Instructions to use tencent/Hy4-preview-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hy4-preview-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hy4-preview-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/Hy4-preview-FP8")
model = AutoModelForCausalLM.from_pretrained("tencent/Hy4-preview-FP8", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tencent/Hy4-preview-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hy4-preview-FP8"
# 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/Hy4-preview-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hy4-preview-FP8

SGLang

How to use tencent/Hy4-preview-FP8 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/Hy4-preview-FP8" \
    --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/Hy4-preview-FP8",
		"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/Hy4-preview-FP8" \
        --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/Hy4-preview-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hy4-preview-FP8 with Docker Model Runner:
```
docker model run hf.co/tencent/Hy4-preview-FP8
```

JustinTong commited on Aug 28

Commit

efe5b4b

verified ·

1 Parent(s): 079d998

SGLang: use the prebuilt multi-arch image instead of building from source

Browse files

Files changed (1) hide show

README.md +12 -21

README.md CHANGED Viewed

@@ -193,29 +193,20 @@ vllm serve tencent/Hy4-preview-FP8 \
 ### SGLang
-Build SGLang from source:
-```bash
-git clone https://github.com/sgl-project/sglang
-cd sglang
-pip3 install pip --upgrade
-pip3 install "transformers>=5.6.0"
-pip3 install -e "python"
-```
-Launch SGLang server with MTP enabled:
 ```bash
-python3 -m sglang.launch_server \
-  --model tencent/Hy4-preview-FP8 \
-  --tp-size 8 \
-  --tool-call-parser hy_v4 \
-  --reasoning-parser hy_v4 \
-  --speculative-num-steps 2 \
-  --speculative-eagle-topk 1 \
-  --speculative-num-draft-tokens 3 \
-  --speculative-algorithm EAGLE \
-  --port 8000 \
-  --served-model-name hy4-preview
 ```
 ## Finetuning

 ### SGLang
+Use the prebuilt image `lmsysorg/sglang:hy4-preview` (multi-arch, x86 and Arm):
 ```bash
+docker pull lmsysorg/sglang:hy4-preview
+docker run --gpus all --ipc=host -p 8000:8000 lmsysorg/sglang:hy4-preview \
+  python3 -m sglang.launch_server \
+    --model tencent/Hy4-preview-FP8 \
+    --tp-size 8 \
+    --reasoning-parser auto --tool-call-parser auto \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
+    --served-model-name hy4-preview \
+    --port 8000
 ```
 ## Finetuning