luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.01-v2_1228
The luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.01-v2_1228 is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-Math-7B. It was trained using the GRPO method on the DigitalLearningGmbH/MATH-lighteval dataset, specializing it in mathematical reasoning tasks. This model is designed to enhance mathematical problem-solving capabilities in open language models, building upon the advancements in the DeepSeekMath paper.
Loading preview...
Overview
This model, luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.01-v2_1228, is a specialized 7.6 billion parameter language model. It is a fine-tuned version of the Qwen/Qwen2.5-Math-7B base model, specifically optimized for mathematical reasoning. The training utilized the TRL library and incorporated the GRPO (Gradient Regularized Policy Optimization) method.
Key Capabilities
- Enhanced Mathematical Reasoning: Fine-tuned on the DigitalLearningGmbH/MATH-lighteval dataset, this model is designed to improve performance on complex mathematical problems.
- GRPO Training Method: Leverages the GRPO method, as introduced in the "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" paper, to achieve better stability and performance in mathematical contexts.
Good for
- Mathematical Problem Solving: Ideal for applications requiring robust mathematical reasoning and accurate numerical computations.
- Research in Mathematical LLMs: Useful for researchers exploring advanced training techniques like GRPO for specialized language models.
- Educational Tools: Can be integrated into tools that assist with or generate solutions for mathematical challenges.