Update README.md

README.md

@@ -12,6 +12,8 @@ The total size of the model is around 2.2B, which is suitable for embedded appli
 ```
 git clone https://github.com/InternLM/xtuner
 pip install -e ./xtuner[deepspeed]
+https://huggingface.co/StarCycle/llava-clip-internlm2-1_8b-pretrain-v1
+cd ./llava-clip-internlm2-1_8b-pretrain-v1
 ```
 
 ## Common Errors
@@ -80,8 +82,15 @@ Please check the final release version
 ## Cheers! Now train your own model!
 1. Alignment module pretraining
 ```
-NPROC_PER_NODE=8 xtuner train ./llava_internlm2_chat_7b_dinov2_e1_gpu8_pretrain.py --deepspeed deepspeed_zero2
+# single GPU
+xtuner train ./llava_internlm2_chat_1_8b_clip_vit_large_p14_336_e1_gpu1_pretrain.py --deepspeed deepspeed_zero2
+
+# multiple GPU
+NPROC_PER_NODE=8 xtuner train ./llava_internlm2_chat_1_8b_clip_vit_large_p14_336_e1_gpu1_pretrain.py --deepspeed deepspeed_zero2
 ```
+
+#### Remember to change the batch size and gradient accumulation parameters. So your batch_size*gradient_accumulation is roughly equal to mine to reproduce the result.
+
 The checkpoint and tensorboard logs are saved by default in ./work_dirs/. I only train it for 1 epoch to be same as the original LLaVA paper. Some researches also report that training for multiple epochs will make the model overfit the training dataset and perform worse in other domains.
 
 This is my loss curve for llava-clip-internlm2-1_8b-pretrain-v1: