[Question] OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /home/LLaVA/llava-v1.5-13b-lora.

haotian-liu / LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

https://llava.hliu.cc

Apache License 2.0

19.59k stars 2.16k forks source link

[Question] OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /home/LLaVA/llava-v1.5-13b-lora. #900

Open gapjialin opened 10 months ago

gapjialin commented 10 months ago

Question

When I use scripts/v1 5/finetune Lora.sh makes minor adjustments and displays: OSError: Error no file named pytorch Model. bin, tf Model. h5, model. ckpt. index or flex_ Model. msgpack found in directory/home/LaVA/lava v1.5-13b lora

Road2Redemption commented 10 months ago

I have met the same problem, I want to do multi-stage training, namely let the parameter --model_name_or_path a checkpoint like this. I don't know whether my method is correct.

yuezhao238 commented 9 months ago

i met the same problem when using cli script. Solved by adding --model-base

Leo-Lsc commented 1 month ago

i met the same problem when using cli script. Solved by adding --model-base我在使用 cli 脚本时遇到了同样的问题。通过添加 --model-base 解决

How do you solve it? I don't quite understand what is "通过添加 --model-base 解决"?