-
Add siglip flashattention support?
I noticed that the navit-flashatten-siglip version already added flash attention, would transformers add it support inside ?
-
can I sft MLLM with your train split?
-
It looks like llama.cpp now [supports openbmb/MiniCPM-Llama3-V-2_5.](https://github.com/ggerganov/llama.cpp/pull/7599)
Here's the [official gguf.](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_…
-
Hi, it looks an extremly tiny trick can make image MLLM do video good, still have 2 questions wanna to disuccus.
1. Does the MVbench tested as well? How does MVBench work?
2. Have u consider do so…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
- `llamafactory` version: 0.8.4.dev0
- Platform: Linux-5.14.0-480.el9.x86_64-x86_64-with-glibc2.17
- Py…
GzmCR updated
2 months ago
-
https://github.com/amusi/ECCV2024-Papers-with-Code
追記:
ECCV2024速報:https://hirokatsukataoka.net/temp/presen/241004ECCV2024Report_finalized.pdf
-
### Description
Test the expert performance
### Additional Information
_No response_
-
**Describe the bug**
Can't import model, running demo code
**To Reproduce**
import package
**Expected behavior**
demo run
**Screenshots**
![image](https://github.com/kyegomez/AudioFlaming…
-
现在的页面过滤只能支持一组关键词，如高亮包含 "multimodal" 的内容。但是无法支持同时高亮多组关键词。
期望功能：支持同时高亮多组关键词，如输入 "multimodal, MLLM"，其中关键词通过 ", " 进行分割，搜索后可以高亮 / 过滤任一包含其中一个关键词的文本。
-
The LlavaPocessor provides a direclty input of images and text.
But when I just need text conversation with MLLMs, it throws error. because images if None, it will have error in returned BatchFeature…