Instructions to use VectorZhao/CSEG-RM-SFT-GRPO-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VectorZhao/CSEG-RM-SFT-GRPO-4B with Transformers:

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

pipe = pipeline("text-generation", model="VectorZhao/CSEG-RM-SFT-GRPO-4B")
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("VectorZhao/CSEG-RM-SFT-GRPO-4B")
model = AutoModelForCausalLM.from_pretrained("VectorZhao/CSEG-RM-SFT-GRPO-4B", 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 VectorZhao/CSEG-RM-SFT-GRPO-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VectorZhao/CSEG-RM-SFT-GRPO-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VectorZhao/CSEG-RM-SFT-GRPO-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VectorZhao/CSEG-RM-SFT-GRPO-4B

SGLang

How to use VectorZhao/CSEG-RM-SFT-GRPO-4B 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 "VectorZhao/CSEG-RM-SFT-GRPO-4B" \
    --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": "VectorZhao/CSEG-RM-SFT-GRPO-4B",
		"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 "VectorZhao/CSEG-RM-SFT-GRPO-4B" \
        --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": "VectorZhao/CSEG-RM-SFT-GRPO-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VectorZhao/CSEG-RM-SFT-GRPO-4B with Docker Model Runner:
```
docker model run hf.co/VectorZhao/CSEG-RM-SFT-GRPO-4B
```

CSEG-RM-SFT-GRPO-4B / README.md

VectorZhao

Add files using upload-large-folder tool

751ee61 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

538 Bytes

metadata

license: apache-2.0
base_model: Qwen/Qwen3-4B
tags:
  - cseg
  - qwen3
pipeline_tag: text-generation
library_name: transformers

CSEG-RM-SFT-GRPO-4B

GRPO-400 initialized from the CSEG-RM SFT checkpoint (global_step_220).

Method: SFT-GRPO
Size: 4B
Initialization: CSEG-RM-SFT-4B (global_step_220)
Checkpoint: global_step_400
Base model: Qwen/Qwen3-4B

Weights are bfloat16 Hugging Face safetensors. The judge is thinking-on and emits full JSON (--prompt-output-spec full).