Update generate.py

generate.py

@@ -13,7 +13,7 @@ from utils import StreamPeftGenerationMixin,StreamLlamaForCausalLM
 from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
 
 parser = argparse.ArgumentParser()
-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
+TOT_CUDA="0" #Upgrade bitsandbytes to the latest version to enable balanced loading of multiple GPUs, for example: pip install bitsandbytes==0.39.0
 BASE_MODEL="ziqingyang/chinese-llama-2-13b"
 LORA_PATH="teachyourselfcoding/llama-2-13b-22sep"
 USE_LOCAL=1 # 1: use local model, 0: use huggingface model