained("laion/larger_clap_music")
processor = ClapProcessor.from_pretrained("laion/larger_clap_music")
inputs = processor(audios=audio_sample["audio"]["array"], return_tensors="pt")
audio_embed = model.get_audio_features(**inputs)
```
### Run the model on GPU:
```python
from datasets import load_dataset
from transformers import ClapModel, ClapProcessor
librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
audio_sample = librispeech_dummy[0]
model = ClapModel.from_pretrained("laion/larger_clap_music").to(0)
processor = ClapProcessor.from_pretrained("laion/larger_clap_music")
inputs = processor(audios=audio_sample["audio"]["array"], return_tensors="pt").to(0)
audio_embed = model.get_audio_features(**inputs)
```
# Citation
If you are using this model for your work, please consider citing the original paper:
```
@misc{https://doi.org/10.48550/arxiv.2211.06687,
doi = {10.48550/ARXIV.2211.06687},
url = {https://arxiv.org/abs/2211.06687},
author = {Wu, Yusong and Chen, Ke and Zhang, Tianyu and Hui, Yuchen and Berg-Kirkpatrick, Taylor and Dubnov, Shlomo},
keywords = {Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
title = {Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
google/ddpm-ema-church-256 | google | "2022-11-08T13:41:12Z" | 2,690 | 11 | diffusers | [
"diffusers",
"pytorch",
"unconditional-image-generation",
"arxiv:2006.11239",
"license:apache-2.0",
"diffusers:DDPMPipeline",
"region:us"
] | unconditional-image-generation | "2022-07-19T10:43:19Z" | ---
license: apache-2.0
tags:
- pytorch
- diffusers
- unconditional-image-generation
---
# Denoising Diffusion Probabilistic Models (DDPM)
**Paper**: [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239)
**Authors**: Jonathan Ho, Ajay Jain, Pieter Abbeel
**Abstract**:
*We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.*
## Inference
**DDPM** models can use *discrete noise schedulers* such as:
- [scheduling_ddpm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddpm.py)
- [scheduling_ddim](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddim.py)
- [scheduling_pndm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_pndm.py)
for inference. Note that while the *ddpm* scheduler yields the highest quality, it also takes the longest.
For a good trade-off between quality and inference speed you might want to consider the *ddim* or *pndm* schedulers instead.
See the following code:
```python
# !pip install diffusers
from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline
model_id = "google/ddpm-ema-church-256"
# load model and scheduler
ddpm = DDPMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference
# run pipeline in inference (sample random noise and denoise)
image = ddpm().images[0]
# save image
image.save("ddpm_generated_image.png")
```
For more in-detail information, please have a look at the [official inference example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb)
## Training
If you want to train your own model, please have a look at the [official training example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb)
## Samples
1. 
2. 
3. 
4.  |
SvenN/sdxl-emoji | SvenN | "2023-10-16T13:20:08Z" | 2,690 | 46 | 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 | "2023-10-16T13:19:53Z" | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
pivotal_tuning: true
textual_embeddings: embeddings.pti
instance_prompt: <s0><s1>
inference: true
---
# sdxl-emoji LoRA by [fofr](https://replicate.com/fofr)
### An SDXL fine-tune based on Apple Emojis
>
## Inference with Replicate API
Grab your replicate token [here](https://replicate.com/account)
```bash
pip install replicate
export REPLICATE_API_TOKEN=r8_*************************************
```
```py
import replicate
output = replicate.run(
"sdxl-emoji@sha256:dee76b5afde21b0f01ed7925f0665b7e879c50ee718c5f78a9d38e04d523cc5e",
input={"prompt": "A TOK emoji of a man"}
)
print(output)
```
You may also do inference via the API with Node.js or curl, and locally with COG and Docker, [check out the Replicate API page for this model](https://replicate.com/fofr/sdxl-emoji/api)
## Inference with 🧨 diffusers
Replicate SDXL LoRAs are trained with Pivotal Tuning, which combines training a concept via Dreambooth LoRA with training a new token with Textual Inversion.
As `diffusers` doesn't yet support textual inversion for SDXL, we will use cog-sdxl `TokenEmbeddingsHandler` class.
The trigger tokens for your prompt will be `<s0><s1>`
```shell
pip install diffusers transformers accelerate safetensors huggingface_hub
git clone https://github.com/replicate/cog-sdxl cog_sdxl
```
```py
import torch
from huggingface_hub import hf_hub_download
from diffusers import DiffusionPipeline
from cog_sdxl.dataset_and_utils import TokenEmbeddingsHandler
from diffusers.models import AutoencoderKL
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
pipe.load_lora_weights("SvenN/sdxl-emoji", weight_name="lora.safetensors")
text_encoders = [pipe.text_encoder, pipe.text_encoder_2]
tokenizers = [pipe.tokenizer, pipe.tokenizer_2]
embedding_path = hf_hub_download(repo_id="SvenN/sdxl-emoji", filename="embeddings.pti", repo_type="model")
embhandler = TokenEmbeddingsHandler(text_encoders, tokenizers)
embhandler.load_embeddings(embedding_path)
prompt="A <s0><s1> emoji of a man"
images = pipe(
prompt,
cross_attention_kwargs={"scale": 0.8},
).images
#your output image
images[0]
```
|
google/paligemma-3b-ft-docvqa-896 | google | "2024-06-27T14:10:22Z" | 2,690 | 2 | transformers | [
"transformers",
"safetensors",
"paligemma",
"pretraining",
"image-text-to-text",
"arxiv:2310.09199",
"arxiv:2303.15343",
"arxiv:2403.08295",
"arxiv:1706.03762",
"arxiv:2010.11929",
"arxiv:2209.06794",
"arxiv:2209.04372",
"arxiv:2103.01913",
"arxiv:2401.06209",
"arxiv:2305.10355",
"arxiv:2205.12522",
"arxiv:2110.11624",
"arxiv:2108.03353",
"arxiv:2010.04295",
"arxiv:2203.10244",
"arxiv:1810.12440",
"arxiv:1905.13648",
"arxiv:1608.00272",
"arxiv:1908.04913",
"license:gemma",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | image-text-to-text | "2024-05-12T23:49:15Z" | ---
library_name: transformers
license: gemma
pipeline_tag: image-text-to-text
extra_gated_heading: Access PaliGemma on Hugging Face
extra_gated_prompt: To access PaliGemma on Hugging Face, you’re required to review
and agree to Google’s usage license. To do this, please ensure you’re logged-in
to Hugging Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
---
# PaliGemma model card
**Model page:** [PaliGemma](https://ai.google.dev/gemma/docs/paligemma)
Transformers PaliGemma 3B weights, fine-tuned with 896*896 input images on the <a href="https://www.docvqa.org/">DocVQA</a> dataset. The models are available in float32, bfloat16 and float16 format for research purposes only. The fine-tune config is available at <a href="https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/transfers/docvqa.py">big_vision</a>.
**Resources and technical documentation:**
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [PaliGemma on Kaggle](https://www.kaggle.com/models/google/paligemma)
* [PaliGemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/363)
**Terms of Use:** [Terms](https://www.kaggle.com/models/google/paligemma-ft/license/consent/verify/huggingface?returnModelRepoId=google/paligemma-3b-ft-docvqa-896)
**Authors:** Google
## Model information
### Model summary
#### Description
PaliGemma is a versatile and lightweight vision-language model (VLM) inspired by
[PaLI-3](https://arxiv.org/abs/2310.09199) and based on open components such as
the [SigLIP vision model](https://arxiv.org/abs/2303.15343) and the [Gemma
language model](https://arxiv.org/abs/2403.08295). It takes both image and text
as input and generates text as output, supporting multiple languages. It is designed for class-leading fine-tune performance on a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation.
#### Model architecture
PaliGemma is the composition of a [Transformer
decoder](https://arxiv.org/abs/1706.03762) and a [Vision Transformer image
encoder](https://arxiv.org/abs/2010.11929), with a total of 3 billion
params. The text decoder is initialized from
[Gemma-2B](https://www.kaggle.com/models/google/gemma). The image encoder is
initialized from
[SigLIP-So400m/14](https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb).
PaliGemma is trained following the PaLI-3 recipes.
#### Inputs and outputs
* **Input:** Image and text string, such as a prompt to caption the image, or
a question.
* **Output:** Generated text in response to the input, such as a caption of
the image, an answer to a question, a list of object bounding box
coordinates, or segmentation codewords.
### Model data
#### Pre-train datasets
PaliGemma is pre-trained on the following mixture of datasets:
* **WebLI:** [WebLI (Web Language Image)](https://arxiv.org/abs/2209.06794) is
a web-scale multilingual image-text dataset built from the public web. A
wide range of WebLI splits are used to acquire versatile model capabilities,
such as visual semantic understanding, object localization,
visually-situated text understanding, multilinguality, etc.
* **CC3M-35L:** Curated English image-alt_text pairs from webpages ([Sharma et
al., 2018](https://aclanthology.org/P18-1238/)). We used the [Google Cloud
Translation API](https://cloud.google.com/translate) to translate into 34
additional languages.
