AnKhanh/Qwen3-8B

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 2, 2026Architecture:Transformer Featherless Exclusive Cold

AnKhanh/Qwen3-8B is an 8 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen3-8B. It specializes in mathematical reasoning, having been trained on the OpenR1-Math-220k dataset using the GRPO method. This model is optimized for tasks requiring advanced mathematical problem-solving capabilities, leveraging a 32768 token context length.

Loading preview...

Model Overview

AnKhanh/Qwen3-8B is an 8 billion parameter language model, fine-tuned from the base Qwen3-8B architecture. Its primary distinction lies in its specialized training for mathematical reasoning, achieved through fine-tuning on the open-r1/OpenR1-Math-220k dataset.

Key Capabilities

  • Enhanced Mathematical Reasoning: The model has been specifically trained to improve its performance on complex mathematical problems.
  • GRPO Training Method: Utilizes the GRPO (Gradient-based Reward Policy Optimization) method, as detailed in the paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" (arXiv:2402.03300), to optimize its reasoning abilities.
  • Instruction-tuned: Designed to follow instructions effectively, making it suitable for various prompt-based applications.
  • Large Context Window: Supports a context length of 32768 tokens, allowing for processing and generating longer, more complex mathematical problems and solutions.

Use Cases

This model is particularly well-suited for applications requiring strong mathematical problem-solving, such as:

  • Automated Math Tutors: Generating explanations or solutions for mathematical queries.
  • Research in AI for Mathematics: Exploring advanced mathematical concepts and proofs.
  • Educational Tools: Assisting students with complex math problems.

Training Details

The model was trained using the TRL library (Transformer Reinforcement Learning) and leverages the GRPO method for fine-tuning, focusing on mathematical reasoning tasks.