File size: 730 Bytes
fa6856c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
TOT_CUDA="0,1" #Upgrade bitsandbytes to the latest version to enable balanced loading of multiple GPUs, for example: pip install bitsandbytes==0.39.0
BASE_MODEL="../chinese-llama-2-13b" #"decapoda-research/llama-13b-hf"
LORA_PATH="../llama2-13b-57" #"./lora-Vicuna/checkpoint-final"
USE_LOCAL=1 # 1: use local model, 0: use huggingface model
TYPE_WRITER=1 # whether output streamly
if [[ USE_LOCAL -eq 1 ]]
then
cp sample/instruct/adapter_config.json $LORA_PATH
fi

#Upgrade bitsandbytes to the latest version to enable balanced loading of multiple GPUs
CUDA_VISIBLE_DEVICES=${TOT_CUDA} python generate.py \
    --model_path $BASE_MODEL \
    --lora_path $LORA_PATH \
    --use_local $USE_LOCAL \
    --use_typewriter $TYPE_WRITER