* **VQ²A-CC3M-35L/VQG-CC3M-35L:** A subset of VQ2A-CC3M ([Changpinyo et al.,
2022a](https://aclanthology.org/2022.naacl-main.142/)), translated into the
same additional 34 languages as CC3M-35L, using the [Google Cloud
Translation API](https://cloud.google.com/translate).
* **OpenImages:** Detection and object-aware questions and answers
([Piergiovanni et al. 2022](https://arxiv.org/abs/2209.04372)) generated by
handcrafted rules on the [OpenImages dataset].
* **WIT:** Images and texts collected from Wikipedia ([Srinivasan et al.,
2021](https://arxiv.org/abs/2103.01913)).
[OpenImages dataset]: https://storage.googleapis.com/openimages/web/factsfigures_v7.html
#### Data responsibility filtering
The following filters are applied to WebLI, with the goal of training PaliGemma
on clean data:
* **Pornographic image filtering:** This filter removes images deemed to be of
pornographic nature.
* **Text safety filtering:** We identify and filter out images that are paired
with unsafe text. Unsafe text is any text deemed to contain or be about
CSAI, pornography, vulgarities, or otherwise offensive.
* **Text toxicity filtering:** We further use the [Perspective
API](https://perspectiveapi.com/) to identify and filter out images that are
paired with text deemed insulting, obscene, hateful or otherwise toxic.
* **Text personal information filtering:** We filtered certain personal information and other sensitive data using [Cloud Data Loss Prevention (DLP)
API](https://cloud.google.com/security/products/dlp) to protect the privacy
of individuals. Identifiers such as social security numbers and [other sensitive information types] were removed.
* **Additional methods:** Filtering based on content quality and safety in
line with our policies and practices.
[other sensitive information types]: https://cloud.google.com/sensitive-data-protection/docs/high-sensitivity-infotypes-reference?_gl=1*jg604m*_ga*ODk5MzA3ODQyLjE3MTAzMzQ3NTk.*_ga_WH2QY8WWF5*MTcxMDUxNTkxMS4yLjEuMTcxMDUxNjA2NC4wLjAuMA..&_ga=2.172110058.-899307842.1710334759
## How to Use
PaliGemma is a single-turn vision language model not meant for conversational use,
and it works best when fine-tuning to a specific use case.
You can configure which task the model will solve by conditioning it with task prefixes,
such as “detect” or “segment”. The pretrained models were trained in this fashion to imbue
them with a rich set of capabilities (question answering, captioning, segmentation, etc.).
However, they are not designed to be used directly, but to be transferred (by fine-tuning)
to specific tasks using a similar prompt structure. For interactive testing, you can use
the "mix" family of models, which have been fine-tuned on a mixture of tasks.
Please, refer to the [usage and limitations section](#usage-and-limitations) for intended
use cases, or visit the [blog post](https://huggingface.co/blog/paligemma-google-vlm) for
additional details and examples.
## Use in Transformers
The following snippets use model `google/paligemma-3b-mix-224` for reference purposes.
The model in this repo you are now browsing may have been trained for other tasks, please
make sure you use appropriate inputs for the task at hand.
### Running the default precision (`float32`) on CPU
```python
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/paligemma-3b-mix-224"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id).eval()
processor = AutoProcessor.from_pretrained(model_id)
# Instruct the model to create a caption in Spanish
prompt = "caption es"
model_inputs = processor(text=prompt, images=image, return_tensors="pt")
input_len = model_inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
```
Output: `Un auto azul estacionado frente a un edificio.`
### Running other precisions on CUDA
For convenience, the repos contain revisions of the weights already converted to `bfloat16` and `float16`,
so you can use them to reduce the download size and avoid casting on your local computer.
This is how you'd run `bfloat16` on an nvidia CUDA card.
```python
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/paligemma-3b-mix-224"
device = "cuda:0"
dtype = torch.bfloat16
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
model = PaliGemmaForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=dtype,
device_map=device,
revision="bfloat16",
).eval()
processor = AutoProcessor.from_pretrained(model_id)
# Instruct the model to create a caption in Spanish
prompt = "caption es"
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
input_len = model_inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
```
### Loading in 4-bit / 8-bit
You need to install `bitsandbytes` to automatically run inference using 8-bit or 4-bit precision:
```
pip install bitsandbytes accelerate
```
```
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/paligemma-3b-mix-224"
device = "cuda:0"
dtype = torch.bfloat16
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
model = PaliGemmaForConditionalGeneration.from_pretrained(
model_id, quantization_config=quantization_config
).eval()
processor = AutoProcessor.from_pretrained(model_id)
# Instruct the model to create a caption in Spanish
prompt = "caption es"
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
input_len = model_inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
```
## Implementation information
### Hardware
PaliGemma was trained using the latest generation of Tensor Processing Unit
(TPU) hardware (TPUv5e).
### Software
Training was done using [JAX](https://github.com/google/jax),
[Flax](https://github.com/google/flax),
[TFDS](https://github.com/tensorflow/datasets) and
[`big_vision`](https://github.com/google-research/big_vision).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
TFDS is used to access datasets and Flax is used for model architecture. The
PaliGemma fine-tune code and inference code are released in the `big_vision`
GitHub repository.
## Evaluation information
### Benchmark results
In order to verify the transferability of PaliGemma to a wide variety of
academic tasks, we fine-tune the pretrained models on each task. Additionally we
train the mix model with a mixture of the transfer tasks. We report results on
different resolutions to provide an impression of which tasks benefit from
increased resolution. Importantly, none of these tasks or datasets are part of
the pretraining data mixture, and their images are explicitly removed from the
web-scale pre-training data.
#### Mix model (fine-tune on mixture of transfer tasks)
<table>
<tbody><tr>
<th>Benchmark</th>
<th>Metric (split)</th>
<th>mix-224</th>
<th>mix-448</th>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2401.06209">MMVP</a></td>
<td>Paired Accuracy</td>
<td>46.00</td>
<td>45.33</td>
</tr>
<tr>
<td><a href="https://arxiv.org/abs/2305.10355">POPE</a></td>
<td>Accuracy<br>(random/popular/adversarial)</td>
<td>
88.00<br>
86.63<br>
85.67
</td>
<td>
89.37<br>
88.40<br>
87.47
</td>
</tr>
<tr>
<td><a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a></td>
<td>Accuracy (test)</td>
<td>65.20</td>
<td>65.47</td>
</tr>
</tbody></table>
#### Single task (fine-tune on single task)
<table>
<tbody><tr>
<th>Benchmark<br>(train split)</th>
<th>Metric<br>(split)</th>
<th>pt-224</th>
<th>pt-448</th>
<th>pt-896</th>
</tr>
<tr>
<th>Captioning</th>
</tr>
<tr>
<td>
<a href="https://cocodataset.org/#home">COCO captions</a><br>(train+restval)
</td>
<td>CIDEr (val)</td>
<td>141.92</td>
<td>144.60</td>
</tr>
<tr>
<td>
<a href="https://nocaps.org/">NoCaps</a><br>(Eval of COCO<br>captions transfer)
</td>
<td>CIDEr (val)</td>
<td>121.72</td>
<td>123.58</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">COCO-35L</a><br>(train)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
139.2<br>
115.8<br>
116.4
</td>
<td>
141.2<br>
118.0<br>
118.6
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/pdf/2205.12522">XM3600</a><br>(Eval of COCO-35L transfer)
</td>
<td>CIDEr dev<br>(en/avg-34/avg)</td>
<td>
78.1<br>
41.3<br>
42.4
</td>
<td>
80.0<br>
41.9<br>
42.9
</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/textcaps/">TextCaps</a><br>(train)
</td>
<td>CIDEr (val)</td>
<td>127.48</td>
<td>153.94</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2110.11624">SciCap</a><br>(first sentence, no subfigure)<br>(train+val)
</td>
<td>CIDEr/BLEU-4<br>(test)</td>
<td>
162.25<br>
0.192<br>
</td>
<td>
181.49<br>
0.211<br>
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2108.03353">Screen2words</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>117.57</td>
<td>119.59</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2010.04295">Widget Captioning</a><br>(train+dev)
</td>
<td>CIDEr (test)</td>
<td>136.07</td>
<td>148.36</td>
</tr>
<tr>
<th>Question answering</th>
</tr>
<tr>
<td>
<a href="https://visualqa.org/index.html">VQAv2</a><br>(train+validation)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>83.19</td>
<td>85.64</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2401.06209">MMVP</a><br>(Eval of VQAv2 transfer)
</td>
<td>Paired Accuracy</td>
<td>47.33</td>
