Sleeping
2
Analyze Stars
โญ
Explore GitHub stars dataset from ArXiv 2412.13459
David Mezzetti
davidmezzetti
AI & ML interests
None yet
Recent Activity
new activity about 1 month ago
NeuML/colbert-bert-tiny:Add Sentence Transformers usage repliedto their post about 1 month ago
Exciting addition coming with the next txtai release: LEMUR for ColBERT-style Late-Interaction Retrieval! ๐
Contributor @Morgan-coded introduced LEMUR to txtai, making it, as far as we know, the first framework to incorporate LEMUR for late-interaction retrieval using standard, fixed-vector indexes.
Key benefits:
๐ Significant boost: 49โ62% higher NDCG@10 than 2,048-dimensional MUVERA
๐พ 5x less storage: 2,048 dimensions vs. MUVERAโs default 10,240
๐ Better geometry: Optional batch mean centering addresses anisotropy in token embeddings
A promising step toward making ColBERT-style retrieval more practical with conventional vector search.
Read the full breakdown: https://huggingface.co/blog/NeuML/txtai-lemur repliedto their post about 1 month ago
Exciting addition coming with the next txtai release: LEMUR for ColBERT-style Late-Interaction Retrieval! ๐
Contributor @Morgan-coded introduced LEMUR to txtai, making it, as far as we know, the first framework to incorporate LEMUR for late-interaction retrieval using standard, fixed-vector indexes.
Key benefits:
๐ Significant boost: 49โ62% higher NDCG@10 than 2,048-dimensional MUVERA
๐พ 5x less storage: 2,048 dimensions vs. MUVERAโs default 10,240
๐ Better geometry: Optional batch mean centering addresses anisotropy in token embeddings
A promising step toward making ColBERT-style retrieval more practical with conventional vector search.
Read the full breakdown: https://huggingface.co/blog/NeuML/txtai-lemurOrganizations