Instructions to use AngelSlim/Hy3-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use AngelSlim/Hy3-GPTQ-Int4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AngelSlim/Hy3-GPTQ-Int4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AngelSlim/Hy3-GPTQ-Int4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AngelSlim/Hy3-GPTQ-Int4
- SGLang
How to use AngelSlim/Hy3-GPTQ-Int4 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "AngelSlim/Hy3-GPTQ-Int4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AngelSlim/Hy3-GPTQ-Int4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "AngelSlim/Hy3-GPTQ-Int4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AngelSlim/Hy3-GPTQ-Int4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AngelSlim/Hy3-GPTQ-Int4 with Docker Model Runner:
docker model run hf.co/AngelSlim/Hy3-GPTQ-Int4
Commit ·
143f1a9
1
Parent(s): 2a3793d
Create README.md (#1)
Browse files- Create README.md (0e5677524ad860f2f295f5fc0ac105bb12ca3a61)
README.md
CHANGED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- tencent/Hy3
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
---
|
| 7 |
+
<p align="center">
|
| 8 |
+
<picture>
|
| 9 |
+
<source media="(prefers-color-scheme: dark)" srcset="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo_light.png?raw=true">
|
| 10 |
+
<img alt="AngelSlim" src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo.png?raw=true" width=55%>
|
| 11 |
+
</picture>
|
| 12 |
+
</p>
|
| 13 |
+
<h3 align="center">
|
| 14 |
+
Dedicated to building a more intuitive, comprehensive, and efficient LLMs compression toolkit.
|
| 15 |
+
</h3>
|
| 16 |
+
|
| 17 |
+
<p align="center">
|
| 18 |
+
📖 <a href="https://angelslim.readthedocs.io/">Documentation</a>   |   🤗 <a href="https://huggingface.co/AngelSlim">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/organization/AngelSlim">ModelScope</a>   |   💬 <a href="./docs/source/assets/angel_slim_wechat.png">WeChat</a>
|
| 19 |
+
<br>
|
| 20 |
+
</p>
|
| 21 |
+
<br>
|
| 22 |
+
|
| 23 |
+
# Hy3 GPTQ-Int4 Quantization
|
| 24 |
+
|
| 25 |
+
<p align="center">
|
| 26 |
+
<img src="assets/benchmark.png" width="95%"/>
|
| 27 |
+
</p>
|