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")
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]:]))

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
```

Can you do an optiq quant?

#11

by codelion - opened 2 days ago

Discussion

codelion

2 days ago

Hello, thanks for the model, is it possible to provide optiq quant from mlx-optiq.com? It will help in efficient inference at apple macs.

sjl623

1 day ago

•

edited 1 day ago

Hello, thanks for the model, is it possible to provide optiq quant from mlx-optiq.com? It will help in efficient inference at apple macs.

Thanks for the suggestion, providing optiq quants for efficient inference on Apple Macs is a great idea. The blocker right now is architecture support: mlx-lm doesn't support the Hy3 architecture yet. Since optiq builds on top of mlx-lm for both quantization and inference, supporting it properly would mean adding Hy3 to mlx-lm and registering/adapting it in mlx-optiq. We’ll keep it in mind for the future, as MLX does indeed provide more efficient inference on Macs.

In the meantime, our AngelSlim team is exploring low-bit GGUF compression for on-device deployment. We’ll share updates when there’s more progress :)

codelion

about 17 hours ago

https://huggingface.co/avlp12/Hy3-Alis-MLX-Dynamic seems like there are others who have done some quants using it can be a useful reference ot try.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment