jianzhnie/LLamaTuner

RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

Closed this issue · 4 comments

which model do you run? the base_model and adapters

which model do you run? the base_model and adapters

the base model: vicuna-13b
adapters: trained with finetune.sh(dataset_format: alpaca-cleaned)

python generate_server.py \
    --model_name_or_path decapoda-research/llama-7b-hf \
    --lora_model_name_or_path  tloen/alpaca-lora-7b \
    --load_8bit

run add test this scripts and find the bugs

python generate_server.py \
    --model_name_or_path decapoda-research/llama-7b-hf \
    --lora_model_name_or_path  tloen/alpaca-lora-7b \
    --load_8bit

run add test this scripts and find the bugs

I ran this script with the same error as before