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 • 674k • • 151 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 42.3k • • 90 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 30.4k • 33 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 270k • 33
models
14
Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
42.3k
•
•
90
Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
330k
•
58
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
89.1k
•
•
121
Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
32.6k
•
•
54
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
270k
•
33
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
30.4k
•
33
Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
674k
•
•
151
Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
40
Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
173
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
722
•
7