Instructions to use tencent/Hy3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hy3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tencent/Hy3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/Hy3")
model = AutoModelForCausalLM.from_pretrained("tencent/Hy3", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tencent/Hy3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hy3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Hy3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hy3

SGLang

How to use tencent/Hy3 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 "tencent/Hy3" \
    --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": "tencent/Hy3",
		"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 "tencent/Hy3" \
        --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": "tencent/Hy3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hy3 with Docker Model Runner:
```
docker model run hf.co/tencent/Hy3
```

yiqichen01 commited on 11 days ago

Commit

89ffd53

verified ·

1 Parent(s): e4e6605

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +5 -0
README_CN.md +5 -0

README.md CHANGED Viewed

@@ -51,6 +51,7 @@ tags:
   - [vLLM](#vllm)
   - [SGLang](#sglang)
 - [Finetuning](#finetuning)
 - [Quantization](#quantization)
 - [License](#license)
 - [Contact Us](#contact-us)
@@ -215,6 +216,10 @@ python3 -m sglang.launch_server \
 Hy3 provides a complete model finetuning pipeline. For detailed documentation, please refer to: [Finetuning Guide](https://huggingface.co/tencent/Hy3/blob/main/finetune/README.md)
 ## Quantization
 We provide [AngelSlim](https://github.com/tencent/AngelSlim), a more accessible, comprehensive, and efficient toolkit for large model compression. AngelSlim supports a comprehensive suite of compression tools for large-scale multimodal models, including common quantization algorithms, low-bit quantization, and speculative sampling.

   - [vLLM](#vllm)
   - [SGLang](#sglang)
 - [Finetuning](#finetuning)
+- [RL Post-training](#rl-post-training)
 - [Quantization](#quantization)
 - [License](#license)
 - [Contact Us](#contact-us)
 Hy3 provides a complete model finetuning pipeline. For detailed documentation, please refer to: [Finetuning Guide](https://huggingface.co/tencent/Hy3/blob/main/finetune/README.md)
+## RL Post-training
+Hy3 supports GRPO reinforcement learning training with [verl](https://github.com/volcengine/verl), training on Megatron-LM (model conversion via NVIDIA Megatron-Bridge) with vLLM rollout. For detailed documentation, please refer to: [RL Training Guide](https://huggingface.co/tencent/Hy3/blob/main/rl/README.md)
 ## Quantization
 We provide [AngelSlim](https://github.com/tencent/AngelSlim), a more accessible, comprehensive, and efficient toolkit for large model compression. AngelSlim supports a comprehensive suite of compression tools for large-scale multimodal models, including common quantization algorithms, low-bit quantization, and speculative sampling.

README_CN.md CHANGED Viewed

@@ -41,6 +41,7 @@
   - [vLLM](#使用-vllm-推理)
   - [SGLang](#使用-sglang-推理)
 - [模型微调](#模型微调)
 - [量化工具](#量化工具)
 - [许可证](#许可证)
 - [联系我们](#联系我们)
@@ -205,6 +206,10 @@ python3 -m sglang.launch_server \
 Hy3 提供了完整的模型微调流程，详细的微调文档请参考：[模型微调指南](https://huggingface.co/tencent/Hy3/blob/main/finetune/README_CN.md)
 ## 量化工具
 我们提供了 [AngelSlim](https://github.com/tencent/AngelSlim)——一套易用、全面、高效的大模型压缩工具包，涵盖常用量化算法、低比特量化和投机采样等能力。

   - [vLLM](#使用-vllm-推理)
   - [SGLang](#使用-sglang-推理)
 - [模型微调](#模型微调)
+- [强化学习训练](#强化学习训练)
 - [量化工具](#量化工具)
 - [许可证](#许可证)
 - [联系我们](#联系我们)
 Hy3 提供了完整的模型微调流程，详细的微调文档请参考：[模型微调指南](https://huggingface.co/tencent/Hy3/blob/main/finetune/README_CN.md)
+## 强化学习训练
+Hy3 支持基于 [verl](https://github.com/volcengine/verl) 的 GRPO 强化学习训练，训练侧使用 Megatron-LM（通过 NVIDIA Megatron-Bridge 完成模型转换），rollout 侧使用 vLLM。详细文档请参考：[强化学习训练指南](https://huggingface.co/tencent/Hy3/blob/main/rl/README_CN.md)
 ## 量化工具
 我们提供了 [AngelSlim](https://github.com/tencent/AngelSlim)——一套易用、全面、高效的大模型压缩工具包，涵盖常用量化算法、低比特量化和投机采样等能力。