metadata
base_model: weblab-GENIAC/Tanuki-8B-dpo-v1.0
license: cc-by-nc-nd-4.0
language:
- ja
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
datasets:
- watashihakobashi/ogiri
Uploaded model
- Developed by: OsakanaTeishoku
- License: apache-2.0
- Finetuned from model : weblab-GENIAC/Tanuki-8B-dpo-v1.0
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
