skypilot

1
# This code is based on lmsys-org/fastchat. Below is the original copyright:
2
#
3
#    Copyright 2023 FastChat authors
4
#    Licensed under the Apache License, Version 2.0 (the "License");
5
#    you may not use this file except in compliance with the License.
6
#    You may obtain a copy of the License at
7
#
8
#        http://www.apache.org/licenses/LICENSE-2.0
9
#
10
#    Unless required by applicable law or agreed to in writing, software
11
#    distributed under the License is distributed on an "AS IS" BASIS,
12
#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
#    See the License for the specific language governing permissions and
14
#    limitations under the License.
15

16
# Make it more memory efficient by monkey patching the LLaMA model with FlashAttn.
17

18
# Need to call this before importing transformers.
19
from xformers_patch import replace_llama_attn_with_xformers_attn
20

21
replace_llama_attn_with_xformers_attn()
22

23
from train import train
24

25
if __name__ == "__main__":
26
    train()
27