Instructions to use GTAlign/Qwen2.5-3B-Math-140step with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GTAlign/Qwen2.5-3B-Math-140step with Transformers:

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

pipe = pipeline("text-generation", model="GTAlign/Qwen2.5-3B-Math-140step")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GTAlign/Qwen2.5-3B-Math-140step")
model = AutoModelForCausalLM.from_pretrained("GTAlign/Qwen2.5-3B-Math-140step")
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 GTAlign/Qwen2.5-3B-Math-140step with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GTAlign/Qwen2.5-3B-Math-140step"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GTAlign/Qwen2.5-3B-Math-140step",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GTAlign/Qwen2.5-3B-Math-140step

SGLang

How to use GTAlign/Qwen2.5-3B-Math-140step 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 "GTAlign/Qwen2.5-3B-Math-140step" \
    --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": "GTAlign/Qwen2.5-3B-Math-140step",
		"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 "GTAlign/Qwen2.5-3B-Math-140step" \
        --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": "GTAlign/Qwen2.5-3B-Math-140step",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GTAlign/Qwen2.5-3B-Math-140step with Docker Model Runner:
```
docker model run hf.co/GTAlign/Qwen2.5-3B-Math-140step
```

Improve model card: Add description, paper and code links

by nielsr HF Staff - opened Oct 24, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+13

-5

Files changed (1) hide show

README.md +13 -5

README.md CHANGED Viewed

@@ -1,11 +1,19 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-3B-Instruct
-pipeline_tag: text-generation
 library_name: transformers
 tags:
 - agent
----

 ---
 base_model:
 - Qwen/Qwen2.5-3B-Instruct
+language:
+- en
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - agent
+---
+# GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare
+GTAlign is an alignment framework that integrates game-theoretic decision-making into both reasoning and training of LLM assistants, encouraging them to make decisions that are not only accurate but also rational, cooperative, and transparent.
+- 📄 Paper: [GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare](https://huggingface.co/papers/2510.08872)
+- 💻 Code: [https://github.com/ulab-uiuc/GTAlign](https://github.com/ulab-uiuc/GTAlign)
+- 🌐 Project Page: [https://huggingface.co/GTAlign](https://huggingface.co/GTAlign)