File size: 525 Bytes
23c9ef8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
# Adopted from https://github.com/lm-sys/FastChat. Below is the original copyright:
# Adopted from tatsu-lab@stanford_alpaca. Below is the original copyright:
# Make it more memory efficient by monkey patching the LLaMA model with xformers attention.

# Need to call this before importing transformers.
from libra.train.llama_xformers_attn_monkey_patch import (
    replace_llama_attn_with_xformers_attn,
)

replace_llama_attn_with_xformers_attn()

from libra.train.train import train

if __name__ == "__main__":
    train()