SwiftKV reduces prefill compute by up to 50% by combining model rewiring and knowledge-preserving self-distillation.

Snowflake
Enterprise
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Learn more about our AI research and open source projects, connect with our research team here.
Collections
3
A collection of text embedding models optimized for retrieval accuracy and efficiency
-
Snowflake/snowflake-arctic-embed-m
Sentence Similarity • Updated • 406k • • 153 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 25.4k • • 91 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 16.5k • 36 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 287k • • 35
models
14

Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
25.4k
•
•
91

Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
227k
•
63

Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
110k
•
•
131

Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
64.9k
•
•
56

Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
287k
•
•
35

Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
16.5k
•
36

Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
406k
•
•
153

Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
40

Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
69

Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
799
•
7