<td>45.33</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2305.10355">POPE</a><br>(Eval of VQAv2 transfer)
</td>
<td>Accuracy<br>(random/popular/<br>adversarial)</td>
<td>
87.80<br>
85.87<br>
84.27
</td>
<td>
88.23<br>
86.77<br>
85.90
</td>
</tr>
<tr>
<td>
<a href="https://okvqa.allenai.org/">OKVQA</a><br>(train)
</td>
<td>Accuracy (val)</td>
<td>63.54</td>
<td>63.15</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (MC)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>76.37</td>
<td>76.90</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (DA)<br>(train+val)
</td>
<td>Accuracy<br>(Test server)</td>
<td>61.85</td>
<td>63.22</td>
</tr>
<tr>
<td>
<a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a><br>(train_balanced+<br>val_balanced)
</td>
<td>Accuracy<br>(testdev balanced)</td>
<td>65.61</td>
<td>67.03</td>
</tr>
<tr>
<td>
<a href="https://aclanthology.org/2022.findings-acl.196/">xGQA</a><br>(Eval of GQA transfer)
</td>
<td>Mean Accuracy<br>(bn, de, en, id,<br>ko, pt, ru, zh)</td>
<td>58.37</td>
<td>59.07</td>
</tr>
<tr>
<td>
<a href="https://lil.nlp.cornell.edu/nlvr/">NLVR2</a><br>(train+dev)
</td>
<td>Accuracy (test)</td>
<td>90.02</td>
<td>88.93</td>
</tr>
<tr>
<td>
<a href="https://marvl-challenge.github.io/">MaRVL</a><br>(Eval of NLVR2 transfer)
</td>
<td>Mean Accuracy<br>(test)<br>(id, sw, ta, tr, zh)</td>
<td>80.57</td>
<td>76.78</td>
</tr>
<tr>
<td>
<a href="https://allenai.org/data/diagrams">AI2D</a><br>(train)
</td>
<td>Accuracy (test)</td>
<td>72.12</td>
<td>73.28</td>
</tr>
<tr>
<td>
<a href="https://scienceqa.github.io/">ScienceQA</a><br>(Img subset, no CoT)<br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>95.39</td>
<td>95.93</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344334">RSVQA-LR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test)</td>
<td>92.65</td>
<td>93.11</td>
</tr>
<tr>
<td>
<a href="https://zenodo.org/records/6344367">RSVQA-HR</a> (Non numeric)<br>(train+val)
</td>
<td>Mean Accuracy<br>(test/test2)</td>
<td>
92.61<br>
90.58
</td>
<td>
92.79<br>
90.54
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/2203.10244">ChartQA</a><br>(human+aug)x(train+val)
</td>
<td>Mean Relaxed<br>Accuracy<br>(test_human,<br>test_aug)</td>
<td>57.08</td>
<td>71.36</td>
</tr>
<tr>
<td>
<a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz VQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>
73.7
</td>
<td>
75.52
</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1810.12440">TallyQA</a><br>(train)
</td>
<td>Accuracy<br>(test_simple/<br>test_complex)</td>
<td>
81.72<br>
69.56
</td>
<td>
84.86<br>
72.27
</td>
</tr>
<tr>
<td>
<a href="https://ocr-vqa.github.io/">OCR-VQA</a><br>(train+val)
</td>
<td>Accuracy (test)</td>
<td>72.32</td>
<td>74.61</td>
<td>74.93</td>
</tr>
<tr>
<td>
<a href="https://textvqa.org/">TextVQA</a><br>(train+val)
</td>
<td>Accuracy<br>(Test server - std)</td>
<td>55.47</td>
<td>73.15</td>
<td>76.48</td>
</tr>
<tr>
<td>
<a href="https://www.docvqa.org/">DocVQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>43.74</td>
<td>78.02</td>
<td>84.77</td>
</tr>
<tr>
<td>
<a href="https://openaccess.thecvf.com/content/WACV2022/papers/Mathew_InfographicVQA_WACV_2022_paper.pdf">Infographic VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>28.46</td>
<td>40.47</td>
<td>47.75</td>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1905.13648">SceneText VQA</a><br>(train+val)
</td>
<td>ANLS (Test server)</td>
<td>63.29</td>
<td>81.82</td>
<td>84.40</td>
</tr>
<tr>
<th>Segmentation</th>
</tr>
<tr>
<td>
<a href="https://arxiv.org/abs/1608.00272">RefCOCO</a><br>(combined refcoco, refcoco+,<br>refcocog excluding val<br>and test images)
</td>
<td>MIoU<br>(validation)<br>refcoco/refcoco+/<br>refcocog</td>
<td>
73.40<br>
68.32<br>
67.65
</td>
<td>
75.57<br>
69.76<br>
70.17
</td>
<td>
76.94<br>
72.18<br>
72.22
</td>
</tr>
<tr>
<th>Video tasks (Caption/QA)</th>
</tr>
<tr>
<td>MSR-VTT (Captioning)</td>
<td>CIDEr (test)</td>
<td>70.54</td>
</tr>
<tr>
<td>MSR-VTT (QA)</td>
<td>Accuracy (test)</td>
<td>50.09</td>
</tr>
<tr>
<td>ActivityNet (Captioning)</td>
<td>CIDEr (test)</td>
<td>34.62</td>
</tr>
<tr>
<td>ActivityNet (QA)</td>
<td>Accuracy (test)</td>
<td>50.78</td>
</tr>
<tr>
<td>VATEX (Captioning)</td>
<td>CIDEr (test)</td>
<td>79.73</td>
</tr>
<tr>
<td>MSVD (QA)</td>
<td>Accuracy (test)</td>
<td>60.22</td>
</tr>
</tbody></table>
## Ethics and safety
### Evaluation approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Human evaluation on prompts covering child safety, content safety and
representational harms. See the [Gemma model
card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for
more details on evaluation approach, but with image captioning and visual
question answering setups.
* Image-to-Text benchmark evaluation: Benchmark against relevant academic
datasets such as FairFace Dataset ([Karkkainen et al.,
2021](https://arxiv.org/abs/1908.04913)).
### Evaluation results
* The human evaluation results of ethics and safety evaluations are within
acceptable thresholds for meeting [internal
policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11)
for categories such as child safety, content safety and representational
harms.
* On top of robust internal evaluations, we also use the Perspective API
(threshold of 0.8) to measure toxicity, profanity, and other potential
issues in the generated captions for images sourced from the FairFace
dataset. We report the maximum and median values observed across subgroups
for each of the perceived gender, ethnicity, and age attributes.
<table>
<tbody><tr>
</tr></tbody><tbody><tr><th>Metric</th>
<th>Perceived<br>gender</th>
<th></th>
<th>Ethnicity</th>
<th></th>
<th>Age group</th>
<th></th>
</tr>
<tr>
<th></th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
<th>Maximum</th>
<th>Median</th>
</tr>
<tr>
<td>Toxicity</td>
<td>0.04%</td>
<td>0.03%</td>
<td>0.08%</td>
<td>0.00%</td>
<td>0.09%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Identity Attack</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Insult</td>
<td>0.06%</td>
<td>0.04%</td>
<td>0.09%</td>
<td>0.07%</td>
<td>0.16%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Threat</td>
<td>0.06%</td>
<td>0.05%</td>
<td>0.14%</td>
<td>0.05%</td>
<td>0.17%</td>
<td>0.00%</td>
</tr>
<tr>
<td>Profanity</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
<td>0.00%</td>
</tr>
</tbody></table>
## Usage and limitations
### Intended usage
Open Vision Language Models (VLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
Fine-tune on specific vision-language task:
* The pre-trained models can be fine-tuned on a wide range of vision-language
tasks such as: image captioning, short video caption, visual question
answering, text reading, object detection and object segmentation.
* The pre-trained models can be fine-tuned for specific domains such as remote
sensing question answering, visual questions from people who are blind,
science question answering, describe UI element functionalities.
* The pre-trained models can be fine-tuned for tasks with non-textual outputs
such as bounding boxes or segmentation masks.
Vision-language research:
* The pre-trained models and fine-tuned models can serve as a foundation for researchers to experiment with VLM
techniques, develop algorithms, and contribute to the advancement of the
field.
### Ethical considerations and risks
The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
* Bias and Fairness
* VLMs trained on large-scale, real-world image-text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
* Misinformation and Misuse
* VLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
* Transparency and Accountability
* This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
Risks identified and mitigations:
* **Perpetuation of biases:** It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* **Generation of harmful content:** Mechanisms and guidelines for content
safety are essential. Developers are encouraged to exercise caution and
implement appropriate content safety safeguards based on their specific
product policies and application use cases.
* **Misuse for malicious purposes:** Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the [Gemma
Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* **Privacy violations:** Models were trained on data filtered to remove certain personal information and sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
### Limitations
* Most limitations inherited from the underlying Gemma model still apply:
* VLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* Natural language is inherently complex. VLMs might struggle to grasp
subtle nuances, sarcasm, or figurative language.
* VLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* VLMs rely on statistical patterns in language and images. They might
lack the ability to apply common sense reasoning in certain situations.
* PaliGemma was designed first and foremost to serve as a general pre-trained
model for transfer to specialized tasks. Hence, its "out of the box" or
"zero-shot" performance might lag behind models designed specifically for
that.
