Shubham Garg

Not able to read pixels from offscreen render target in filament web

5

I am trying to render a sample triangle to a offscreen render target and trying to use readPixels API to get the pixels buffer on the web. First thing i...

Fix for broken requirements.txt

Missing Multimodel Pretraining step

1

Hi, For the paper https://arxiv.org/pdf/2310.01218.pdf , the following is mentioned in pretraining section : ``` For efficiency, we first train SEED-LLaMA using LoRA [32] tuning and together optimize the parameters...

train_scripts/causal_qformer.sh not working

1

Hi, While trying to run step 3 of Training SEED Tokenization, I am observing following error: ``` Traceback (most recent call last): File "/SEED/SEED_Tokenizer/train.py", line 16, in import lavis.tasks as...

Step 3 of Multimodal LLM Pre-training was failing. Fix for same is in this PR

Training code for SEED-LLaMA

1

Hi, I am wondering if at any point the training code for SEED-LLaMA will be made available?