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

Libraries

How to use Bingguang/FunReason-MT with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bingguang/FunReason-MT"
# 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-MT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Bingguang/FunReason-MT

SGLang

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

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

Bingguang commited on Nov 3, 2025

Commit

8b82b4d

verified ·

1 Parent(s): f6773ea

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ library_name: transformers
 The **FunReason-MT-4B** model is a high-performance **Large Language Model (LLM)** fine-tuned for complex, multi-turn **Function Calling (FC)** and agentic tool-use tasks. Built upon the **Qwen3-4B-Instruct-2507** base model , it has been trained using the novel **FunReason-MT data synthesis framework**.
-FunReason-MT-4B achieves state-of-the-art results on the **Berkeley Function-Calling Leaderboard (BFCLv3)** Multi-Turn and Agentic Evaluation benchmarks. This performance demonstrates that high-quality, synthesized data can effectively overcome the complexity barrier in multi-turn FC data generation.
   - **Base Model:** Qwen3-4B-Instruct-2507
   - **Size:** 4 Billion parameters

 The **FunReason-MT-4B** model is a high-performance **Large Language Model (LLM)** fine-tuned for complex, multi-turn **Function Calling (FC)** and agentic tool-use tasks. Built upon the **Qwen3-4B-Instruct-2507** base model , it has been trained using the novel **FunReason-MT data synthesis framework**.
+FunReason-MT-4B achieves ssuperior results on the **Berkeley Function-Calling Leaderboard (BFCLv3)** Multi-Turn and Agentic Evaluation benchmarks. This performance demonstrates that high-quality, synthesized data can effectively overcome the complexity barrier in multi-turn FC data generation.
   - **Base Model:** Qwen3-4B-Instruct-2507
   - **Size:** 4 Billion parameters