Kazuki1450/Qwen2.5-1.5B-Instruct_csum_6_10_tok_actions_1p0_0p0_1p0_grpo_42_rule

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Jan 16, 2026Architecture:Transformer Cold

Kazuki1450/Qwen2.5-1.5B-Instruct_csum_6_10_tok_actions_1p0_0p0_1p0_grpo_42_rule is a 1.5 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. This model was trained using the GRPO method, which is designed to enhance mathematical reasoning capabilities, as introduced in the DeepSeekMath paper. With a substantial context length of 131,072 tokens, it is optimized for tasks requiring deep understanding and generation of text, particularly in areas benefiting from improved reasoning.

Loading preview...

Model Overview

This model, Kazuki1450/Qwen2.5-1.5B-Instruct_csum_6_10_tok_actions_1p0_0p0_1p0_grpo_42_rule, is a 1.5 billion parameter instruction-tuned variant of the Qwen2.5-1.5B-Instruct base model. It has been specifically fine-tuned using the TRL library and incorporates the GRPO (Gradient-based Reward Policy Optimization) training method.

Key Differentiator: GRPO Training

The primary distinction of this model lies in its application of the GRPO method, detailed in the paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models". This training approach is designed to significantly improve the model's mathematical reasoning abilities and overall logical coherence in responses.

Capabilities

  • Enhanced Reasoning: Benefits from GRPO training, suggesting improved performance on tasks requiring logical deduction and problem-solving.
  • Instruction Following: As an instruction-tuned model, it is designed to accurately follow user prompts and generate relevant responses.
  • Large Context Window: Features a context length of 131,072 tokens, allowing it to process and generate longer, more complex texts while maintaining coherence.

When to Use This Model

  • Mathematical and Logical Tasks: Ideal for applications where robust reasoning and accurate problem-solving are critical.
  • Complex Instruction Following: Suitable for scenarios requiring the model to understand and execute intricate multi-step instructions.
  • Long-form Content Generation: Its large context window makes it well-suited for generating or analyzing extensive documents, articles, or conversations.