dszpr

About the lables in the VQA task using OPT models

2

Hi！ I noticed that in forward function in blip2_opt.py, only the questions in the VQA dateset are used. Both the text_input and the target lables are derived from the opt_tokens...

ERROR when eval internvl_chat_llava model

2

Hi! Thanks for the great work. I am working on the multi-model Vision-QA tasks using internvl_chat_llava model. When evaluate the internvl_chat_llava model, an error occurs: ``` Traceback (most recent call...

RuntimeError: Error(s) in loading state_dict for ResNet

7

Hi! Much appreciated for the excellent work! When doing instruction finetuning, I encountered an error: ------------------------ WARNING:root:Pytorch pre-release version 1.14.0a0+410ce96 - assuming intent to test it /usr/local/lib/python3.8/dist-packages/diffusers/models/cross_attention.py:30: FutureWarning: Importing from...

How to use the mm-cot frame as a utility library through local LLM?

1

Hi! Much appreciated for the excellent work! I am working on vision-QA task using BLIP2, which consists of three modules: ViT that extracting vision feature QFORMER that narrow the gap...