GTAlign
/

Qwen2.5-3B-Full-160step

Text Generation

text-generation-inference

Model card Files Files and versions

https://huggingface.co/papers/2510.08872

Downloads last month: 6

Safetensors

Model size

3B params

Tensor type

BF16

·

Model tree for GTAlign/Qwen2.5-3B-Full-160step

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(906)

this model

Paper for GTAlign/Qwen2.5-3B-Full-160step

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

Paper • 2510.08872 • Published Oct 10, 2025 • 3