-
Please I want LLaVA.
https://llava-vl.github.io/
-
### Your current environment
```text
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.5 LTS (x86_64)
GCC ve…
-
Hello,
I am trying to evaluate LLaVA OneVision 72B, but finding I need to use tensor-parallelism to fit it on memory. However, when I do, evaluating on datasets (e.g., MLVU) takes 90+hrs on 4 A100s…
-
## Problem Statement
To support Vision models on Cortex, we need the following:
- [ ] 1. Download model .gguf and mmproj file
- [ ] 2. `v1/models/start` takes in `model_path` (.gguf) and `mmproj` p…
-
Hi, I try to use LLaVA-Video to evaluate nextqa and longvideobench_val dataset, but i got wrong answer in every questions
![image](https://github.com/user-attachments/assets/261cbbf0-55b1-4a61-9680-7…
-
Hi, based on your guidance, I train my model based on Qwen 1.5-1.8B.
While conducting the evaluation, I noticed that there appear to be some issues with the SQA and MMBench evaluations. The results …
-
Thank you for sharing the great work. I ask for some mismatch between the current codebase and arXiv technical report.
1. SlowFast mode
* Is slowfast representation only used for inference time,…
-
Hello,
A pretty novel work! But I have some questions.
I notice that in Table 2 of your paper, the base ACC & F1 on POPE for LLaVA-1.5 is 84.07 and 82.62,
![image](https://github.com/user-atta…
-
Dear @xiaoachen98,
Thank you very much for releasing the code. I am running your fine-tuning script to replicate your LLaMA 3 results. However, I am getting zero loss after the first iteration. Hav…
-
### 🚀 The feature, motivation and pitch
I see from the demo app codebase that Executorch supports LLAVA-1.5. Is there any plans to support LLaVA-NeXT, the updated and better vision model?
### Alte…