* PaliGemma is not a multi-turn chatbot. It is designed for a single round of
image and text input.
|
lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF | lmstudio-community | "2024-06-22T19:11:36Z" | 2,690 | 10 | null | [
"gguf",
"text-generation",
"base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
"license:other",
"region:us"
] | text-generation | "2024-06-17T18:01:28Z" | ---
license: other
license_name: deepseek-license
license_link: LICENSE
quantized_by: bartowski
pipeline_tag: text-generation
lm_studio:
param_count: 16b
use_case: coding
release_date: 17-06-2024
model_creator: DeepSeek
prompt_template: DeepSeek Chat
system_prompt: none
base_model: DeepSeek
original_repo: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
---
## 💫 Community Model> DeepSeek-Coder-V2-Lite-Instruct by DeepSeek
*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [DeepSeek](https://huggingface.co/deepseek-ai)<br>
**Original model**: [DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3166](https://github.com/ggerganov/llama.cpp/releases/tag/b3166)<br>
## Model Settings:
Requires LM Studio 0.2.25, update can be downloaded from here: https://lmstudio.ai
Flash attention MUST be **disabled** for this model to work.
## Model Summary:
This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions.<br>
This model performs well across a series of coding benchmarks and should be used for both instruction following and code completion.
## Prompt template:
The best performing template is `Deepseek Coder` preset in your LM Studio.
This will format the prompt as follows:
```
You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science.",
### Instruction: {user_message}
### Response: {assistant_message}
```
The "official" template seems to tend towards generating Chinese, however if you'd like to use it you can set it up by choosing the `LM Studio Blank Preset` preset in your LM Studio and then:
Set your User Message Prefix to `User: `
Set your User Message Suffix to `\n\nAssistant: `
This will format the prompt as follows:
```
User: {user_message}
Assistant: {assistant_message}
```
## Technical Details
This model is an MoE architecture, using 16B total weights with only 2.4B activated to achieve excellent inference speed.
DeepSeek-Coder-V2 is based on the DeepSeek-V2 model, further trained on 6 trillion high quality coding tokens to enhance coding and mathematical reasoning.
It supports an incredible 128k context length.
For more details, read their paper here: https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/paper.pdf
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/)
🙏 Special thanks to [Kalomaze](https://github.com/kalomaze) and [Dampf](https://github.com/Dampfinchen) for their work on the dataset (linked [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)) that was used for calculating the imatrix for all sizes.
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio. |
aisuko/phi3-medium-128k-instruct-gguf | aisuko | "2024-06-29T02:23:14Z" | 2,689 | 0 | null | [
"gguf",
"license:mit",
"region:us"
] | null | "2024-06-29T01:35:40Z" | ---
license: mit
---
Original repo: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct
Note: Make sure you have enough CPUs resources, otherwise it will load failed.
```
ec2-user@ip-10-110-145-52:~/workspace/llama.cpp$ ./llama-cli -m ../Phi-3-medium-128k-instruct/phi3-medium-128k-instruct-Q4_K_M-v2.gguf -n 128 --repeat_penalty 1.0 --co
lor -i -r "User:" -f prompts/chat-with-bob.txt
Log start
main: build = 3233 (a8d49d86)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1719626314
llama_model_loader: loaded meta data with 27 key-value pairs and 245 tensors from ../Phi-3-medium-128k-instruct/phi3-medium-128k-instruct-Q4_K_M-v2.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = phi3
llama_model_loader: - kv 1: general.name str = Phi3
llama_model_loader: - kv 2: phi3.context_length u32 = 131072
llama_model_loader: - kv 3: phi3.rope.scaling.original_context_length u32 = 4096
llama_model_loader: - kv 4: phi3.embedding_length u32 = 5120
llama_model_loader: - kv 5: phi3.feed_forward_length u32 = 17920
llama_model_loader: - kv 6: phi3.block_count u32 = 40
llama_model_loader: - kv 7: phi3.attention.head_count u32 = 40
llama_model_loader: - kv 8: phi3.attention.head_count_kv u32 = 10
llama_model_loader: - kv 9: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: phi3.rope.dimension_count u32 = 128
llama_model_loader: - kv 11: phi3.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 12: general.file_type u32 = 15
llama_model_loader: - kv 13: phi3.rope.scaling.attn_factor f32 = 1.190238
llama_model_loader: - kv 14: tokenizer.ggml.model str = llama
llama_model_loader: - kv 15: tokenizer.ggml.pre str = default
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,32064] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,32064] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,32064] = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 32000
llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 32000
llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 24: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 25: tokenizer.chat_template str = {% for message in messages %}{% if (m...
llama_model_loader: - kv 26: general.quantization_version u32 = 2
llama_model_loader: - type f32: 83 tensors
llama_model_loader: - type q4_K: 101 tensors
llama_model_loader: - type q5_K: 40 tensors
llama_model_loader: - type q6_K: 21 tensors
llm_load_vocab: special tokens cache size = 323
llm_load_vocab: token to piece cache size = 0.1687 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = phi3
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32064
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 131072
llm_load_print_meta: n_embd = 5120
llm_load_print_meta: n_head = 40
llm_load_print_meta: n_head_kv = 10
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1280
llm_load_print_meta: n_embd_v_gqa = 1280
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 17920
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 2
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 4096
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: model type = 14B
llm_load_print_meta: model ftype = Q4_K - Medium
llm_load_print_meta: model params = 13.96 B
llm_load_print_meta: model size = 7.98 GiB (4.91 BPW)
llm_load_print_meta: general.name = Phi3
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 32000 '<|endoftext|>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 32000 '<|endoftext|>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_print_meta: EOT token = 32007 '<|end|>'
llm_load_print_meta: max token length = 48
llm_load_tensors: ggml ctx size = 0.13 MiB
llm_load_tensors: CPU buffer size = 8169.25 MiB
```
|
mtgv/MobileLLaMA-1.4B-Chat | mtgv | "2023-12-30T03:33:30Z" | 2,687 | 12 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:Aeala/ShareGPT_Vicuna_unfiltered",
"arxiv:2312.16886",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-29T02:17:37Z" | ---
license: apache-2.0
datasets:
- Aeala/ShareGPT_Vicuna_unfiltered
tags:
- llama
---
# Model Summery
MobileLLaMA-1.4B-Chat is fine-tuned from [MobileLLaMA-1.4B-Base](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Base) with supervised instruction fine-tuning on [ShareGPT dataset](https://huggingface.co/datasets/Aeala/ShareGPT_Vicuna_unfiltered).
# Model Sources
- Repository: https://github.com/Meituan-AutoML/MobileVLM
- Paper: https://arxiv.org/abs/2312.16886
# How to Get Started with the Model
Model weights can be loaded with Hugging Face Transformers. Examples can be found at [Github](https://github.com/Meituan-AutoML/MobileVLM).
# Training Details
please refer to our paper in section 4.1: [MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://arxiv.org/pdf/2312.16886.pdf). |
CoprolaliacPress/The_Editor-Q6_K-GGUF | CoprolaliacPress | "2024-07-01T08:12:47Z" | 2,687 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"base_model:CoprolaliacPress/The_Editor",
"endpoints_compatible",
"region:us"
] | null | "2024-07-01T08:12:23Z" | ---
base_model: CoprolaliacPress/The_Editor
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
---
# CoprolaliacPress/The_Editor-Q6_K-GGUF
This model was converted to GGUF format from [`CoprolaliacPress/The_Editor`](https://huggingface.co/CoprolaliacPress/The_Editor) 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/CoprolaliacPress/The_Editor) 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 CoprolaliacPress/The_Editor-Q6_K-GGUF --hf-file the_editor-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CoprolaliacPress/The_Editor-Q6_K-GGUF --hf-file the_editor-q6_k.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CoprolaliacPress/The_Editor-Q6_K-GGUF --hf-file the_editor-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CoprolaliacPress/The_Editor-Q6_K-GGUF --hf-file the_editor-q6_k.gguf -c 2048
```
|
timm/vit_tiny_patch16_384.augreg_in21k_ft_in1k | timm | "2023-05-06T00:30:08Z" | 2,686 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-21k",
"arxiv:2106.10270",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-12-22T07:56:14Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-21k
---
# Model card for vit_tiny_patch16_384.augreg_in21k_ft_in1k
A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 5.8
- GMACs: 3.2
- Activations (M): 12.1
- Image size: 384 x 384
- **Papers:**
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-21k
- **Original:** https://github.com/google-research/vision_transformer
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_tiny_patch16_384.augreg_in21k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_tiny_patch16_384.augreg_in21k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 577, 192) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{steiner2021augreg,
title={How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers},
author={Steiner, Andreas and Kolesnikov, Alexander and and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
journal={arXiv preprint arXiv:2106.10270},
year={2021}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
valhalla/t5-small-qg-hl | valhalla | "2021-06-23T14:43:48Z" | 2,685 | 1 | transformers | [
"transformers",
"pytorch",
"jax",
"t5",
"text2text-generation",
"question-generation",
"dataset:squad",
"arxiv:1910.10683",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2022-03-02T23:29:05Z" | ---
datasets:
- squad
tags:
- question-generation
widget:
- text: "<hl> 42 <hl> is the answer to life, the universe and everything. </s>"
- text: "Python is a programming language. It is developed by <hl> Guido Van Rossum <hl>. </s>"
- text: "Simple is better than <hl> complex <hl>. </s>"
license: mit
---
## T5 for question-generation
This is [t5-small](https://arxiv.org/abs/1910.10683) model trained for answer aware question generation task. The answer spans are highlighted within the text with special highlight tokens.
