search

laelhalawani / 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.
https://laelhalawani.github.io/glai/
Other
5 stars 0 forks source link

ModelDB search logic - change search score logic #22

Closed laeljh closed 6 months ago

laeljh commented 6 months ago

Curretly similarity scores for name_search, quantization_search, keyword_search in ModelDB are weighted evenly. Model name match should be prioritized over quantization and both of these over keywords

laelhalawani commented 6 months ago

Done and GGUF ModelDB has been moved to a dedicated package gguf_modeldb availablen on github and pypi https://github.com/laelhalawani/gguf_modeldb pip install gguf_modeldb>=0.0.1a3