luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskSentence-1e-4-HessianMaskSentence-0.01-v2_6736
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-GRPO-NoBaseline-FisherMaskSentence-1e-4-HessianMaskSentence-0.01-v2_6736 is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-Math-7B. This model specializes in mathematical reasoning, having been trained on the DigitalLearningGmbH/MATH-lighteval dataset using the GRPO method. It is designed to enhance performance in complex mathematical tasks and problem-solving, leveraging a 32768 token context length.
Loading preview...
Model Overview
This model, luckeciano/Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskSentence-1e-4-HessianMaskSentence-0.01-v2_6736, is a 7.6 billion parameter language model derived from the Qwen2.5-Math-7B architecture. It has been specifically fine-tuned to excel in mathematical reasoning tasks.
Key Capabilities & Training
- Mathematical Reasoning: The model's primary focus is on advanced mathematical problem-solving, achieved through fine-tuning on the DigitalLearningGmbH/MATH-lighteval dataset.
- GRPO Training Method: It utilizes the GRPO (Generalized Reinforcement Learning with Policy Optimization) method, as introduced in the paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" (arXiv:2402.03300), to optimize its performance.
- Framework: Training was conducted using the TRL library (Transformer Reinforcement Learning).
- Context Length: The model supports a substantial context length of 32768 tokens, allowing for processing longer and more complex mathematical problems.
Use Cases
- Mathematical Problem Solving: Ideal for applications requiring accurate and robust mathematical reasoning.
- Research in Mathematical AI: Suitable for researchers exploring advanced techniques in AI for mathematics.
- Educational Tools: Can be integrated into tools designed to assist with or generate mathematical solutions.