You can play with the model using the inference API, just highlight the answer spans with `<hl>` tokens and end the text with `</s>`. For example
`<hl> 42 <hl> is the answer to life, the universe and everything. </s>`
For more deatils see [this](https://github.com/patil-suraj/question_generation) repo.
### Model in action 🚀
You'll need to clone the [repo](https://github.com/patil-suraj/question_generation).
[](https://colab.research.google.com/github/patil-suraj/question_generation/blob/master/question_generation.ipynb)
```python3
from pipelines import pipeline
nlp = pipeline("question-generation")
nlp("42 is the answer to life, universe and everything.")
=> [{'answer': '42', 'question': 'What is the answer to life, universe and everything?'}]
``` |
Yntec/AbyssOrangeMix | Yntec | "2024-04-28T03:37:03Z" | 2,684 | 3 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"WarriorMama777",
"NovelAI",
"AnythingV3.0",
"hesw23168",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-04-27T13:51:21Z" | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
- WarriorMama777
- NovelAI
- AnythingV3.0
- hesw23168
---
# Abyss Orange Mix
768x768 version of this model with the MoistMixV2VAE baked in. Original page: https://huggingface.co/WarriorMama777/OrangeMixs#abyssorangemix-aom-1
Samples and prompts:
(Click for larger)
Top left: face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck
Top right: 1990 movie screenshot. beautiful daughters. festive scene at a copper brewery with a wooden keg of beer in the center. sitting cute little girls. Display mugs of dark beer. faces. accompanied by autumn ingredients
Bottom left: Full body picture of a pretty cute little girl making cake in school, detailed brown eyes, short smile, beautiful and aesthetic, intricate, neat hair, highly detailed, detailed face, smooth, sharp focus, chiaroscuro, magazine ad, 1949, 2D Game Art, anime on canvas, rossdraws, clay mann, CHIBI ART, light novel cover art
Bottom right: (digital painting:1.3), cartoon, trending on artstation, close up of pretty cute Swedish loli, centered, (messy bun), blue eyes, pale skin, behind teal mountains, snow, (high detailed skin:1.2), film grain, Fujifilm XT3, (high detailed face:1.3) |
mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF | mradermacher | "2024-06-09T17:25:22Z" | 2,684 | 0 | transformers | [
"transformers",
"gguf",
"bangla",
"large language model",
"bn",
"en",
"dataset:wikimedia/wikipedia",
"base_model:BanglaLLM/BanglaLLama-3-8b-BnWiki-Base",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | "2024-06-09T16:19:30Z" | ---
base_model: BanglaLLM/BanglaLLama-3-8b-BnWiki-Base
datasets:
- wikimedia/wikipedia
language:
- bn
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- bangla
- large language model
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/BanglaLLM/BanglaLLama-3-8b-BnWiki-Base
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-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/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-BnWiki-Base-GGUF/resolve/main/BanglaLLama-3-8b-BnWiki-Base.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 -->
|
RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf | RichardErkhov | "2024-06-22T23:33:52Z" | 2,683 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-22T23:25:11Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
TinyLlama-1.1B-Chat-v0.4 - GGUF
- Model creator: https://huggingface.co/TinyLlama/
- Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.4/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [TinyLlama-1.1B-Chat-v0.4.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q2_K.gguf) | Q2_K | 0.4GB |
| [TinyLlama-1.1B-Chat-v0.4.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [TinyLlama-1.1B-Chat-v0.4.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.IQ3_S.gguf) | IQ3_S | 0.47GB |
| [TinyLlama-1.1B-Chat-v0.4.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
| [TinyLlama-1.1B-Chat-v0.4.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [TinyLlama-1.1B-Chat-v0.4.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q3_K.gguf) | Q3_K | 0.51GB |
| [TinyLlama-1.1B-Chat-v0.4.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [TinyLlama-1.1B-Chat-v0.4.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [TinyLlama-1.1B-Chat-v0.4.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
| [TinyLlama-1.1B-Chat-v0.4.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q4_0.gguf) | Q4_0 | 0.59GB |
| [TinyLlama-1.1B-Chat-v0.4.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
| [TinyLlama-1.1B-Chat-v0.4.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
| [TinyLlama-1.1B-Chat-v0.4.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q4_K.gguf) | Q4_K | 0.62GB |
| [TinyLlama-1.1B-Chat-v0.4.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
| [TinyLlama-1.1B-Chat-v0.4.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q4_1.gguf) | Q4_1 | 0.65GB |
| [TinyLlama-1.1B-Chat-v0.4.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q5_0.gguf) | Q5_0 | 0.71GB |
| [TinyLlama-1.1B-Chat-v0.4.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
| [TinyLlama-1.1B-Chat-v0.4.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q5_K.gguf) | Q5_K | 0.73GB |
| [TinyLlama-1.1B-Chat-v0.4.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
| [TinyLlama-1.1B-Chat-v0.4.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q5_1.gguf) | Q5_1 | 0.77GB |
| [TinyLlama-1.1B-Chat-v0.4.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q6_K.gguf) | Q6_K | 0.84GB |
| [TinyLlama-1.1B-Chat-v0.4.Q8_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-Chat-v0.4-gguf/blob/main/TinyLlama-1.1B-Chat-v0.4.Q8_0.gguf) | Q8_0 | 1.09GB |
Original model description:
---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- OpenAssistant/oasst_top1_2023-08-25
language:
- en
---
<div align="center">
# TinyLlama-1.1B
</div>
https://github.com/jzhang38/TinyLlama
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
#### This Model
This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T).
The dataset used is [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25) following the [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) format.
#### How to use
You will need the transformers>=4.31
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
```
from transformers import AutoTokenizer
import transformers
import torch
model = "PY007/TinyLlama-1.1B-Chat-v0.4"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
CHAT_EOS_TOKEN_ID = 32002
prompt = "How to get in a good university?"
formatted_prompt = (
f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
)
sequences = pipeline(
formatted_prompt,
do_sample=True,
top_k=50,
top_p = 0.9,
num_return_sequences=1,
repetition_penalty=1.1,
max_new_tokens=1024,
eos_token_id=CHAT_EOS_TOKEN_ID,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
|
maywell/Synatra-10.7B-v0.4 | maywell | "2024-01-29T03:17:44Z" | 2,682 | 9 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-27T12:51:26Z" | ---
license: cc-by-sa-4.0
---
# **Synatra-10.7B-v0.4🐧**
# Join our discord
[Server Link](https://discord.gg/MrBt3PXdXc)
# **License**
The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included **cc-by-sa-4.0** license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.
# **Model Details**
**Base Model**
[upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0)
**Trained On**
A100 80GB * 1
**Instruction format**
It follows **Alpaca** format.
# **Model Benchmark**
## Ko-LLM-Leaderboard
On Benchmarking...
# **Implementation Code**
Since, chat_template already contains insturction format above.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-10.7B-v0.4")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-10.7B-v0.4")
messages = [
{"role": "user", "content": "바나나는 원래 하얀색이야?"},
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
``` |
GalalEwida/LLM-BERT-Model-Based-Skills-Extraction-from-jobdescription | GalalEwida | "2024-02-23T00:57:41Z" | 2,682 | 8 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"token-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2024-02-23T00:48:26Z" | Entry not found |
uclanlp/plbart-java-cs | uclanlp | "2021-11-09T17:08:40Z" | 2,681 | 0 | transformers | [
"transformers",
"pytorch",
"plbart",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2022-03-02T23:29:05Z" | Entry not found |
NinedayWang/PolyCoder-2.7B | NinedayWang | "2022-10-21T06:03:23Z" | 2,680 | 38 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"arxiv:2202.13169",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-10-20T09:47:34Z" | This is a PolyCoder model with **2.7B** parameters,
presented in the paper ["A Systematic Evaluation of Large Language Models of Code"](https://arxiv.org/pdf/2202.13169.pdf) (MAPS'2022 and ICLR'2022 Workshop Deep Learning 4 Code).
The model was trained on **249 GB** of code across **12** programming languages.
