luckeciano/Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-v2_2665

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 14, 2025Architecture:Transformer Featherless Exclusive Cold

The luckeciano/Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-v2_2665 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 in mathematical reasoning tasks. This model leverages a 32768 token context length and is optimized for enhanced performance in complex mathematical problem-solving.

Loading preview...

Model Overview

This model, luckeciano/Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-v2_2665, is a fine-tuned variant of the Qwen/Qwen2.5-Math-7B base model, featuring 7.6 billion parameters and a 32768 token context length. Its development focused on improving mathematical reasoning capabilities.

Key Training Details

  • Base Model: Qwen/Qwen2.5-Math-7B.
  • Fine-tuning Method: Utilizes GRPO (Generalized Reinforcement Learning with Policy Optimization), a technique introduced in the "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" paper.
  • Dataset: Fine-tuned on the DigitalLearningGmbH/MATH-lighteval dataset, specifically designed for mathematical tasks.
  • Framework: Training was conducted using the TRL (Transformer Reinforcement Learning) library.

Intended Use Cases

This model is particularly well-suited for applications requiring advanced mathematical reasoning and problem-solving. Its fine-tuning on a math-specific dataset and the application of the GRPO method suggest improved performance in handling complex mathematical queries and generating accurate solutions.

Finetunes
1 models