zhuoshi_llm_factory/examples/lora_single_gpu/predict.sh

20 lines
637 B
Bash

#!/bin/bash
CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--stage sft \
--do_predict \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft,../../saves/LLaMA2-7B/lora/dpo \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../data \
--template default \
--finetuning_type lora \
--output_dir ../../saves/LLaMA2-7B/lora/predict \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_eval_batch_size 1 \
--max_samples 20 \
--predict_with_generate