Instructions to use tencent-community/Hunyuan-A52B-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent-community/Hunyuan-A52B-Instruct-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="tencent-community/Hunyuan-A52B-Instruct-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tencent-community/Hunyuan-A52B-Instruct-FP8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tencent-community/Hunyuan-A52B-Instruct-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent-community/Hunyuan-A52B-Instruct-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-community/Hunyuan-A52B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent-community/Hunyuan-A52B-Instruct-FP8

SGLang

How to use tencent-community/Hunyuan-A52B-Instruct-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-community/Hunyuan-A52B-Instruct-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-community/Hunyuan-A52B-Instruct-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-community/Hunyuan-A52B-Instruct-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-community/Hunyuan-A52B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent-community/Hunyuan-A52B-Instruct-FP8 with Docker Model Runner:
```
docker model run hf.co/tencent-community/Hunyuan-A52B-Instruct-FP8
```

ValueError: Unknown quantization type

by grg - opened Nov 7, 2024

Discussion

grg

Nov 7, 2024

Hello,
Thanks for the model!

I am having some issue with running the model. Here is the code snippet:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "tencent-community/Hunyuan-A52B-Instruct-FP8"

print("Loading tokenizer")
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

print("Loading model")
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)

Upon loading the model, this gives me the following error

ValueError: Unknown quantization type, got fp8 - supported types are: ['awq', 'bitsandbytes_4bit', 'bitsandbytes_8bit', 'gptq', 'aqlm', 'quanto', 'eetq', 'hqq', 'compressed-tensors', 'fbgemm_fp8', 'torchao', 'bitnet']

The problem can most probably be resolved by updating the config.json

"quant_method": "fp8"

or by defining which additional library and or version should be installed.

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