jz666
simpo-train-small-wrong
Based on google/gemma-2-9b-it
Tags
- safetensors
- gemma2
- alignment-handbook
- trl
- simpo
- generated_from_trainer
- conversational
- dataset:jz666/gemma2-ultrafeedback-ppl-split
- base_model:google/gemma-2-9b-it
- base_model:finetune:google/gemma-2-9b-it
- license:gemma
- text-generation-inference
- Author
- jz666
- Task
- text-generation
- Library
- transformers
- Architecture
- gemma2
- License
- gemma
- Base model
- google/gemma-2-9b-it
- Downloads
- 13
- Likes
- 0
