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
```

Bingguang commited on May 27, 2025

Commit

c0a4619

verified ·

1 Parent(s): f879aa4

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ base_model:
 # FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement
 <p align="center">
-         &nbsp&nbsp📊 <a href="https://huggingface.co/Bingguang/FunReason">Dataset(Coming)</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/Bingguang/FunReason">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://huggingface.co/Bingguang/FunReason">Paper(Coming)</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://huggingface.co/Bingguang/FunReason">Blog(Coming)</a> &nbsp&nbsp ｜ &nbsp&nbsp📖 <a href="https://github.com/BingguangHao/FunReason">Github</a>
 </p>
 > [!IMPORTANT]
@@ -39,6 +39,8 @@ The integration of large language models (LLMs) with function calling has emerge
 ```md
 @article{FunReason,
   title={FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement},
-  author={Bingguang Hao, Maolin Wang, Zengzhuang Xu, Cunyin Peng, Yicheng Chen, Xiangyu Zhao, Jinjie Gu, Chenyi Zhuang}
 }
 ```

 # FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement
 <p align="center">
+         &nbsp&nbsp📊 <a href="https://huggingface.co/Bingguang/FunReason">Dataset(Coming)</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/Bingguang/FunReason">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/pdf/2505.20192">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://huggingface.co/Bingguang/FunReason">Blog(Coming)</a> &nbsp&nbsp ｜ &nbsp&nbsp📖 <a href="https://github.com/BingguangHao/FunReason">Github</a>
 </p>
 > [!IMPORTANT]
 ```md
 @article{FunReason,
   title={FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement},
+  author={Bingguang Hao, Maolin Wang, Zengzhuang Xu, Cunyin Peng, Yicheng Chen, Xiangyu Zhao, Jinjie Gu, Chenyi Zhuang},
+  journal={arXiv preprint arXiv:2505.20192},
+  year={2025}
 }
 ```