cjiao/goldengoose-p3_goose_lowdiv_n128_random-25grp

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026Architecture:Transformer Featherless Exclusive Cold

The cjiao/goldengoose-p3_goose_lowdiv_n128_random-25grp model is a 1.5 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. Developed by cjiao, this model was trained using the GRPO method, which is designed to enhance mathematical reasoning capabilities. It is optimized for tasks requiring improved reasoning, particularly in mathematical contexts, leveraging techniques from DeepSeekMath.

Loading preview...

Model Overview

The cjiao/goldengoose-p3_goose_lowdiv_n128_random-25grp is a 1.5 billion parameter language model, fine-tuned from the Qwen/Qwen2.5-1.5B-Instruct base model. This model was developed by cjiao and specifically trained using the GRPO (Gradient-based Reward Policy Optimization) method, as introduced in the research paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models".

Key Characteristics

  • Base Model: Qwen2.5-1.5B-Instruct, a robust instruction-tuned causal language model.
  • Training Method: Utilizes GRPO, a technique aimed at improving mathematical reasoning and problem-solving abilities.
  • Framework: Fine-tuned using the TRL library (version 0.19.1) from Hugging Face.
  • Context Length: Supports a context window of 32768 tokens.

Intended Use Cases

This model is particularly well-suited for applications that require enhanced reasoning, especially in mathematical domains. Its training with the GRPO method suggests improved performance on tasks where logical deduction and numerical understanding are critical. Developers can integrate it using the Hugging Face transformers library for text generation tasks, as demonstrated in the quick start example.