-
Hi,
Thank you for your nice work.
I have a trouble in replicating the benchmark result like this:
- "paper-Tokenpacker" is the papers result
- "open-checkpoint" uses the checkpoint of…
-
In sunshine-lwt/TokenPacker-7b-144token, use openai/clip-vit-large-patch14-336, when I load model, appear :
![image](https://github.com/user-attachments/assets/c2bcf2fe-5745-44c7-910a-2713cc7e4a53)
…
-
Thanks for the excellent survey!
Would you like include a new work: TokenPacker: Efficient Visual Projector for Multimodal LLM.
Paper: https://arxiv.org/abs/2407.02392
Code: https://github.com/…
-
我正在试图在mini-gemini的预训练和指令微调数据集上复现TokenPacker-HD-7b-9patch-144token,但是没能得到比较满意的结果。我得到的pretrain阶段的loss曲线如下
![image](https://github.com/user-attachments/assets/9ccb2333-ccb3-4edd-94c7-52b97c148d7c)
inst…
-
-
https://github.com/CircleRadon/TokenPacker/blob/305ce146ec8b6d8b5ec4959f6cac699e7c8b9ed4/llava/train/train.py#L320
There is a comment on Line 321 which makes the indented block wrong. Maybe there s…
-
Thanks for your great job!
I’m quite curious about the performance comparison between TokenPacker and Average Pooling, because from my experience, the Pooling method converges faster and achieves bet…
-
Hello, I’m the author of TextHawk. I have noticed that TokenPacker shares the same starting points as TextHawk, including token compression and multi-level features. It's great to see more people gett…
-
Hi authors of this great project!
Fuyu-8 is great for it's flexibility to accept any aspect ratio or resolution great for UI understanding, but we don't know how it's trained. but now we got SOLO!
…
-
Hi authors,
Are the experimental results reported in Table 1 trained using miniGemini's training sample data? Or did you only use CC3M and 656K SFT data consistent with LLaVA-1.5.
Thanks.
Yxxxb updated
2 months ago