mlvlab/Flipped-VQA
Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)
PythonMIT
Issues
- 1
- 2
What are the average stats being reported at the end of every epoch in training?
#18 opened by SimMLPhys - 3
- 2
- 2
A question about QAV task in the code
#8 opened by inesriahi - 1
- 1
Checkpoints
#5 opened by iquibalh - 3
From where to download LLaMA-v1 model?
#4 opened by inesriahi - 5
How to use a trained checkpoint to make inference on validation set and resume from checkpoint.
#3 opened by iquibalh - 1
Error when training with TVQA dataset: AttributeError in DataLoader worker process
#2 opened by iquibalh - 2
How to extract features using CLIP VIT-L?
#1 opened by yuanrr - 1
- 0
need llama-13B finetuned checkpoints
#17 opened by Huangbukun - 4
Not getting the reported number.
#11 opened by a6o - 1
about self.gate2
#16 opened by dunknsabsw - 1
meaning of qav loss
#15 opened by dunknsabsw - 3
finetuned using lamma-13B
#13 opened by Huangbukun - 2
Cannot reproduce the result
#12 opened by pseudo-aloha - 3
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 3 (pid: 55662) of binary: /usr/bin/python3
#6 opened by inesriahi