Comments (3)
This error is due to insufficient CPU RAM, specifically, the model parameters are loaded into CPU RAM before they are assigned to the GPUs. You can refer to the official documents: https://huggingface.co/blog/accelerate-large-models
Please try to use the option offload_folder="offload"
.
from chat-univi.
This error is due to insufficient CPU RAM, specifically, the model parameters are loaded into CPU RAM before they are assigned to the GPUs. You can refer to the official documents: https://huggingface.co/blog/accelerate-large-models
Please try to use the option
offload_folder="offload"
.
Loading checkpoint shards: 67%|███████████████████████████████████████████████████████████████████████████████████████████████████▎ | 2/3 [00:18<00:09, 9.21s/it]Killed
from chat-univi.
I have not encountered these errors before, according to the instructions of the official documents, you can try to use the option offload_state_dict = True, torch_dtype=torch.float16
.
from chat-univi.
Related Issues (20)
- Question about how to detect events in video HOT 2
- 16GB-VRAM run Chat-UniVi-7B-v1.5 model? HOT 1
- Where is `CGD/images`, `LA/images` and `SD/images`? HOT 1
- When will the training codes and model weights of `Chat-UniVi-7B v1.5` be released? HOT 2
- dpc implementation HOT 1
- Could you release the trained weights of the Stage-1 Training? HOT 2
- A bug of the latest commit ` add v1.5` HOT 2
- Hardware requirements for inference
- inference
- 【Bug】Training becomes pending if the training dataset contains text data. HOT 1
- Unable to Reproduce Training Process HOT 1
- huggingface demo error
- Is it a mistake to get patch_num_h from w? HOT 1
- ModuleNotFoundError: No module named 'ChatUniVi.model.language_model.phi' HOT 3
- Downloading the ActivityNet (Zero Shot) Dataset HOT 3
- Why `image_aspect_ratio` is set to `square` rather than `pad` HOT 1
- Hosting ChatUniVi in Sanic Application: ZeroDivisionError
- mm_projector.bin | size mismatch error
- Can this model apply a few-shot when inference?
- The image folder in the MIMIC_Imageonly
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 chat-univi.