Instructions to use ZhouBencheng/9G4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZhouBencheng/9G4B with Transformers:

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

pipe = pipeline("text-generation", model="ZhouBencheng/9G4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ZhouBencheng/9G4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZhouBencheng/9G4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZhouBencheng/9G4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZhouBencheng/9G4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZhouBencheng/9G4B

SGLang

How to use ZhouBencheng/9G4B 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 "ZhouBencheng/9G4B" \
    --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": "ZhouBencheng/9G4B",
		"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 "ZhouBencheng/9G4B" \
        --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": "ZhouBencheng/9G4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZhouBencheng/9G4B with Docker Model Runner:
```
docker model run hf.co/ZhouBencheng/9G4B
```

九格 FM9G-4B（官方权重社区镜像）

本仓库由 ZhouBencheng 维护，镜像官方公开的 9G4B.tar。原始归档中的 10 个文件保持原始字节；本镜像没有修改或转换权重及配套代码。

官方项目：OSRedm / CPM-9G-8B
原始归档：华为云 9G4B.tar
归档大小：9,239,613,440 bytes
归档 SHA256：28ff0bad05c04b97433c57de1ed2aef0ccd233536e260773a4a9e7482b6db89c

原包 config.json 声明架构为 FM9GForCausalLM，max_position_embeddings 为 4096，torch_dtype 为 bfloat16。原包附带 configuration_fm9g.py、modeling_fm9g.py 和 infer_demo.py，使用其自定义模型代码。

Downloads last month: 179