FastLoRAChat

FastLoRAChat copied to clipboard

显存不够问题

1

OutOfMemoryError: CUDA out of memory. Tried to allocate 128.00 MiB (GPU 0; 14.76 GiB total capacity; 13.96 GiB already allocated; 83.75 MiB free; 14.00 GiB reserved in total by PyTorch)...

qcxyzff

fine-turning on vicuna-13b-1.1

4

demo fine-turning json file not find

apachemycat

can fine-tining with fast_lora_chat_v1_sunlight model?

2

can i fine-tine fast_lora_chat_v1_sunlight modle ? https://huggingface.co/icybee/fast_lora_chat_v1_sunlight with your train code python3 finetune_fastchat.py \

apachemycat

请问合并权重时报错应该如何解决

16

zhufq00

这个仓库支持vicnua13b lora训练吗

5

zhufq00