Edit model card

train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO. train tinyllama1b-instruct for 20k DPO.

Downloads last month
3,235
Safetensors
Model size
1.1B params
Tensor type
FP16
·