Comments (3)
thistleknot
commented on August 28, 2024
1
This is cool. I read about quantizing the model down using some other
methods... I thought I'd try my hand
https://github.com/juncongmoo/pyllama
…On Fri, Apr 7, 2023 at 10:49 AM aka4el ***@***.***> wrote:
You can try this solution from the next branch (I successfully switched to
it, but I have 12 GB of video memory)
https://github.com/oobabooga/text-generation-webui#readme
Scroll the page to the points - *Installation-One-Click Installers*
-oobabooga-windows.zip
Just download the zip and follow the instructions, everything will go in
auto mode. With a small amount of video memory, there are options to use
hybrid modes using the CPU, RAM, disk cache.
You can also read about small video memory and here -
https://github.com/oobabooga/text-generation-webui/wiki/Low-VRAM-guide
—
Reply to this email directly, view it on GitHub
<#211 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABHKKOUYCIWE4H6R5VB6BX3XABHRTANCNFSM6AAAAAAWWXVFPQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
from alpaca.cpp.
aka4el
commented on August 28, 2024
You can try this solution from the next branch (I successfully switched to it, but I have 12 GB of video memory) https://github.com/oobabooga/text-generation-webui#readme
Scroll the page to the points - Installation-One-Click Installers-oobabooga-windows.zip
Just download the zip and follow the instructions, everything will go in auto mode. With a small amount of video memory, there are options to use hybrid modes using the CPU, RAM, disk cache.
You can also read about small video memory and here - https://github.com/oobabooga/text-generation-webui/wiki/Low-VRAM-guide
If you start that project, then the models will need a different type, but it’s easy to download them, there is a set of links, or you can find them yourself on huggingface(dot)co
I found for example a small (but also weaker) model, it takes only 2GB of memory to work, see how it just flies 14 tokens per second like a rocket
from alpaca.cpp.
thistleknot
commented on August 28, 2024
this isreally cool, thanks for the tip!
from alpaca.cpp.
Related Issues (20)
- Issues with Monte Carlo Tree Search on alpaca.cpp
- Input Handling HOT 1
- Segmentation Fault with 7b on Raspberry Pi 3 HOT 5
- ### Instruction: ### Response: HOT 3
- Random seed not working correctly, "too many inputs", chinese symbols?
- How to use with python HOT 1
- Can i use it on linux with nvidia gpu HOT 4
- minimum specs
- Does not perceive other languages HOT 5
- Are there any plans to add support for 13B and beyond? HOT 7
- Running very slow HOT 7
- Redpajama dataset?
- using ggml-alpaca-13b-q4.bin HOT 1
- Archive Repository HOT 1
- main: failed to load model from 'ggml-alpaca-7b-q4.bin' HOT 4
- llama_model_load: failed to open 'ggml-alpaca-7b-native-q4.bin' HOT 1
- HuggingFaceH4/starchat-alpha Cpp LLM
- Adding risc-v architecture support HOT 1
- failed to load model
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 alpaca.cpp.