Comments (5)
Hi @Nastu-Ho,
As per our experiments, we did not notice any accuracy gains when using Phi3-mini-4K LLM or Vicuna. However, full fine-tuning was better in the case of LLaMA-3 as compared to LoRA.
Thank you for your reply.
One thing I'm curious about is whether a stronger LLM can continue to bring improvements in mvbench.
The problem I am currently encountering is that my model has been replaced with a stronger LLM (qwen2, mistral) and has not been significantly improved like videochat2.
So I'm curious about the performance of your method using different LLMs (such as LLaMA3, mistral) on mvbench?
from videogpt-plus.
Hi @Nastu-Ho,
We sample 16 frames for VCGBench_FINETUNING
training and 8 frames for MVBench_FINETUNING
training.
For video branch, the features per frame are 64 and for image branch the features per frame are 144. So in total for 8 frame configuration, the total number of vision tokens is 64x8+144x8=1664.
I hope it will help.
from videogpt-plus.
Hi @Nastu-Ho,
As per our experiments, we did not notice any accuracy gains when using Phi3-mini-4K LLM or Vicuna. However, full fine-tuning was better in the case of LLaMA-3 as compared to LoRA.
from videogpt-plus.
Hi @Nastu-Ho,
We do not have the MVBench results using LLaMA-3 LLM, however, I can share the numbers with Vicuna 7B and 13B that we observe during experiments and this may give us some clues about the trend.
With Vicuna 7B and 13B, we obtain 53.10 and 58.67 average scores on MVBench. These experiments show that using a better/stronger LLM improves the MVBench performance. However, we do not have any ablations with LLaMA-3 and Mistral.
If you have any findings, please do share. Thank You.
from videogpt-plus.
Hey, I want to know how many frames a video is sampled during the training process?
If the number of samples is fixed, how many visual tokens will be input to LLM for a video?
from videogpt-plus.
Related Issues (20)
- Where to download the VCGplus 110k original video? HOT 6
- Performance on MVBench HOT 8
- are you planning to relase the inference codes for VideoGPT-plus_LLaMA3-8B-8k and/or VideoGPT-plus_Vicuna-7B-4k HOT 1
- The webm file from ssv2 can not be loaded HOT 3
- Simple Demo HOT 3
- eval/vcgbench/inference/run_ddp_inference.sh HOT 1
- About pre-training stage. HOT 2
- Detailed Video Descriptions HOT 3
- In what order should I reproduce the paper? HOT 6
- About downloading the datatset? HOT 1
- Question about Training Time HOT 1
- Intermediate descriptions for vcg-plus_112k
- Phi3Model ImportError HOT 2
- You are using a model of type phi3 to instantiate a model of type VideoGPT+. This is not supported for all configurations of models and can yield errors.
- “python setup.py install” for flash-attention reports errors HOT 1
- Where can I find the dense captions for the 112K videos?
- Support for Multi-turn Conversations with Fixed Video Input?
- Inquiry about Costs Associated with Video LLM Benchmarks
- Zero-shot QA evaluation
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from videogpt-plus.