ZHANG Bowen

Grid size (4) < 2 * SM count (164) will likely result in GPU under utilization due to low occupancy.

1

Thank you for your great work! This is very useful and works like a charm for my use case. Here is one quick question: ``` /net/papilio/storage2/bowenz/anaconda3/envs/zbw/lib/python3.9/site-packages/numba/cuda/compiler.py:726: NumbaPerformanceWarning: Grid size (4)...

fairseq-hydra-train with multi-nodes distributed training

14

Hi, is there any instruction on multiple nodes multiple GPUs distributed training with hydra train? https://fairseq.readthedocs.io/en/latest/getting_started.html#distributed-training The fairseq documentation seems to be out-of-date, where hydra does not expect the `local_rank`...

Difference result from the paper when finetuning ASR

1

Hi, sorry to disturb you again. I used the provided pre-trained model `base_lrs3_iter5.pt`, the `30h_data` data split, the `base_lrs3_30h.yaml` config to finetune for ASR, all following the README, and finally...

RuntimeError: Python version >= 3.9 required

8

The specified python version as suggested is 3.8, but after executing the following ``` conda create -n lmdrive python=3.8 conda activate lmdrive cd vision_encoder python setup.py develop ``` I got...

text to image view

1

First thank you for the great work! I would like to know whether this tool can also do text-to-image attention views for large vision-language models such as MiniGPT-4, LLaVA, InstructBLIP,...

Hi, thank you for the interesting work. I have a question about the proposed method. > a 2D convolution with an output channel of 1 along with a Sigmoid function...

Thank you for sharing this interesting work. As I looked at the prompts used in the work, I noticed almost in all cases the negations simply replace the word 'correct'...