**Note** - this model requires `transformers` version of at least **4.23.0**:
```
pip install transformers==4.23.0
```
For more information, see: [https://github.com/VHellendoorn/Code-LMs](https://github.com/VHellendoorn/Code-LMs)
If you use this model, please cite:
```
@inproceedings{
xu2022polycoder,
title={A Systematic Evaluation of Large Language Models of Code},
author={Frank F. Xu and Uri Alon and Graham Neubig and Vincent Josua Hellendoorn},
booktitle={Deep Learning for Code Workshop},
year={2022},
url={https://openreview.net/forum?id=SLcEnoObJZq}
}
``` |
TheBloke/CodeLlama-34B-Python-GGUF | TheBloke | "2023-09-27T12:46:07Z" | 2,680 | 34 | transformers | [
"transformers",
"gguf",
"llama",
"llama-2",
"text-generation",
"code",
"arxiv:2308.12950",
"base_model:codellama/CodeLlama-34b-python-hf",
"license:llama2",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-24T21:32:21Z" | ---
language:
- code
license: llama2
tags:
- llama-2
model_name: CodeLlama 34B Python
base_model: codellama/CodeLlama-34b-python-hf
inference: false
model_creator: Meta
model_type: llama
pipeline_tag: text-generation
prompt_template: '[INST] Write code to solve the following coding problem that obeys
the constraints and passes the example test cases. Please wrap your code answer
using ```:
{prompt}
[/INST]
'
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 -->
# CodeLlama 34B Python - GGUF
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [CodeLlama 34B Python](https://huggingface.co/codellama/CodeLlama-34b-python-hf)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Meta's CodeLlama 34B Python](https://huggingface.co/codellama/CodeLlama-34b-python-hf).
<!-- 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/CodeLlama-34B-Python-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF)
* [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-34b-python-hf)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: CodeLlama
```
[INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:
{prompt}
[/INST]
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [codellama-34b-python.Q2_K.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q2_K.gguf) | Q2_K | 2 | 14.21 GB| 16.71 GB | smallest, significant quality loss - not recommended for most purposes |
| [codellama-34b-python.Q3_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q3_K_S.gguf) | Q3_K_S | 3 | 14.61 GB| 17.11 GB | very small, high quality loss |
| [codellama-34b-python.Q3_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q3_K_M.gguf) | Q3_K_M | 3 | 16.28 GB| 18.78 GB | very small, high quality loss |
| [codellama-34b-python.Q3_K_L.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q3_K_L.gguf) | Q3_K_L | 3 | 17.77 GB| 20.27 GB | small, substantial quality loss |
| [codellama-34b-python.Q4_0.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q4_0.gguf) | Q4_0 | 4 | 19.05 GB| 21.55 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [codellama-34b-python.Q4_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q4_K_S.gguf) | Q4_K_S | 4 | 19.15 GB| 21.65 GB | small, greater quality loss |
| [codellama-34b-python.Q4_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q4_K_M.gguf) | Q4_K_M | 4 | 20.22 GB| 22.72 GB | medium, balanced quality - recommended |
| [codellama-34b-python.Q5_0.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q5_0.gguf) | Q5_0 | 5 | 23.24 GB| 25.74 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [codellama-34b-python.Q5_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q5_K_S.gguf) | Q5_K_S | 5 | 23.24 GB| 25.74 GB | large, low quality loss - recommended |
| [codellama-34b-python.Q5_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q5_K_M.gguf) | Q5_K_M | 5 | 23.84 GB| 26.34 GB | large, very low quality loss - recommended |
| [codellama-34b-python.Q6_K.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q6_K.gguf) | Q6_K | 6 | 27.68 GB| 30.18 GB | very large, extremely low quality loss |
| [codellama-34b-python.Q8_0.gguf](https://huggingface.co/TheBloke/CodeLlama-34B-Python-GGUF/blob/main/codellama-34b-python.Q8_0.gguf) | Q8_0 | 8 | 35.86 GB| 38.36 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/CodeLlama-34B-Python-GGUF and below it, a specific filename to download, such as: codellama-34b-python.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/CodeLlama-34B-Python-GGUF codellama-34b-python.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/CodeLlama-34B-Python-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/CodeLlama-34B-Python-GGUF codellama-34b-python.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 codellama-34b-python.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:\n{prompt}\n[/INST]"
```
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/CodeLlama-34B-Python-GGUF", model_file="codellama-34b-python.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: Meta's CodeLlama 34B Python
# **Code Llama**
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 34B Python specialist version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
| | Base Model | Python | Instruct |
| --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
## Model Use
To use this model, please make sure to install transformers from `main` until the next version is released:
```bash
pip install git+https://github.com/huggingface/transformers.git@main accelerate
```
Model capabilities:
- [x] Code completion.
- [ ] Infilling.
- [ ] Instructions / chat.
- [x] Python specialist.
## Model Details
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
**Model Developers** Meta
**Variations** Code Llama comes in three model sizes, and three variants:
* Code Llama: base models designed for general code synthesis and understanding
* Code Llama - Python: designed specifically for Python
* Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B and 34B parameters.
**This repository contains the Python version of the 34B parameters model.**
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
**Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## Intended Use
**Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
**Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
## Hardware and Software
**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
**Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
## Training Data
All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
## Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
## Ethical Considerations and Limitations
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-user-guide](https://ai.meta.com/llama/responsible-user-guide).
<!-- original-model-card end -->
|
timm/tf_efficientnetv2_xl.in21k | timm | "2023-04-27T22:18:06Z" | 2,679 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-21k",
"arxiv:2104.00298",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-12-13T00:19:38Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-21k
---
# Model card for tf_efficientnetv2_xl.in21k
A EfficientNet-v2 image classification model. Trained on ImageNet-21k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 234.8
- GMACs: 52.8
- Activations (M): 139.2
- Image size: train = 384 x 384, test = 512 x 512
- **Papers:**
- EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298
- **Dataset:** ImageNet-21k
- **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tf_efficientnetv2_xl.in21k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnetv2_xl.in21k',
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, 32, 192, 192])
# torch.Size([1, 64, 96, 96])
# torch.Size([1, 96, 48, 48])
# torch.Size([1, 256, 24, 24])
# torch.Size([1, 640, 12, 12])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnetv2_xl.in21k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 12, 12) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{tan2021efficientnetv2,
title={Efficientnetv2: Smaller models and faster training},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={10096--10106},
year={2021},
organization={PMLR}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
digiplay/BadAnime_v1 | digiplay | "2024-05-03T10:38:01Z" | 2,679 | 7 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-07-15T13:49:12Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/107703?modelVersionId=115852
Sample image I made thru Huggingface's API :
Original Author's DEMO image :
 |
yanolja/EEVE-Korean-Instruct-2.8B-v1.0 | yanolja | "2024-03-04T12:26:40Z" | 2,679 | 14 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"generated_from_trainer",
"conversational",
"custom_code",
"arxiv:2402.14714",
"arxiv:2310.01377",
"arxiv:2306.02707",
"base_model:yanolja/EEVE-Korean-2.8B-v1.0",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-22T04:40:06Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
base_model: yanolja/EEVE-Korean-2.8B-v1.0
model-index:
- name: yanolja/EEVE-Korean-Instruct-2.8B-v1.0
results: []
---
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<p align="left">
<img src="https://huggingface.co/yanolja/EEVE-Korean-Instruct-2.8B-v1.0/resolve/main/eeve_logo.webp" width="50%"/>
<p>
# EEVE-Korean-Instruct-2.8B-v1.0
## Join Our Community on Discord!
If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server. It's worth noting that Korean is the primary language used in this server. The landscape of LLM is evolving rapidly, and without active sharing, our collective knowledge risks becoming outdated swiftly. Let's collaborate and drive greater impact together! Join us here: [Discord Link](https://discord.gg/b27bAHg95m).
## Our Dedicated Team (Alphabetical Order)
| Research | Engineering | Product Management | UX Design |
|-----------------|-----------------|--------------------|--------------
| Myeongho Jeong | Geon Kim | Bokyung Huh | Eunsue Choi |
| Seungduk Kim | Rifqi Alfi | | |
| Seungtaek Choi | Sanghoon Han | | |
| | Suhyun Kang | | |
## About the Model
This model is a fine-tuned version of [yanolja/EEVE-Korean-2.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-2.8B-v1.0), which is a Korean vocabulary-extended version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2). Specifically, we utilized Direct Preference Optimization (DPO) through the use of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
For more details, please refer to our technical report: [Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models](https://arxiv.org/abs/2402.14714).
## Prompt Template
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
Human: {prompt}
Assistant:
```
## How to Use it
```python
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yanolja/EEVE-Korean-Instruct-2.8B-v1.0", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("yanolja/EEVE-Korean-Instruct-2.8B-v1.0", trust_remote_code=True)
prompt_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {prompt}\nAssistant:\n"
text = '한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.\n\n(A) 경성\n(B) 부산\n(C) 평양\n(D) 서울\n(E) 전주'
model_inputs = tokenizer(prompt_template.format(prompt=text), return_tensors='pt')
outputs = model.generate(**model_inputs, max_new_tokens=256)
output_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
print(output_text)
```
### Example Output
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
Human: 한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.
(A) 경성
(B) 부산
(C) 평양
(D) 서울
(E) 전주
Assistant:
한국의 수도는 (D) 서울입니다. 서울은 수도권과 수도권 내의 주요 도시들을 포함하는 광역 행정구역으로, 대한민국의 수도입니다. 서울은 수도권 인구의 약 70%를 차지하며, 대한민국의 경제, 정치, 문화의 중심지입니다.
