Qwen2.5-3B-GRPO
Collection
Trained with unsloth on just 250 steps (resource constraints) on GSM8K to add reasoning abilities to Qwen2.5-3B (smaller model because resources)
•
3 items
•
Updated
Uploaded model
- Developed by: sarthak247
- License: apache-2.0
- Finetuned from model : unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.