-
Hi, Amazing job for new llava-next-video model! Since it has 34B params and maybe need more than 1 GPU, so do we have support some inference accelerate method for new llava-next-video models? like sgl…
-
I tried the demo code and got an error:
```
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
from ll…
-
I'm trying to deploy llava-next-video with sglang, and it can successfully work. But I find it only focus on the first frame of input, like if I input 10 frames, and let model to describe it. And the …
-
不是引流,只是考虑到可能大家会有些不构成 issue 的小问题,有个群会比较好。 后续如果官方有需要,我愿意转让群管理
我的微信 dreamingforhope ,若二维码失效可添加我
![image](https://github.com/user-attachments/assets/7d2e8a60-3dcd-4a0a-85f4-6929d7b2222f)
-
I am seeking to utilize the llava-next-110b model to generate complex descriptions for an input image. Having tested numerous images, I've encountered instances where the inference result is empty, in…
J0eky updated
2 months ago
-
Hi, thank you very much for you research, it is very interesting!
I am interested in running the LLaVA-Next Interleave model but the file playground/demo/interleave_demo.py is missing
Can i find t…
-
- [x] MiniCPM-Llama3-V-2_5
- [x] Florence 2
- [x] Phi-3-vision
- [x] Bunny
- [x] Dolphi-vision-72b
- [x] Llava Next
- [ ] Idefics 3
- [ ] Llava Interleave
- [ ] Llava onevision
- [ ] internlm…
-
Thanks for your work! Can I input multi-images and multi-instructions for few-shot inference?
-
### System Info
transformers==4.42.3
### Who can help?
@zucchini-nlp
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Tasks
- [X] An official…
-
In multi-docvqa, a single data can have up to 20 images. Since llava-next doesn't compress tokens, wouldn't this result in too many tokens?