cjiao/goldengoose-divsweepv2_lowdiv_goose_n128_random_n25

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 21, 2026Architecture:Transformer Featherless Exclusive Cold

The cjiao/goldengoose-divsweepv2_lowdiv_goose_n128_random_n25 model is a 1.5 billion parameter language model fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. Developed by cjiao, it was trained using the GRPO method, which is designed to enhance mathematical reasoning capabilities. This model is optimized for tasks requiring improved logical and mathematical problem-solving, building upon its Qwen2.5 base.

Loading preview...

Model Overview

The cjiao/goldengoose-divsweepv2_lowdiv_goose_n128_random_n25 is a 1.5 billion parameter language model that has been fine-tuned from the Qwen/Qwen2.5-1.5B-Instruct base model. It was developed by cjiao and trained using the TRL framework.

Key Training Details

A significant aspect of this model's development is its training procedure, which utilized GRPO (Gradient-based Reward Policy Optimization). GRPO is a method introduced in the research paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models." This suggests an optimization focus on enhancing the model's capabilities in areas related to mathematical reasoning and problem-solving.

Intended Use Cases

Given its fine-tuning with the GRPO method, this model is likely to perform well in applications that require:

  • Mathematical reasoning: Tasks involving numerical problems, logical deductions, or mathematical explanations.
  • Instruction following: Building upon its Qwen2.5-Instruct base, it should maintain strong instruction-following capabilities.

Developers can integrate this model using the Hugging Face transformers library, as demonstrated in the quick start example provided in its model card.