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 • 661k • • 151 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 42.2k • • 90 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 29.9k • 34 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 268k • 33
models
14
Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
42.2k
•
•
90
Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
340k
•
58
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
91.4k
•
•
124
Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
31.5k
•
•
55
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
268k
•
33
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
29.9k
•
34
Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
661k
•
•
151
Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
44
Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
178
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
806
•
7