Comments (5)
Hi,
I was able to get 30B param model working.
13B should work fine too and 65B (If someone releases it xD)
You can look at this branch
https://github.com/PotatoSpudowski/fastLLaMa/tree/alpaca-lora
You will have to follow the build steps and convert the model again.
The issue with LoRA models are their embedding size. Based on how LoRA method works (It creates low rank decomposition matrices and freezes the pertained weights), I suspect that is why we have have different embedding sizes compared to non LoRA models.
Will need to sort out a few things before merging to main but feel free to use this and let me know if you face any issues :)
from fastllama.
Merged to main.
Structure of fastLlama.Model()
is updated. Please change accordingly!
from fastllama.
I will try and get it integrated tonight ;)
from fastllama.
Hi @PotatoSpudowski . I was curious how alpaca models are handled differently. For example, llama.cpp
requires alpaca models to have n_parts
and ins
flags. are those things accounted for ?
My C/C++ skills are not good enough to navigate your code.
from fastllama.
Yup, That's why why require users to specify the ModelIdentifier when initialising the model.
Based on the identifier, we chose the config from the backend (Which tells us about parts, vocab size etc). It is an underrated feature of fastLLaMa which imo is the right way to go about it.
The ins flag if I am not right is supposed to specify that it is in instruction mode is it? Either ways we have example files for Alpaca and LLaMA models which show how to use these models for either text completion or QNA tasks.
Finally we also are working on redesigning our save and load feature and optimising it for latency and size in the feature/save_load
branch. Extremely GOATED implementation!
Developers should be allowed to implement their own workflows using the features that were developed using first principles thinking rather than us deciding workflows for them. Will document everything extensively so it is easier for everyone!!!
from fastllama.
Related Issues (20)
- Cmake Error HOT 1
- Cannot build this HOT 5
- Pip support testing HOT 21
- from build.fastllama import Model, ModelKind ModuleNotFoundError: No module named 'build.fastllama' HOT 8
- convert-pth-to-ggml.py expects 2 parts for ALPACA-LORA-13B, but it has only one HOT 5
- Bad Magic error HOT 6
- When stop words are reached, they get ingested, but are not forwarded to streaming_fn. HOT 4
- Enabling custom logger makes it crash at ingestion. HOT 1
- TypeError: Model.generate() got an unexpected keyword argument 'stop_word' HOT 2
- Pip uninstall not removing the package HOT 2
- Designing the UI HOT 1
- Deciding the Schema for the protocol between webUI and webSocket Server HOT 2
- "No module named 'fastllama.api' " after pip installation HOT 10
- Implement the WebSocket Server
- Integrating + Testing webUI and WebSocket Server
- README.md is outdated in sections #running-llama and #running-alpaca-lora HOT 1
- how to load model in webui ? HOT 3
- Port llama.cpp openCL support to fastllama?
- Webui UX issue on mobile
- GGUF and/or LLama-3 support?
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 fastllama.