InfiniAILab/OpenR1-Qwen-7B-Math-Instruct

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 7, 2025Architecture:Transformer Featherless Exclusive Cold

The InfiniAILab/OpenR1-Qwen-7B-Math-Instruct is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-Math-7B-Instruct. Developed by InfiniAILab, this model specializes in mathematical reasoning and problem-solving. It was trained on the OpenR1-Math-220k dataset, making it particularly adept at handling complex mathematical tasks. With a context length of 32768 tokens, it is designed for applications requiring robust mathematical instruction following.

Loading preview...

Model Overview

InfiniAILab/OpenR1-Qwen-7B-Math-Instruct is a 7.6 billion parameter language model, fine-tuned from the Qwen/Qwen2.5-Math-7B-Instruct base model. Its primary focus is on enhancing mathematical reasoning and instruction following capabilities. The model was specifically trained using the open-r1/OpenR1-Math-220k dataset, a specialized collection for mathematical problems.

Key Capabilities

  • Specialized Mathematical Reasoning: Optimized for understanding and solving mathematical problems, building upon the Qwen2.5-Math-7B-Instruct foundation.
  • Instruction Following: Designed to accurately follow mathematical instructions and generate relevant responses.
  • Extended Context: Supports a context length of 32768 tokens, allowing for processing longer and more complex mathematical queries.

Training Details

The model was fine-tuned using the TRL library with an SFT (Supervised Fine-Tuning) approach. This training methodology leverages the OpenR1-Math-220k dataset to imbue the model with strong mathematical proficiency. The training process can be visualized via Weights & Biases, as linked in the original model card.