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

nielsr HF Staff commited on Oct 30, 2025

Commit

532a4ec

verified ·

1 Parent(s): 0e78e55

Improve model card: Add pipeline tag, library name, and explicit links (#1)

Browse files

- Improve model card: Add pipeline tag, library name, and explicit links (44d410621c7ec862db6659c498af9c30c077ea27)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +13 -12

README.md CHANGED Viewed

@@ -1,24 +1,24 @@
 ---
-license: apache-2.0
 base_model:
 - Qwen/Qwen3-4B-Instruct-2507
-task_categories:
-- question-answering
-- text-generation
 language:
 - en
 tags:
 - agent
 - Agentic Learning
 - tool use
 - BFCL
 ---
 # FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling
-[![arXiv](https://img.shields.io/badge/arXiv-2510.24645-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2510.24645) [![Model](https://img.shields.io/badge/Hugging%20Face-Model-yellow?logo=huggingface)](https://huggingface.co/Bingguang/FunReason-MT) [![Dataset](https://img.shields.io/badge/Hugging%20Face-Dataset-yellow?logo=huggingface)](https://huggingface.co/datasets/Bingguang/FunReason-MT)
 ## Model Overview
@@ -30,9 +30,7 @@ FunReason-MT-4B achieves state-of-the-art results on the **Berkeley Function-Cal
   - **Size:** 4 Billion parameters
   - **Key Capability:** Advanced Multi-Turn Function Calling and Agentic Tool-Use
-The full usage of the model is in this [pull request](https://github.com/ShishirPatil/gorilla/pull/1229)
 ## 📊 Evaluation Results
@@ -195,8 +193,11 @@ class FunReasonMTHandler(OSSHandler):
         cleaned_response = model_response
         if "</think>" in model_response:
             parts = model_response.split("</think>")
-            reasoning_content = parts[0].rstrip("\n").split("<think>")[-1].lstrip("\n")
-            cleaned_response = parts[-1].lstrip("\n")
         else:
             cleaned_response = "response outputs too long or no slash think in response."
         print("cleaned_response: ", cleaned_response)

 ---
 base_model:
 - Qwen/Qwen3-4B-Instruct-2507
 language:
 - en
+license: apache-2.0
 tags:
 - agent
 - Agentic Learning
 - tool use
 - BFCL
+task_categories:
+- question-answering
+- text-generation
+pipeline_tag: text-generation
+library_name: transformers
 ---
 # FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling
+[![arXiv](https://img.shields.io/badge/arXiv-2510.24645-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2510.24645) [![Paper](https://img.shields.io/badge/Hugging%20Face-Paper-yellow?logo=huggingface)](https://huggingface.co/papers/2510.24645) [![Model](https://img.shields.io/badge/Hugging%20Face-Model-yellow?logo=huggingface)](https://huggingface.co/Bingguang/FunReason-MT) [![Dataset](https://img.shields.io/badge/Hugging%20Face-Dataset-yellow?logo=huggingface)](https://huggingface.co/datasets/Bingguang/FunReason-MT) [![GitHub](https://img.shields.io/badge/GitHub-Code-181717?logo=github)](https://github.com/inclusionAI/AWorld-RL) [![Project Page](https://img.shields.io/badge/Project-AWorld-green)](https://github.com/inclusionAI/AWorld)
 ## Model Overview
   - **Size:** 4 Billion parameters
   - **Key Capability:** Advanced Multi-Turn Function Calling and Agentic Tool-Use
+The full usage of the model is in the [AWorld-RL GitHub repository](https://github.com/inclusionAI/AWorld-RL).
 ## 📊 Evaluation Results
         cleaned_response = model_response
         if "</think>" in model_response:
             parts = model_response.split("</think>")
+            reasoning_content = parts[0].rstrip("
+").split("<think>")[-1].lstrip("
+")
+            cleaned_response = parts[-1].lstrip("
+")
         else:
             cleaned_response = "response outputs too long or no slash think in response."
         print("cleaned_response: ", cleaned_response)