luckeciano/Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-5e-4-v3_7785
TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 15, 2025Architecture:Transformer Featherless Exclusive Cold
This model is a 7.6 billion parameter Qwen 2.5-based language model, fine-tuned by luckeciano. It specializes in mathematical reasoning, having been trained using the GRPO method on the MATH-lighteval dataset. This fine-tuning enhances its capabilities for complex mathematical problem-solving. It is suitable for applications requiring advanced mathematical understanding and computation.
Loading preview...
Model Overview
This model, luckeciano/Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-5e-4-v3_7785, is a fine-tuned version of the Qwen 2.5-Math-7B base model. It has been specifically optimized for mathematical reasoning tasks.
Key Capabilities
- Enhanced Mathematical Reasoning: The model was trained using the GRPO (Gradient Regularized Policy Optimization) method, as introduced in the DeepSeekMath paper, which is designed to push the limits of mathematical reasoning in open language models.
- Specialized Dataset Training: Fine-tuned on the DigitalLearningGmbH/MATH-lighteval dataset, ensuring a strong focus on mathematical problem-solving.
- TRL Framework: Training was conducted using the TRL (Transformer Reinforcement Learning) framework, indicating a reinforcement learning approach to fine-tuning.
Good For
- Applications requiring robust mathematical problem-solving abilities.
- Research and development in advanced mathematical AI.
- Tasks that benefit from models specifically optimized for numerical and logical reasoning.