Instructions to use dyyyyyyyy/FAPO-GenRM-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dyyyyyyyy/FAPO-GenRM-4B with Transformers:

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

pipe = pipeline("text-generation", model="dyyyyyyyy/FAPO-GenRM-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dyyyyyyyy/FAPO-GenRM-4B")
model = AutoModelForCausalLM.from_pretrained("dyyyyyyyy/FAPO-GenRM-4B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dyyyyyyyy/FAPO-GenRM-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dyyyyyyyy/FAPO-GenRM-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": "dyyyyyyyy/FAPO-GenRM-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dyyyyyyyy/FAPO-GenRM-4B

SGLang

How to use dyyyyyyyy/FAPO-GenRM-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 "dyyyyyyyy/FAPO-GenRM-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": "dyyyyyyyy/FAPO-GenRM-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 "dyyyyyyyy/FAPO-GenRM-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": "dyyyyyyyy/FAPO-GenRM-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dyyyyyyyy/FAPO-GenRM-4B with Docker Model Runner:
```
docker model run hf.co/dyyyyyyyy/FAPO-GenRM-4B
```

Improve model card: Add pipeline tag, library name, paper link, and abstract

by nielsr HF Staff - opened Oct 31, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

nielsr

Oct 31, 2025

This PR enhances the model card by:

Adding pipeline_tag: text-generation to accurately categorize the model's primary function on the Hugging Face Hub.
Specifying library_name: transformers as the model is compatible with the 🤗 Transformers library (evidenced by config.json and tokenizer_config.json), which enables the automated "how to use" widget.
Including a direct link to the research paper: FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning.
Adding the paper's abstract to provide immediate context and an overview of the model's background and purpose.

Please note: A sample usage code snippet has not been added, as the provided GitHub README did not contain an explicit inference snippet for this specific model, in adherence to the task's instructions.

Improve model card: Add pipeline tag, library name, paper link, and abstract6ac877a3

dyyyyyyyy changed pull request status to merged Oct 31, 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