alpaca-lora
alpaca-lora copied to clipboard
seems index error
use default command line
Please provide more context. finetune or inference? precise command launched? gpus type and count? clean py env or some other one from alpaca serve? Also see the debug hint the message gives you.
Please provide more context. finetune or inference? precise command launched? gpus type and count? clean py env or some other one from alpaca serve? Also see the debug hint the message gives you.
fixed. the models download from huggingface is wrong. when i used original weights and use transformers.models.llama.convert_llama_weights_to_hf, its worked.