Comments (4)
Thanks for your interest. We don't have plans to train a smaller model at the moment
from lwm.
If other researchers have such plan, please reply and we may work together!
from lwm.
@StarCycle This is an amazing project but, I'm just going to try to load it 8bit (i don't even know if it will work). I have a 4070ti, never loads f16 let alone 32 for 7B models. If there was a way for the community to pinch in and help you guys to do the training on tinyllama or phi3 it would be awesome. I have no idea how much it would cost, I don't think it's cheap or affordable. If it's any of the two I'm jumping in.
from lwm.
@StarCycle This is an amazing project but, I'm just going to try to load it 8bit (i don't even know if it will work). I have a 4070ti, never loads f16 let alone 32 for 7B models. If there was a way for the community to pinch in and help you guys to do the training on tinyllama or phi3 it would be awesome. I have no idea how much it would cost, I don't think it's cheap or affordable. If it's any of the two I'm jumping in.
Hi @befman123, I tried to generate video with LWM. It needs a quite large GPU memory to achieve that (I had to use A100 80G or H100). After 3 minutes, I got a video with 2 second and the quality is bad. Btw, I am not familiar with Jax though I hear that Jax is quite efficient even on Nvidia GPU.
I think maybe we can wait for Meta to make their Chameleon open source, which is similar to LWM (text and image generation with LLM + VQGAN encoder/decoder, without video generation). Bytedance also made their VAR open-source. The smallest version of VAR only has 310M parameters. The best news: they are written in pytorch.
Perhaps you can first start with finetuning these pytorch model? If you like, we can set up a discord server first and check how many people are also interested in it!
from lwm.
Related Issues (20)
- Request for publicizing the LWM-1K/8K JAX or PyTorch model
- AttributeError: module 'jax.numpy' has no attribute 'DeviceArray' when run sample_video.sh
- RESOURCE_EXHAUSTED: XLA:TPU compile permanent
- DP FSDP & SP
- ValueError: Incompatible shapes for broadcasting: (2, 1, 1, 526464) and requested shape (2, 1, 32768, 32768) HOT 2
- Can it be used in the environment H100 ?
- Great work! Any plan for the vision-language models in Pytorch?
- Weight conversion scripts HOT 1
- Minimum GPU memory capacity required to run HOT 1
- vision model initialization
- what is the "_missing_keys"?
- Interesting Problems of Accuracy & Inference Speed with run_eval_needle.sh
- Question about loading LLaMA-2 7B on the LLM context extension stage
- vison-language model training data example for videos
- Any consideration on why use 4 sp & 32 tp?
- Quantize model weights
- Error while running bash command: run_sample_video.sh | Error: "TypeError: missing a required argument: 'segment_ids'" HOT 5
- Hang in vision_generation.py with newer versions of Jax HOT 1
- A question on your implementation of decoder phase of llama
- I wonder if you will release the tokenized dataset.
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 lwm.