Uploaded finetuned model
- Developed by: CompassioninMachineLearning
- License: apache-2.0
- Finetuned from model : CompassioninMachineLearning/Basellama_plus3kv3_plus20kfinetune2epochs
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 73
Model tree for CompassioninMachineLearning/Basellama_plus3kv3_plus20kfinetune2epochs_plus5kGRPO
Base model
meta-llama/Llama-3.1-8B
Finetuned
unsloth/Llama-3.1-8B