Uploaded model
- Developed by: HSakakura
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
行った工夫
‐ 基本的には配布されたテンプレートを使っていますが、学習時のパラメータを調整しています。学習率を下げ、Train_lossが最も下がったとStepで打ち切っています。
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for HSakakura/llm-jp-3-13b-finetune-lr1e-4
Base model
llm-jp/llm-jp-3-13b