Instructions to use tencent/Hunyuan-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hunyuan-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hunyuan-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/Hunyuan-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("tencent/Hunyuan-7B-Instruct")
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

vLLM

How to use tencent/Hunyuan-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hunyuan-7B-Instruct"
# 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/Hunyuan-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hunyuan-7B-Instruct

SGLang

How to use tencent/Hunyuan-7B-Instruct 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/Hunyuan-7B-Instruct" \
    --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/Hunyuan-7B-Instruct",
		"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/Hunyuan-7B-Instruct" \
        --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/Hunyuan-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hunyuan-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/tencent/Hunyuan-7B-Instruct
```

hunyuan-1.8b 转换onnx 模型时 BitShift算子出现这个 tensor(int32)无效是layers.31网络层出现什么问题吗？

by YouLei0106 - opened Aug 8, 2025

Discussion

YouLei0106

Aug 8, 2025

Traceback (most recent call last):
File "/opt/conda/bin/optimum-cli", line 7, in
sys.exit(main())
File "/opt/conda/lib/python3.9/site-packages/optimum/commands/optimum_cli.py", line 208, in main
service.run()
File "/opt/conda/lib/python3.9/site-packages/optimum/commands/export/onnx.py", line 276, in run
main_export(
File "/opt/conda/lib/python3.9/site-packages/optimum/exporters/onnx/main.py", line 418, in main_export
onnx_export_from_model(
File "/opt/conda/lib/python3.9/site-packages/optimum/exporters/onnx/convert.py", line 1186, in onnx_export_from_model
_, onnx_outputs = export_models(
File "/opt/conda/lib/python3.9/site-packages/optimum/exporters/onnx/convert.py", line 770, in export_models
export(
File "/opt/conda/lib/python3.9/site-packages/optimum/exporters/onnx/convert.py", line 903, in export
config.fix_dynamic_axes(output, device=device, input_shapes=input_shapes, dtype=dtype)
File "/opt/conda/lib/python3.9/site-packages/optimum/exporters/onnx/base.py", line 235, in fix_dynamic_axes
session = InferenceSession(model_path.as_posix(), providers=providers, sess_options=session_options)
File "/opt/conda/lib/python3.9/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 419, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "/opt/conda/lib/python3.9/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 480, in _create_inference_session
sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
onnxruntime.capi.onnxruntime_pybind11_state.InvalidGraph: [ONNXRuntimeError] : 10 : INVALID_GRAPH : Load model from hunyuan_tflite_float32/model.onnx failed:This is an invalid model. Type Error: Type 'tensor(int32)' of input parameter (/model/layers.31/mlp/up_proj/Expand_output_0) of operator (BitShift) in node (/model/layers.31/mlp/up_proj/BitShift) is invalid.

YouLei0106 changed discussion title from hunyuan-1.8b 转换onnx 模型时 BitShift算子出现这个 tensor(int32) 是layers.31网络层出现什么问题吗？ to hunyuan-1.8b 转换onnx 模型时 BitShift算子出现这个 tensor(int32)无效是layers.31网络层出现什么问题吗？ Aug 8, 2025

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

hunyuan-1.8b 转换onnx 模型时 BitShift算子出现这个 tensor(int32)无效 是layers.31网络层出现什么问题吗？

hunyuan-1.8b 转换onnx 模型时 BitShift算子出现这个 tensor(int32)无效是layers.31网络层出现什么问题吗？