MonolithFoundation

ValueError: Unable to retrieve user and repo ID from the passed HF ID: https://huggingface.co/MonolithFoundation/Bumblebee-Light

9

I have loggined, the repo https://huggingface.co/MonolithFoundation/Bumblebee-Light exist. Just can not push models, why?

Consider using `hf_transfer` for faster uploads. T

1

Can be more detailed explain how to: `Consider using `hf_transfer` for faster uploads. T`?

Looks the code copied could lost the \n

2

Select part of the code block to copy (not all of them), the code's \n would be lost. Any suggestions about it? this would be text copied: ``` // Markdown文本...

Is there any reason for this?

May I ask how to single request add history?

2

May I ask how to single request add history? This really needed

Hi, If my model is multimodal and the geneates actually defines different like this: ``` generation_output = model_tp.generate( pixel_values=pixel_values, input_ids=input_ids, attention_mask=attention_mask, **generation_config, ) ``` it is don't work. How to...

How does the VILA preprocessed video?

1

Hi, looks like VILA trained a lot of videos, how does the being sampled? And how does it dealed with S2?

Does S2 able to unfreeze vit to train?

1

I think if using s2, and unfreeze vit, the result could be worse, as the s2 split images.

VisionEncoder里面的vit，用的是idefics2还是 hf4m那个啊？

5

VisionEncoder里面的vit，与训练 权重 用的是idefics2还是 hf4m那个啊？

如何显示英文啊？

2

如何显示英文啊？ yuan cheng远程显示不了中文