🥃 Distilling Tiny Embeddings
•
22
AI & ML interests
Applying machine learning to solve everyday problems
Recent Activity
Articles
Set of BERT models with a modified embeddings layer
Add knowledge to your txtai agents and processes.
Datasets with medical and scientific literature.
Models distilled with Model2Vec - 100K / 500K / 1M / 2M / 8M parameter variants.
-
NeuML/pubmedbert-base-embeddings-8M
Sentence Similarity • Updated • 132 • 10 -
NeuML/pubmedbert-base-embeddings-2M
Sentence Similarity • Updated • 17 • 3 -
NeuML/pubmedbert-base-embeddings-1M
Sentence Similarity • Updated • 9 • 2 -
NeuML/pubmedbert-base-embeddings-500K
Sentence Similarity • Updated • 17 • 2
Embeddings indexes and datasets for Wikipedia data.
Late interaction models
-
NeuML/colbert-muvera-femto
Sentence Similarity • 243k • Updated • 4 • 20 -
NeuML/colbert-muvera-pico
Sentence Similarity • 448k • Updated • 6 • 1 -
NeuML/colbert-muvera-nano
Sentence Similarity • 970k • Updated • 320 • 3 -
NeuML/colbert-muvera-micro
Sentence Similarity • Updated • 43 • 25
StaticVectors models to detect language. Exports of FastText that run in NumPy without needing FastText
Models for working with medical and scientific literature.
-
NeuML/pubmedbert-base-embeddings
Sentence Similarity • 0.1B • Updated • 597k • • 184 -
NeuML/pubmedbert-base-embeddings-matryoshka
Sentence Similarity • 0.1B • Updated • 4.27k • • 23 -
NeuML/pubmedbert-base-embeddings-8M
Sentence Similarity • Updated • 132 • 10 -
NeuML/pubmedbert-base-colbert
Sentence Similarity • 0.1B • Updated • 52 • 7
Text to Speech (TTS) models compatible with txtai's TextToSpeech pipeline.
Legacy word vectors (FastText, GloVe, Word2Vec) stored in the StaticVectors format
Set of BERT models with a modified embeddings layer
Late interaction models
-
NeuML/colbert-muvera-femto
Sentence Similarity • 243k • Updated • 4 • 20 -
NeuML/colbert-muvera-pico
Sentence Similarity • 448k • Updated • 6 • 1 -
NeuML/colbert-muvera-nano
Sentence Similarity • 970k • Updated • 320 • 3 -
NeuML/colbert-muvera-micro
Sentence Similarity • Updated • 43 • 25
Add knowledge to your txtai agents and processes.
StaticVectors models to detect language. Exports of FastText that run in NumPy without needing FastText
Datasets with medical and scientific literature.
Models for working with medical and scientific literature.
-
NeuML/pubmedbert-base-embeddings
Sentence Similarity • 0.1B • Updated • 597k • • 184 -
NeuML/pubmedbert-base-embeddings-matryoshka
Sentence Similarity • 0.1B • Updated • 4.27k • • 23 -
NeuML/pubmedbert-base-embeddings-8M
Sentence Similarity • Updated • 132 • 10 -
NeuML/pubmedbert-base-colbert
Sentence Similarity • 0.1B • Updated • 52 • 7
Models distilled with Model2Vec - 100K / 500K / 1M / 2M / 8M parameter variants.
-
NeuML/pubmedbert-base-embeddings-8M
Sentence Similarity • Updated • 132 • 10 -
NeuML/pubmedbert-base-embeddings-2M
Sentence Similarity • Updated • 17 • 3 -
NeuML/pubmedbert-base-embeddings-1M
Sentence Similarity • Updated • 9 • 2 -
NeuML/pubmedbert-base-embeddings-500K
Sentence Similarity • Updated • 17 • 2
Text to Speech (TTS) models compatible with txtai's TextToSpeech pipeline.
Embeddings indexes and datasets for Wikipedia data.
Legacy word vectors (FastText, GloVe, Word2Vec) stored in the StaticVectors format