glai
glai - GGUF LLAMA AI - Package for simplified model handling and text generation with Llama models quantized to GGUF format. APIs for downloading and loading models automatically, includes a db with models of various scale and quantizations. With this high level API you need one line to load the model and one to generate text completions.
OTHER License
Bot releases are hidden (Show)
Published by laelhalawani 9 months ago
Published by laelhalawani 9 months ago
Published by laelhalawani 9 months ago
ModelDB moved to separate package gguf_modeldb with parallel API, with extended functionality
EasyAI - added ability to selectively import models from db, search only downloaded models and import from url repo
AutoAI - added ability to use only downloaded models
What's Changed
- Gguf modeldb as separate package by @laelhalawani in https://github.com/laelhalawani/glai/pull/35
- Develop by @laelhalawani in https://github.com/laelhalawani/glai/pull/36
Full Changelog: https://github.com/laelhalawani/glai/compare/v0.0.19...v0.1.0
Published by laelhalawani 9 months ago
System prompt support added for models compatible with it.
56 verified model GGUFs added to DB with preconfigured and tested prompt formatting for super easy deployment
Now the DB works globally for all your projects (meaning models are stored in the main package and accessible from all projects), but you can also specify a specific model_db dir to use it instead of the global db.
Published by laelhalawani 10 months ago
Published by laelhalawani 10 months ago
moved components to dedicated packages:
LlamaAI -> gguf_llama
helpers -> util_helper
updated init.py(s) and requirements
Published by laelhalawani 10 months ago
Published by laelhalawani 10 months ago
Published by laelhalawani 10 months ago
Published by laelhalawani 10 months ago
Second alpha release.
Published by laelhalawani 10 months ago