```
## Training Data
- Korean-translated version of [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
- Korean-translated version of [argilla/ultrafeedback-binarized-preferences-cleaned](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned)
- No other dataset was used
## Citation
```
@misc{kim2024efficient,
title={Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models},
author={Seungduk Kim and Seungtaek Choi and Myeongho Jeong},
year={2024},
eprint={2402.14714},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{cui2023ultrafeedback,
title={UltraFeedback: Boosting Language Models with High-quality Feedback},
author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
year={2023},
eprint={2310.01377},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{SlimOrcaDedup,
title = {SlimOrca Dedup: A Deduplicated Subset of SlimOrca},
author = {Wing Lian and Guan Wang and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium" and Nathan Hoos},
year = {2023},
publisher = {HuggingFace},
url = {https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup/}
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
# [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_yanolja__EEVE-Korean-Instruct-2.8B-v1.0)
| Metric |Value|
|---------------------------------|----:|
|Avg. |58.71|
|AI2 Reasoning Challenge (25-Shot)|58.28|
|HellaSwag (10-Shot) |72.42|
|MMLU (5-Shot) |53.35|
|TruthfulQA (0-shot) |48.32|
|Winogrande (5-shot) |74.82|
|GSM8k (5-shot) |45.11|
|
inswave/AISquare-Instruct-llama2-koen-13b-v0.9.24 | inswave | "2024-01-10T00:11:41Z" | 2,678 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-18T23:45:16Z" | ---
language:
- en
pipeline_tag: text-generation
license: cc-by-nc-4.0
---
# AISquare-Instruct-llama2-koen-13b-v0.9.24
## Model Details
**Developed by**
[Inswave Systems](https://www.inswave.com) UI Platform Team
**Method**
Using DPO method and SFT method
**Hardware**
We utilized an A100x4 * 1 for training our model
**Base Model**
[beomi/llama2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b)
# Implementation Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.24"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
```
---
|
lighthouse/mdeberta-v3-base-kor-further | lighthouse | "2023-07-19T08:12:05Z" | 2,677 | 13 | transformers | [
"transformers",
"pytorch",
"deberta-v2",
"deberta",
"deberta-v3",
"mdeberta",
"korean",
"pretraining",
"multilingual",
"en",
"ko",
"ar",
"bg",
"de",
"el",
"es",
"fr",
"hi",
"ru",
"sw",
"th",
"tr",
"ur",
"vi",
"zh",
"arxiv:2006.03654",
"arxiv:2111.09543",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | "2022-08-22T02:12:13Z" | ---
language:
- multilingual
- en
- ko
- ar
- bg
- de
- el
- es
- fr
- hi
- ru
- sw
- th
- tr
- ur
- vi
- zh
tags:
- deberta
- deberta-v3
- mdeberta
- korean
- pretraining
license: mit
---
# mDeBERTa-v3-base-kor-further
> 💡 아래 프로젝트는 KPMG Lighthouse Korea에서 진행하였습니다.
> KPMG Lighthouse Korea에서는, Financial area의 다양한 문제들을 해결하기 위해 Edge Technology의 NLP/Vision AI를 모델링하고 있습니다.
> https://kpmgkr.notion.site/
## What is DeBERTa?
- [DeBERTa](https://arxiv.org/abs/2006.03654)는 `Disentangled Attention` + `Enhanced Mask Decoder` 를 적용하여 단어의 positional information을 효과적으로 학습합니다. 이와 같은 아이디어를 통해, 기존의 BERT, RoBERTa에서 사용했던 absolute position embedding과는 달리 DeBERTa는 단어의 상대적인 위치 정보를 학습 가능한 벡터로 표현하여 모델을 학습하게 됩니다. 결과적으로, BERT, RoBERTA 와 비교했을 때 더 준수한 성능을 보여주었습니다.
- [DeBERTa-v3](https://arxiv.org/abs/2111.09543)에서는, 이전 버전에서 사용했던 MLM (Masked Language Model) 을 RTD (Replaced Token Detection) Task 로 대체한 ELECTRA 스타일의 사전학습 방법과, Gradient-Disentangled Embedding Sharing 을 적용하여 모델 학습의 효율성을 개선하였습니다.
- DeBERTa의 아키텍처로 풍부한 한국어 데이터를 학습하기 위해서, `mDeBERTa-v3-base-kor-further` 는 microsoft 가 발표한 `mDeBERTa-v3-base` 를 약 40GB의 한국어 데이터에 대해서 **추가적인 사전학습**을 진행한 언어 모델입니다.
## How to Use
- Requirements
```
pip install transformers
pip install sentencepiece
```
- Huggingface Hub
```python
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("lighthouse/mdeberta-v3-base-kor-further") # DebertaV2ForModel
tokenizer = AutoTokenizer.from_pretrained("lighthouse/mdeberta-v3-base-kor-further") # DebertaV2Tokenizer (SentencePiece)
```
## Pre-trained Models
- 모델의 아키텍처는 기존 microsoft에서 발표한 `mdeberta-v3-base`와 동일한 구조입니다.
| | Vocabulary(K) | Backbone Parameters(M) | Hidden Size | Layers | Note |
| --- | --- | --- | --- | --- | --- |
| mdeberta-v3-base-kor-further (mdeberta-v3-base와 동일) | 250 | 86 | 768 | 12 | 250K new SPM vocab |
## Further Pretraing Details (MLM Task)
- `mDeBERTa-v3-base-kor-further` 는 `microsoft/mDeBERTa-v3-base` 를 약 40GB의 한국어 데이터에 대해서 MLM Task를 적용하여 추가적인 사전 학습을 진행하였습니다.
| | Max length | Learning Rate | Batch Size | Train Steps | Warm-up Steps |
| --- | --- | --- | --- | --- | --- |
| mdeberta-v3-base-kor-further | 512 | 2e-5 | 8 | 5M | 50k |
## Datasets
- 모두의 말뭉치(신문, 구어, 문어), 한국어 Wiki, 국민청원 등 약 40 GB 의 한국어 데이터셋이 추가적인 사전학습에 사용되었습니다.
- Train: 10M lines, 5B tokens
- Valid: 2M lines, 1B tokens
- cf) 기존 mDeBERTa-v3은 XLM-R 과 같이 [cc-100 데이터셋](https://data.statmt.org/cc-100/)으로 학습되었으며, 그 중 한국어 데이터셋의 크기는 54GB입니다.
## Fine-tuning on NLU Tasks - Base Model
| Model | Size | NSMC(acc) | Naver NER(F1) | PAWS (acc) | KorNLI (acc) | KorSTS (spearman) | Question Pair (acc) | KorQuaD (Dev) (EM/F1) | Korean-Hate-Speech (Dev) (F1) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| XLM-Roberta-Base | 1.03G | 89.03 | 86.65 | 82.80 | 80.23 | 78.45 | 93.80 | 64.70 / 88.94 | 64.06 |
| mdeberta-base | 534M | 90.01 | 87.43 | 85.55 | 80.41 | **82.65** | 94.06 | 65.48 / 89.74 | 62.91 |
| mdeberta-base-kor-further (Ours) | 534M | **90.52** | **87.87** | **85.85** | **80.65** | 81.90 | **94.98** | **66.07 / 90.35** | **68.16** |
## KPMG Lighthouse KR
https://kpmgkr.notion.site/
## Citation
```
@misc{he2021debertav3,
title={DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing},
author={Pengcheng He and Jianfeng Gao and Weizhu Chen},
year={2021},
eprint={2111.09543},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@inproceedings{
he2021deberta,
title={DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION},
author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=XPZIaotutsD}
}
```
## Reference
- [mDeBERTa-v3-base-kor-further](https://github.com/kpmg-kr/mDeBERTa-v3-base-kor-further)
- [DeBERTa](https://github.com/microsoft/DeBERTa)
- [Huggingface Transformers](https://github.com/huggingface/transformers)
- [모두의 말뭉치](https://corpus.korean.go.kr/)
- [Korpora: Korean Corpora Archives](https://github.com/ko-nlp/Korpora)
- [sooftware/Korean PLM](https://github.com/sooftware/Korean-PLM) |
timm/tf_efficientnetv2_b3.in21k | timm | "2023-04-27T22:17:19Z" | 2,677 | 1 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-21k",
"arxiv:2104.00298",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-12-13T00:14:53Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-21k
---
# Model card for tf_efficientnetv2_b3.in21k
A EfficientNet-v2 image classification model. Trained on ImageNet-21k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 46.4
- GMACs: 2.0
- Activations (M): 10.0
- Image size: train = 240 x 240, test = 300 x 300
- **Papers:**
- EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298
- **Dataset:** ImageNet-21k
- **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tf_efficientnetv2_b3.in21k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnetv2_b3.in21k',
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, 16, 120, 120])
# torch.Size([1, 40, 60, 60])
# torch.Size([1, 56, 30, 30])
# torch.Size([1, 136, 15, 15])
# torch.Size([1, 232, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnetv2_b3.in21k',
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, 1536, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{tan2021efficientnetv2,
title={Efficientnetv2: Smaller models and faster training},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={10096--10106},
year={2021},
organization={PMLR}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
BAAI/seggpt-vit-large | BAAI | "2024-02-22T14:16:11Z" | 2,677 | 4 | transformers | [
"transformers",
"safetensors",
"seggpt",
"vision",
"arxiv:2304.03284",
"license:apache-2.0",
"region:us"
] | null | "2023-11-30T07:20:36Z" | ---
license: apache-2.0
tags:
- vision
inference: false
---
# SegGPT model
The SegGPT model was proposed in [SegGPT: Segmenting Everything In Context](https://arxiv.org/abs/2304.03284) by Xinlong Wang, Xiaosong Zhang, Yue Cao, Wen Wang, Chunhua Shen, Tiejun Huang.
