metadata
base_model: Creekside/Qwen-2.5-GRPO-1e
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- grpo
license: apache-2.0
language:
- en
datasets:
- openai/gsm8k
- Creekside/GRPO-Lambda-ParsedForUnsloth
Uploaded model
- Developed by: Creekside
- License: apache-2.0
- Finetuned from model : Creekside/Qwen-2.5-GRPO-1e
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.