Instructions to use HIT-SCIR/huozi3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HIT-SCIR/huozi3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HIT-SCIR/huozi3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HIT-SCIR/huozi3") model = AutoModelForCausalLM.from_pretrained("HIT-SCIR/huozi3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HIT-SCIR/huozi3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HIT-SCIR/huozi3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HIT-SCIR/huozi3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HIT-SCIR/huozi3
- SGLang
How to use HIT-SCIR/huozi3 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 "HIT-SCIR/huozi3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HIT-SCIR/huozi3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "HIT-SCIR/huozi3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HIT-SCIR/huozi3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HIT-SCIR/huozi3 with Docker Model Runner:
docker model run hf.co/HIT-SCIR/huozi3
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
<!-- markdownlint-disable first-line-h1 -->
|
| 2 |
<!-- markdownlint-disable html -->
|
| 3 |
|
|
@@ -592,4 +595,4 @@ stream_output = model.generate(
|
|
| 592 |
|
| 593 |
## <img src="https://cdn.jsdelivr.net/gh/LightChen233/blog-img/star.png" width="25" /> Star History
|
| 594 |
|
| 595 |
-
[](https://star-history.com/#HIT-SCIR/huozi&Date)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
<!-- markdownlint-disable first-line-h1 -->
|
| 5 |
<!-- markdownlint-disable html -->
|
| 6 |
|
|
|
|
| 595 |
|
| 596 |
## <img src="https://cdn.jsdelivr.net/gh/LightChen233/blog-img/star.png" width="25" /> Star History
|
| 597 |
|
| 598 |
+
[](https://star-history.com/#HIT-SCIR/huozi&Date)
|