Instructions to use Bingguang/FunReason with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bingguang/FunReason with Transformers:

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

pipe = pipeline("text-generation", model="Bingguang/FunReason")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bingguang/FunReason")
model = AutoModelForCausalLM.from_pretrained("Bingguang/FunReason")
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 Bingguang/FunReason with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Bingguang/FunReason

SGLang

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

Docker Model Runner
How to use Bingguang/FunReason with Docker Model Runner:
```
docker model run hf.co/Bingguang/FunReason
```

Replace incorrect model card content and update license for AWorld

by nielsr HF Staff - opened Aug 15, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+565

-28

nielsr

Aug 15, 2025

This PR completely revamps the model card for this repository. The previous content incorrectly displayed information for a different project ("FunReason").

This update ensures the model card accurately reflects the "AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving" project.

Key changes include:

Replaced all incorrect model card content with details specific to the AWorld project.
Added the correct paper title and a link to its Hugging Face paper page.
Included the paper's abstract.
Provided a prominent link to the official GitHub repository for AWorld.
Integrated an overview of the AWorld framework, its agentic achievements, quick start guide, architectural principles, applications, and contributing guidelines from the GitHub README.
Updated the license from apache-2.0 to mit, as specified in the AWorld project's GitHub repository.

Please review and merge these changes to improve the clarity and accuracy of this model's documentation.

Replace incorrect model card content and update license for AWorldd7adf7a0

Bingguang changed pull request status to closed Aug 15, 2025

Bingguang

Owner Aug 15, 2025

This project is a part of Aworld but the model is for FC only, and should not be replaced by the model card of Aworld.

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