Added and replaced relevant files to download in download_model.py to allow for app use on AWS 49e0db8 seanpedrickcase commited on Nov 20, 2024
App now retains original index following cleaning to allow for referring back to original data 90553eb seanpedrickcase commited on Sep 25, 2024
Now installed dependencies into correct folder in Dockerfile 5888649 seanpedrickcase commited on Aug 15, 2024
Finally managed to enforce cpu torch install in Dockerfile 97913c4 seanpedrickcase commited on Aug 15, 2024
Further optimised Dockerfile and requirements (smaller torch installation now hopefully) 00db72b seanpedrickcase commited on Aug 15, 2024
Transferring across installed packages from build stage in Dockerfile c9da99d seanpedrickcase commited on Aug 14, 2024
Changed Dockerfile to multi-stage build to further reduce size 0fd155c seanpedrickcase commited on Aug 14, 2024
Trying to make container image smaller through Dockerfile 7d5387e seanpedrickcase commited on Aug 14, 2024
Removed some requirements from Dockerfile for AWS deployment to reduce container size 51ba1cb seanpedrickcase commited on Aug 13, 2024
Added NUMBA_CACHE_DIR to Docker environmental variables cd6a3e0 seanpedrickcase commited on Aug 13, 2024
Allowed for app running on AWS to use smaller embedding model and not to load representation LLM (due to size restrictions). 22ca76e seanpedrickcase commited on Aug 12, 2024
Dockerfile now installs models directly into user folder instead of moving from base folder 3c1c3de seanpedrickcase commited on Aug 9, 2024
Updated Gradio version for spaces. Updated Dockerfile to enable Llama.cpp build with Cmake d34af22 seanpedrickcase commited on Aug 9, 2024
Updated packages. Improve hierarchy vis. Better models - mixedbread and phi3. Now option to split texts into sentences before modelling. 04a15c5 seanpedrickcase commited on Jun 20, 2024
