Uploaded model
- Developed by: morizon
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b-instruct2
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 38
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for morizon/llm-jp-3-13b-instruct2-grpo-R1-0225_std_step3000
Base model
llm-jp/llm-jp-3-13b-instruct2