Updated packages, models, preparing for use with AWS (in background) 4a190c2 seanpedrickcase commited on 28 days ago
Changed 'large' model to Phi 3 Mini gguf 128k. Added requirements file for cpu. Put prompts in separate file. 232a079 seanpedrickcase commited on Jun 5, 2024
Attempted Gradio downgrade to 3.50.2 to resolve version conflicts 15476e8 seanpedrickcase commited on Jun 1, 2024
CPU Flan inference is crashing, so trying to revert to previous package versions that worked 85b6613 seanpedrickcase commited on Jun 1, 2024
Upgraded gradio and packages to latest. Switched Ctransformers with Llama.cpp Python f301d67 seanpedrickcase commited on Jun 1, 2024
Minor dependency updates, increased max allowable layers for GPU 8aa3ebb Sean-Case commited on Jan 17, 2024
Added temperature slider, more stringent checks for document relevance 6a76923 Sean-Case commited on Oct 24, 2023
put back pip install requirement for gradio 3.42.0 for likeData compatibility a462256 Sean-Case commited on Oct 23, 2023
Put sources behind accordion, minor change to model params. Gitignore update c2ff47a Sean-Case commited on Oct 20, 2023
Build fail when gpu_layers > 0, so will set to 0 at start and modify in app. 0a7a8db Sean-Case commited on Oct 16, 2023
Made GPU layer bar invisible. Changed default GPU layers when CUDA available 8249fd3 Sean-Case commited on Oct 16, 2023
Upgraded large model to Mistral OpenOrca 7B Q4. More checks for empty questions. 994ad90 Sean-Case commited on Oct 16, 2023
Changed embedding model, added reference to chat model on front page 275393f Sean-Case commited on Oct 13, 2023
Improved advanced model prompt, added stop generation button. context prompt improvements d213c15 Sean-Case commited on Oct 13, 2023
Stop generation button. Better model load. Trying one source that's longer. d5a8385 Sean-Case commited on Oct 12, 2023
Setting gpu_layer slider to false to prevent accidental misuse 9aef340 Sean-Case commited on Oct 11, 2023
gpu_layers should now update correctly. Added code for creating distribution. 114048b Sean-Case commited on Oct 11, 2023
Hopefully fixed Orca load cuda error. Loads in Orca on app load. Later gradio version installed. 1365c48 Sean-Case commited on Oct 10, 2023
Temporarily disabled Orca Mini load until Cuda compatibility sorted out 67af224 Sean-Case commited on Oct 10, 2023
Explicitly installs required gradio version upon loading app e78df68 Sean-Case commited on Oct 9, 2023
Added working like buttons. Added model choice. Modified requirements txt 2e536f9 Sean-Case commited on Oct 9, 2023
Disabled chat memory as I think it is not needed for most user queries (max_memory_length = 0) ed48a70 Sean-Case commited on Sep 1, 2023
Changed theme, example set now disappears upon new file load 71c040a Sean-Case commited on Sep 1, 2023
Adapted code to keep newly-loaded vectorstores within local user state 102df35 Sean-Case commited on Aug 30, 2023
New file uploads no longer write a global variable so hopefully not shared between sessions bc459f6 Sean-Case commited on Aug 29, 2023
Added to intro, temp disabled web page load, address pdf load issue 41ed1b7 Sean-Case commited on Aug 24, 2023
Remove ctransformers model load (not needed yet). Used faster keyword model 1ae7b34 Sean-Case commited on Aug 24, 2023