seanpedrickcase/topic_modelling at 00db72b43b950414f2e3397c91839588d57a4810

topic_modelling

180 kB

4 contributors

History: 53 commits

seanpedrickcase

Further optimised Dockerfile and requirements (smaller torch installation now hopefully)

00db72b over 1 year ago

.github
first commit almost 2 years ago
funcs
Removed some requirements from Dockerfile for AWS deployment to reduce container size over 1 year ago
.dockerignore

203 Bytes

Can split passages into sentences. Improved embedding, LLM representation models, improved zero shot capabilities over 1 year ago
.gitignore

226 Bytes

Can split passages into sentences. Improved embedding, LLM representation models, improved zero shot capabilities over 1 year ago
Dockerfile

2.75 kB

Further optimised Dockerfile and requirements (smaller torch installation now hopefully) over 1 year ago
LICENSE

11.6 kB

first commit almost 2 years ago
README.md

1.9 kB

Updated Gradio version for spaces. Updated Dockerfile to enable Llama.cpp build with Cmake over 1 year ago
app.py

13.7 kB

Allowed for app running on AWS to use smaller embedding model and not to load representation LLM (due to size restrictions). over 1 year ago
download_model.py

517 Bytes

Updated download_model.py to download pytorch .bin file over 1 year ago
how_to_create_exe_dist.txt

1.89 kB

Upgraded to Gradio 4.16.0. Guide for converting to exe added. almost 2 years ago
requirements.txt

615 Bytes

Allowed for app running on AWS to use smaller embedding model and not to load representation LLM (due to size restrictions). over 1 year ago
requirements_aws.txt

393 Bytes

Further optimised Dockerfile and requirements (smaller torch installation now hopefully) over 1 year ago
requirements_gpu.txt

646 Bytes

Allowed for app running on AWS to use smaller embedding model and not to load representation LLM (due to size restrictions). over 1 year ago