DidulaThavishaPro/exp_13_2_grpo_smooth_error_16bit_vllm
09
Uploaded finetuned model
- Developed by: DidulaThavishaPro
- License: apache-2.0
- Finetuned from model : DidulaThavishaPro/exp110sft16bit_vllm
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
