luckeciano/Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-0.01-v2_6981
TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 13, 2025Architecture:Transformer Featherless Exclusive Cold
The luckeciano/Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-0.01-v2_6981 is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-Math-7B. It utilizes the GRPO training method, as introduced in the DeepSeekMath paper, and is specifically optimized for mathematical reasoning tasks. This model is designed to enhance performance on complex mathematical problems, building upon its base model's capabilities.
Loading preview...
Overview
This model, luckeciano/Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-0.01-v2_6981, is a 7.6 billion parameter language model fine-tuned from the Qwen/Qwen2.5-Math-7B base model. It was trained using the TRL library on the DigitalLearningGmbH/MATH-lighteval dataset.
Key Capabilities
- Enhanced Mathematical Reasoning: The model incorporates the GRPO (Generalized Reinforcement Learning with Policy Optimization) training method, which is specifically designed to improve mathematical reasoning capabilities. This method was introduced in the paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" (arXiv:2402.03300).
- Fine-tuned for Math Datasets: Its training on the
MATH-lightevaldataset indicates a specialization in handling and solving mathematical problems.
Good for
- Mathematical Problem Solving: Ideal for applications requiring robust mathematical reasoning and problem-solving.
- Research in RLHF for Math: Useful for researchers exploring advanced reinforcement learning techniques like GRPO in the context of language models for mathematics.