4 Commits

Author	SHA1	Message	Date
Debanjum Singh Solanky	4a90972e38	Use a better model for asymmetric semantic search ... - The multi-qa-MiniLM-L6-cos-v1 is more extensively benchmarked[1] - It has the right mix of model query speed, size and performance on benchmarks - On hugging face it has way more downloads and likes than the msmarco model[2] - On very preliminary evaluation of the model - It doubles the encoding speed of all entries (down from ~8min to 4mins) - It gave more entries that stay relevant to the query (3/5 vs 1/5 earlier) [1]: https://www.sbert.net/docs/pretrained_models.html [2]: https://huggingface.co/sentence-transformers	2022-07-18 20:27:26 +04:00
Debanjum Singh Solanky	78b76d65a0	Minor fix to notes jsonl file extension in sample_config.yml	2022-01-29 04:13:36 -05:00
Debanjum Singh Solanky	c31abad0a6	Mount embeddings to /data/embeddings for directory naming consistency ... - Keeps directory paths consistent between host and container volumes - Consistency simplifies documentation and updates required to setup sample_config.yml for local installation	2022-01-29 03:24:02 -05:00
Debanjum Singh Solanky	b0067fc32e	Store docker, conda, semantic-search configuration in a config directory ... - Improves organization of config files required for application - Declutters the application root directory from configs	2022-01-29 02:41:11 -05:00