mirror of
https://github.com/khoaliber/khoj.git
synced 2026-03-07 21:29:13 +00:00
Use a more accurate model for symmetric semantic search
- The all-MiniLM-L6-v2 is more accurate
- The exact previous model isn't benchmarked but based on the
performance of the closest model to it. Seems like the new model
maybe similar in speed and size
- On very preliminary evaluation of the model, the new model seems
faster, with pretty decent results
This commit is contained in:
@@ -14,7 +14,7 @@ def search_config(tmp_path_factory):
|
||||
search_config = SearchConfig()
|
||||
|
||||
search_config.asymmetric = SymmetricSearchConfig(
|
||||
encoder = "sentence-transformers/paraphrase-MiniLM-L6-v2",
|
||||
encoder = "sentence-transformers/all-MiniLM-L6-v2",
|
||||
cross_encoder = "cross-encoder/ms-marco-MiniLM-L-6-v2",
|
||||
model_directory = model_dir
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user