Comments (10)
Closed as this is not an issue that can be solved with a pull request. We are training improved models to deploy on edge which will progressively perform better on more difficult tasks such as the one you posed.
I encourage you to keep using OpenAI and we'll focus on making edge LLMs sicker, more powerful and based on a strong open source foundation!
from gpt4all.
It is Said in the Training Log About This...
from gpt4all.
There should be options repeat_last_n
and repeat_penalty
, you may try to set like --repeat_last_n 4096 --repeat_penalty 1.5
, but will it correctly work or not is a different question.
from gpt4all.
Also happens sometimes in Linux, like a loop of verbiage
from gpt4all.
There it produced valid code. Here there’s no valid code. No idea if the underlying issue is the same.
from gpt4all.
Same here
from gpt4all.
It won't correctly work, at least in my example. It answers a different question.
> Give me a C++ algorithm for the integer square root (isqrt)
Here'll be your code snippet to calculate sqrt of any positive number in cpp using function overloading technique : ```cpp`int i, j; // Declare two variables int arr[10];//Declaring array with capacity as per requirement `void main() { scanf("%d", &n); printf("Enter Number\t"); getchar(); } while(arr != NULL && n > -2){ if((j = atoi(&std::cin >> std::ws)) == EOF || !isdigit(*&eof)){ eprintf("\r" << "Invalid input.\nTry Again."); continue;} else{if(!strcmp_icaseins(_T('\x7F'), _T(' '), strtok())) return;`
Well, fair enough. Sounds like useful code generation is a bit too hard for it atm :-)
from gpt4all.
Just to wrap things up, here's a response from GPT-4. Spoiler alert: it gets it perfectly right.
from gpt4all.
It even tries to circumvent repeat penalty!
### Instructions (cont.):
### Response:
### Instructuions(cont):
#####Instruction: ####Response:
#####Instruction: ###Response:
#########Instruction: # Response:
#################Instruction: ##Response:
******************Instruction: ****Response:*****
#################Instruction: **Response:*********/
/////////////////////Instruction: /////Response://////////
////////////////////////////Instruction:: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::://
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::/
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::~
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::o
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::l
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::r
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::v
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::t
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::c
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::a
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::d
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::b
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::f
////////////////////////////Instruction: ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::g
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::h
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::i
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::j
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::k
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::l
////////////////////////////Instruction: :::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::m
from gpt4all.
@AndriyMulyar Why is it closed without any notice? This bug still exists.
from gpt4all.
Related Issues (20)
- crashes at launch HOT 2
- [Feature] Allow different context window lengths in python binding (i.e., n_ctx set by user) HOT 1
- C# build instructions for MSVC on Windows are unclear
- Can not install gpt4all on windows 7 HOT 1
- Hello, I have installed Starcoder. How do I use it? HOT 1
- How to configure models specifically for RAG (localdocs)?
- Build success, but packed failed using QT deploy tool both win & mac HOT 13
- GPT4All v2.7.3: List of Chats: Visible construction of the short summary/main idea of a Chat
- [Feature] Add llama 3 model HOT 7
- Load model failed and report PrefetchVirtualMemory unavailable HOT 1
- No local models available for download in chat UI? HOT 1
- SDK for Game Engine HOT 2
- [Feature] Add Dolphin 2.9 Llama 3 8b (uncensored) HOT 2
- [Feature] add the ability to use plugins
- C# bindings need to be updated HOT 2
- [Feature] Apple Silicon Neural Engine: Core ML model package format support HOT 4
- Crash on a windows laptop - Fixed, problem was a non-ASCII character in model download directory HOT 1
- GPT4All crashes when I try to reload my models in a chat
- Incorrect tool tip instructions HOT 1
- [bug] Continue showing "Load a model to continue" HOT 5
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.