Instructions to use mm824/Qwen3-8B-RM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mm824/Qwen3-8B-RM with Transformers:

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

pipe = pipeline("text-generation", model="mm824/Qwen3-8B-RM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mm824/Qwen3-8B-RM")
model = AutoModelForCausalLM.from_pretrained("mm824/Qwen3-8B-RM")
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 mm824/Qwen3-8B-RM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mm824/Qwen3-8B-RM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mm824/Qwen3-8B-RM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mm824/Qwen3-8B-RM

SGLang

How to use mm824/Qwen3-8B-RM 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 "mm824/Qwen3-8B-RM" \
    --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": "mm824/Qwen3-8B-RM",
		"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 "mm824/Qwen3-8B-RM" \
        --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": "mm824/Qwen3-8B-RM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mm824/Qwen3-8B-RM with Docker Model Runner:
```
docker model run hf.co/mm824/Qwen3-8B-RM
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

请说明你的使用目的。提交申请后，作者会手动审核。

Qwen3-8B-RM

这是一个基于 Qwen3-8B 的 Reward Model。模型权重需要申请访问，申请通过后才可以下载和使用。

Files

model.safetensors: base model weights
value_head.safetensors: reward/value head weights
config.json: model config
tokenizer.json: tokenizer
chat_template.jinja: chat template
rm_export_meta.json: reward model export metadata

Access

This model is gated. Please submit an access request and describe your intended use.

Terms

请勿未经授权重新分发模型权重。

Downloads last month: 225

Safetensors

Model size

8B params

Tensor type

BF16