Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llm-jp-3-13b-finetune-lr1e-4 – AI Model by HSakakura | AlphaNeural AI
You can deploy this model and start earning money today!
HSakakura
/
llm-jp-3-13b-finetune-lr1e-4
like
0
transformers
safetensors
text-generation-inference
unsloth
llama
trl
en
llm-jp/llm-jp-3-13b
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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。
