Instructions to use ByteDance-Seed/BFS-Prover-V1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance-Seed/BFS-Prover-V1-7B with Transformers:

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

pipe = pipeline("text-generation", model="ByteDance-Seed/BFS-Prover-V1-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ByteDance-Seed/BFS-Prover-V1-7B")
model = AutoModelForCausalLM.from_pretrained("ByteDance-Seed/BFS-Prover-V1-7B")
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

vLLM

How to use ByteDance-Seed/BFS-Prover-V1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance-Seed/BFS-Prover-V1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/BFS-Prover-V1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ByteDance-Seed/BFS-Prover-V1-7B

SGLang

How to use ByteDance-Seed/BFS-Prover-V1-7B 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 "ByteDance-Seed/BFS-Prover-V1-7B" \
    --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": "ByteDance-Seed/BFS-Prover-V1-7B",
		"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 "ByteDance-Seed/BFS-Prover-V1-7B" \
        --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": "ByteDance-Seed/BFS-Prover-V1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ByteDance-Seed/BFS-Prover-V1-7B with Docker Model Runner:
```
docker model run hf.co/ByteDance-Seed/BFS-Prover-V1-7B
```

Add GitHub repository link to model card

by nielsr HF Staff - opened Oct 10, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-5

nielsr

Oct 10, 2025

This PR improves the model card by explicitly adding a link to the GitHub repository of the BFS-Prover project (https://github.com/bytedance-research/BFS-Prover). This was inferred from the abstract stating the model is open-sourced and the common naming convention of the model's Hugging Face ID. The current card only links to a related library, so this addition will make the project's main codebase more accessible to users. A GitHub badge is also added to the header, and emojis for the paper and code links are updated for better visual clarity.

Add GitHub repository link to model carde2a575c0

RanXinByteDance

ByteDance Seed org Oct 14, 2025

Please correct the github repo in PR to https://github.com/ByteDance-Seed/BFS-Prover-V2

Update README.mdfbe9a865

nielsr

Oct 14, 2025

Done

RanXinByteDance changed pull request status to merged Oct 14, 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