Comments (2)
cebtenzzre
commented on September 25, 2024
1
I think fixing the endless generation bug (which is mainly caused by a logic error that creates an infinite loop) makes more sense than putting significant effort into allowing the LLModel thread to be restarted even if it encounters an infinite loop.
See also #2167 (comment). Would it be better to display the garbage the model is attempting to generate than to get stuck like this? The ideal fix includes adding customizable stop sequences to the UI, but it will be longer before that is implemented.
from gpt4all.
Seedmanc
commented on September 25, 2024
This makes Llama3 models barely usable as I have to manage to his the stop button before they finish. I never had this problem with any other model, including the one mentioned in the linked issue. Clearly it's something about the new Llama version that is missing support in GPT4All.
Also Llama3 7B works at 5 t/s sometimes despite all other 7B models doing 50 on my 2070s/CUDA.
from gpt4all.
Related Issues (20)
- Blog: Monitoring GPT4ALL HOT 2
- Issue in chat server response HOT 2
- UI Blurry HOT 2
- Python bindings cannot find msvcp140.dll - is there something I need to install? HOT 7
- v3.2.1 - Translations - LocalDocs - Date format in collections' descriptions does not change properly HOT 1
- v3.2.1 - Translations - Settings- >Application->Font Size
- Problem with phi-3.5-mini-instruct chat template and endless generation HOT 9
- [Feature] Add a copy button to the chat HOT 1
- v3.2.1 - LocalDocs - Deprecated/False/Misleading information HOT 4
- [Feature] Add support for RWKV
- Fine Tuning
- [Feature] Support nvidia_Llama3-ChatQA-1.5-8B
- [M1 Mac] Chat crashes when using Metal Device and Model too large HOT 2
- Scroll issue while downloading a model HOT 5
- 无法下载模型，有老哥知道原因么
- Example of http request to GPT4ALL local server api HOT 2
- [Feature] Unified Support for Ollama-Downloaded Models in GPT4All
- [Feature] +v3.x - LocalDocs - An option to open the folder which identifies a Collection
- Startup crash on 3.2.1
- GPT4All crashes when loading certain models since v3.2.1 HOT 2
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 gpt4all.