-
Hi this is really a nice work that shows potential on embedding anything using LLMs.
In section 3.1, you explained that by a summary prompt, both vision and text can be embedded into next token. A…
-
I installed the repo with the provided script:
```sh
git clone https://github.com/DAMO-NLP-SG/VideoLLaMA2
cd VideoLLaMA2
pip install -r requirements.txt
pip install flash-attn==2.5.8 --no-build-i…
-
On my system I have a lot more memory compared to size of files that I open, so for almost all files precomputation runs.
In theory this is a good thing, but in practice I've noticed some weird bug…
-
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> import torch
>>> from PIL import Image
>>> checkpoint = "qihoo360/360VL-8B"
>>> model = AutoModelForCausalLM.from_pretrained(ch…
-
CODE:
```python
from PIL import Image
import torch
import os
from llava.serve.classes.Utils import *
from llava.serve.classes.Compiler import *
from llava.model.builder import load_mixed_…
-
**Describe the project you are working on:**
Not related to my project.
**Describe the problem or limitation you are having in your project:**
Lights in Godot Engine are clunky and look the same.…
-
Hello, I have a question.
First of all, I would like to ask if you used Depth image in the Pre-training process to train mm_projector.
If not, the shape of mm_projector in Pre-training and Fine-…
-
### Describe the issue
Issue:
We are trying to finetune the model on our dataset.
Currently, we are able to successfully finetune model `lmsys/vicuna-13b-v1.5` using projector weights `llava-v…
-
Hi there, I'm very interested in your work, and I am trying to train the model from the beginning following the instruction. However, I'm having trouble running the code, it says "AttributeError: 'V…
-
In GitLab by @Popolechien on Nov 1, 2019, 10:31
So we have a use case where everyone in the room has a tablet or smartphone but the teacher also wants to showcase on a large screen (projector or TV s…