## Model description
SegGPT employs a decoder-only (GPT-like) Transformer that can generate a segmentation mask given an input image, a prompt image and its corresponding prompt mask.
The model achieves remarkable one-shot results with 56.1 mIoU on COCO-20 and 85.6 mIoU on FSS-1000.
## Intended uses & limitations
You can use the raw model for one-shot image segmentation.
### How to use
Here's how to use the model for one-shot semantic segmentation:
```python
import torch
from datasets import load_dataset
from transformers import SegGptImageProcessor, SegGptForImageSegmentation
model_id = "BAAI/seggpt-vit-large"
image_processor = SegGptImageProcessor.from_pretrained(checkpoint)
model = SegGptForImageSegmentation.from_pretrained(checkpoint)
dataset_id = "EduardoPacheco/FoodSeg103"
ds = load_dataset(dataset_id, split="train")
# Number of labels in FoodSeg103 (not including background)
num_labels = 103
image_input = ds[4]["image"]
ground_truth = ds[4]["label"]
image_prompt = ds[29]["image"]
mask_prompt = ds[29]["label"]
inputs = image_processor(
images=image_input,
prompt_images=image_prompt,
prompt_masks=mask_prompt,
num_labels=num_labels,
return_tensors="pt"
)
with torch.no_grad():
outputs = model(**inputs)
target_sizes = [image_input.size[::-1]]
mask = image_processor.post_process_semantic_segmentation(outputs, target_sizes, num_labels=num_labels)[0]
```
### BibTeX entry and citation info
```bibtex
@misc{wang2023seggpt,
title={SegGPT: Segmenting Everything In Context},
author={Xinlong Wang and Xiaosong Zhang and Yue Cao and Wen Wang and Chunhua Shen and Tiejun Huang},
year={2023},
eprint={2304.03284},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
``` |
p1atdev/wd-swinv2-tagger-v3-hf | p1atdev | "2024-03-11T07:55:43Z" | 2,677 | 9 | transformers | [
"transformers",
"onnx",
"safetensors",
"swinv2",
"image-classification",
"wd-tagger",
"optimum",
"custom_code",
"base_model:SmilingWolf/wd-swinv2-tagger-v3",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | image-classification | "2024-03-08T04:33:49Z" | ---
library_name: transformers
license: apache-2.0
base_model: SmilingWolf/wd-swinv2-tagger-v3
inference: false
tags:
- wd-tagger
- optimum
---
# WD SwinV2 Tagger v3 with 🤗 transformers
Converted from [SmilingWolf/wd-swinv2-tagger-v3](https://huggingface.co/SmilingWolf/wd-swinv2-tagger-v3) to transformers library format.
## Example
[](https://colab.research.google.com/gist/p1atdev/d420d9fcd5c8ea66d9e10918fc330741/wd-swinv2-tagger-v3-hf-pipe.ipynb)
### Installation
```bash
pip install transformers
```
### Pipeline
```py
from transformers import pipeline
pipe = pipeline(
"image-classification",
model="p1atdev/wd-swinv2-tagger-v3-hf",
trust_remote_code=True,
)
print(pipe("sample.webp", top_k=15))
#[{'label': '1girl', 'score': 0.9973934888839722},
# {'label': 'solo', 'score': 0.9719744324684143},
# {'label': 'dress', 'score': 0.9539461135864258},
# {'label': 'hat', 'score': 0.9511678218841553},
# {'label': 'outdoors', 'score': 0.9438753128051758},
# ...
```
### AutoModel
```py
from PIL import Image
import numpy as np
import torch
from transformers import (
AutoImageProcessor,
AutoModelForImageClassification,
)
MODEL_NAME = "p1atdev/wd-swinv2-tagger-v3-hf"
model = AutoModelForImageClassification.from_pretrained(
MODEL_NAME,
)
processor = AutoImageProcessor.from_pretrained(MODEL_NAME, trust_remote_code=True)
image = Image.open("sample.webp")
inputs = processor.preprocess(image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs.to(model.device, model.dtype))
logits = torch.sigmoid(outputs.logits[0]) # take the first logits
# get probabilities
results = {model.config.id2label[i]: logit.float() for i, logit in enumerate(logits)}
results = {
k: v for k, v in sorted(results.items(), key=lambda item: item[1], reverse=True) if v > 0.35 # 35% threshold
}
print(results) # rating tags and character tags are also included
#{'1girl': tensor(0.9974),
# 'solo': tensor(0.9720),
# 'dress': tensor(0.9539),
# 'hat': tensor(0.9512),
# 'outdoors': tensor(0.9439),
# ...
```
### Accelerate with 🤗 Optimum
Maybe about 30% faster and about 50% light weight model size than transformers version, but the accuracy is slightly degraded.
```bash
pip install optimum[onnxruntime]
```
```diff
-from transformers import pipeline
+from optimum.pipelines import pipeline
pipe = pipeline(
"image-classification",
model="p1atdev/wd-swinv2-tagger-v3-hf",
trust_remote_code=True,
)
print(pipe("sample.webp", top_k=15))
#[{'label': '1girl', 'score': 0.9966088533401489},
# {'label': 'solo', 'score': 0.9740601778030396},
# {'label': 'dress', 'score': 0.9618403911590576},
# {'label': 'hat', 'score': 0.9563733339309692},
# {'label': 'outdoors', 'score': 0.945336639881134},
# ...
```
## Labels
All of rating tags have prefix `rating:` and character tags have prefix `character:`.
- Rating tags: `rating:general`, `rating:sensitive`, ...
- Character tags: `character:frieren`, `character:hatsune miku`, ... |
juliovp/distilbert_republican_democrat_tweets | juliovp | "2024-06-21T14:58:55Z" | 2,677 | 1 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"license:unknown",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2024-06-21T12:45:35Z" | ---
license: unknown
---
|
RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf | RichardErkhov | "2024-06-29T16:03:54Z" | 2,675 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-29T14:24:27Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1 - GGUF
- Model creator: https://huggingface.co/habanoz/
- Original model: https://huggingface.co/habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q2_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q2_K.gguf) | Q2_K | 0.4GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ3_S.gguf) | IQ3_S | 0.47GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K.gguf) | Q3_K | 0.51GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_0.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_0.gguf) | Q4_0 | 0.59GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_K.gguf) | Q4_K | 0.62GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_1.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q4_1.gguf) | Q4_1 | 0.65GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_0.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_0.gguf) | Q5_0 | 0.71GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_K.gguf) | Q5_K | 0.73GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_1.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q5_1.gguf) | Q5_1 | 0.77GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q6_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q6_K.gguf) | Q6_K | 0.84GB |
| [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q8_0.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-gguf/blob/main/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1.Q8_0.gguf) | Q8_0 | 1.09GB |
Original model description:
---
language:
- en
license: apache-2.0
datasets:
- databricks/databricks-dolly-15k
pipeline_tag: text-generation
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
model-index:
- name: TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
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: 30.55
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
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: 53.7
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
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: 26.07
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
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: 35.85
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
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: 58.09
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
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: 0.0
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1
name: Open LLM Leaderboard
---
TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T finetuned using dolly dataset.
Training took 1 hour on an 'ml.g5.xlarge' instance.
```python
hyperparameters ={
'num_train_epochs': 3, # number of training epochs
'per_device_train_batch_size': 6, # batch size for training
'gradient_accumulation_steps': 2, # Number of updates steps to accumulate
'gradient_checkpointing': True, # save memory but slower backward pass
'bf16': True, # use bfloat16 precision
'tf32': True, # use tf32 precision
'learning_rate': 2e-4, # learning rate
'max_grad_norm': 0.3, # Maximum norm (for gradient clipping)
'warmup_ratio': 0.03, # warmup ratio
"lr_scheduler_type":"constant", # learning rate scheduler
'save_strategy': "epoch", # save strategy for checkpoints
"logging_steps": 10, # log every x steps
'merge_adapters': True, # wether to merge LoRA into the model (needs more memory)
'use_flash_attn': True, # Whether to use Flash Attention
}
```
# [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_habanoz__TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |34.04|
|AI2 Reasoning Challenge (25-Shot)|30.55|
|HellaSwag (10-Shot) |53.70|
|MMLU (5-Shot) |26.07|
|TruthfulQA (0-shot) |35.85|
|Winogrande (5-shot) |58.09|
|GSM8k (5-shot) | 0.00|
|
Subsets and Splits
No saved queries yet
Save your SQL queries to embed, download, and access them later. Queries will appear here once saved.