Zi-Yuan Hu
Zi-Yuan Hu
> I add the following scripts: > > `os.environ["WANDB_PROJECT"]="YOUR_PROJECT_NAME"` in `LLaVA/llava/train/train_mem.py` > > and `--run_name 'YOUR_RUN_NAME' \` to training arguments same with you
@haotian-liu I think the answer is the value of ['all']['cand/anchor']?
> @haotian-liu I have the same question, can you share which result to present? > > > > @OliverLeeXZ and @g-h-chen were you able to find the correct strategy? >...
@ChunyuanLI Thanks for your quick reply. My main concern is not performance, but curiosity about the contribution of instruction tuning for the performance improvement. By the way, one of the...
@haotian-liu Hi, batch evaluation is really important for VQAv2, which takes too much time. I think issue #675 has provided a solution to batch image captioning without evaluation. If would...
What about "evaluate_functional_correctness data/example_samples.jsonl --problem_file=data/example_problem.jsonl"?
Great sharing!
By the way, I noticed that the README provides a Training part. However, it lacks a lot of details:)
@anas-awadalla Thanks for your quick reply. Take your running command as an example, how can I change the following command to only train on LAION-2B based on a pre-trained OPT-1.3B?...
@Soonhwan-Kwon @anas-awadalla Thanks for your great reply!! I will try it later:)