llama-factory
llama-factory fine-tuning 4 (mixtral fine-tuning)
introduction fine-tuning command click to view the code CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage sft \ --do_train \ --model_name_or_p ......
llama-factory fine-tuning 3
1 Introduction In this blog, we will use 3 dataset to fine-tuning our model using llama-factory. 2 dataset preparation 2.1 MedQA dataset (address) in ......
llama-factory fine-tuning-3 (conception and technologies explanation)
train method supervised fine-tuning Reward Modeling PPO training DPO training full-parameter partial-parameter LoRA QLoRA command parameter fp16 gradi ......
llama-factory fine-tuning
data preparation for llama-factory fine-tuning, here is the instruction for custom dataset preparation. dataset classification alpaca stanford_alpaca ......