bytedance / lynx-llm

paper: https://arxiv.org/abs/2307.02469 page: https://lynx-llm.github.io/

bytedance/lynx-llm Issues

paper says adapters are added every M blocks(M=1) but checkpoints seems to add every two
Closed a year ago2
How is the dimension of pos_embed handled when the image size is increased to 420x420 in the pre-training phase?
Updated a year ago2
Pretrained models
Updated a year ago1
Could you please provide the pictures and videos used by benchmark for convenience?
Updated a year ago1
Prompt during training and inference
Updated a year ago3
when the training script will be released?
Updated a year ago7