Instructions to use TIGER-Lab/Qwen2.5-Math-7B-CFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/Qwen2.5-Math-7B-CFT with Transformers:

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

pipe = pipeline("text-generation", model="TIGER-Lab/Qwen2.5-Math-7B-CFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/Qwen2.5-Math-7B-CFT")
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/Qwen2.5-Math-7B-CFT")
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 TIGER-Lab/Qwen2.5-Math-7B-CFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/Qwen2.5-Math-7B-CFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/Qwen2.5-Math-7B-CFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TIGER-Lab/Qwen2.5-Math-7B-CFT

SGLang

How to use TIGER-Lab/Qwen2.5-Math-7B-CFT 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 "TIGER-Lab/Qwen2.5-Math-7B-CFT" \
    --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": "TIGER-Lab/Qwen2.5-Math-7B-CFT",
		"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 "TIGER-Lab/Qwen2.5-Math-7B-CFT" \
        --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": "TIGER-Lab/Qwen2.5-Math-7B-CFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TIGER-Lab/Qwen2.5-Math-7B-CFT with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/Qwen2.5-Math-7B-CFT
```

nielsr HF Staff commited on Feb 1, 2025

Commit

27aa12b

verified ·

1 Parent(s): 939589d

Add pipeline tag and library name

Browse files

This PR ensures the "how to use" button appears on the top right (with a Transformers code snippet), along with the correct pipeline tag, ensuring people can find the model at https://huggingface.co/models?pipeline_tag=text-generation.

Files changed (1) hide show

README.md +3 -8

README.md CHANGED Viewed

@@ -10,9 +10,10 @@ tags:
 - cft
 - math
 - reasoning
 ---
 # Qwen2.5-Math-7B-CFT
 <div style="display: flex; gap: 4px; align-items: center">
@@ -68,10 +69,4 @@ The model demonstrates that learning to critique is more effective than learning
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/636a35eff8d9af4aea181608/tLLFW6OEASFojDyX1Zh-K.png)*Table 1: Performance comparison of Qwen2.5-Math-7B-CFT vs. other reasoning-specialized models.*
-For more details about the model architecture, methodology, and comprehensive evaluation results, please visit our [project webpage](https://tiger-ai-lab.github.io/CritiqueFineTuning).

 - cft
 - math
 - reasoning
+pipeline_tag: text-generation
+library_name: transformers
 ---
 # Qwen2.5-Math-7B-CFT
 <div style="display: flex; gap: 4px; align-items: center">
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/636a35eff8d9af4aea181608/tLLFW6OEASFojDyX1Zh-K.png)*Table 1: Performance comparison of Qwen2.5-Math-7B-CFT vs. other reasoning-specialized models.*
+For more details about the model architecture, methodology, and comprehensive evaluation results, please visit our [project webpage](https://tiger-ai-lab.github.io/CritiqueFineTuning).