Sam Motamed comments

Results 9 comments of


                                            Sam Motamed

About the training data.

I second this

Please update requirements

"s" in requirements is missing in your script

Errors in Lora : UnboundLocalError: local variable '_tmp' referenced before assignment`

This indeed seems to be a diffusers version mismatch.

Llava-video slowfast mode

same Q here! confused about paper / code discrepancy

Llava-video slowfast mode

Thanks @ZhangYuanhan-AI for the answer on this. So for the 7B model, only 10 frames are given to the model with full tokens (no pooling) per frame?

Llava-video slowfast mode

One last question @ZhangYuanhan-AI; 7B-Qwen model uses 10 frames during training correct? or does it sample varying frames based on fps?

slow fast features not being used in current code

They replied on another thread. They don't use the slow fast pooling on the 7B model, only on the 72B.

No evaluation_script_starter.py file

Any update on this?

Code Bug for llava/model/llava_arch.py

It looks like they have commented this out in the code, so I am also wondering whether the released models have actually used the slow-fast features as described in the...