Modify infos in README

README.md

@@ -71,9 +71,8 @@ pip install mmengine==0.10.3
 cd /your_code_path/llama3_pytorch
 pip install modelscope
 python download_models.py
-mv ./LLM-Research/* ./
 ```
-2. 修改[llama3_8b_instruct_qlora_alpaca_e3_M.py](./llama3_8b_instruct_qlora_alpaca_e3_M.py)代码中的`pretrained_model_name_or_path`、`data_path`为本地对应数据地址；
+2. 修改[llama3_8b_instruct_qlora_alpaca_e3_M.py](./llama3_8b_instruct_qlora_alpaca_e3_M.py)代码中的`pretrained_model_name_or_path`、`data_path`为本地模型、数据地址；
 3. 根据硬件环境和自身训练需求来调整`max_length`、`batch_size`、`accumulative_counts`、`max_epochs`、`lr`、`save_steps`、`evaluation_freq`、model.lora中的`r`、`lora_alpha`参数，默认参数支持4*32G；
 4. ${DCU_NUM}参数修改为要使用的DCU卡数量，不同数据集需要修改llama3_8b_instruct_qlora_alpaca_e3_M.py中`SYSTEM`、`evaluation_inputs`、`dataset_map_fn`、`train_dataloader.sampler`、`train_cfg`参数设置，详情请参考代码注释项，当前默认alpaca数据集。
 5. 执行

llama3_8b_instruct_qlora_alpaca_e3_M.py

@@ -24,7 +24,7 @@ from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE
 #                          PART 1  Settings                           #
 #######################################################################
 # Model
-pretrained_model_name_or_path = '/home/llama3/Meta-Llama-3-8B-Instruct'
+pretrained_model_name_or_path = '/your_model_save_path/LLM-Research/Meta-Llama-3-8B-Instruct'
 use_varlen_attn = False  # new
 
 # Data