SwiftKV reduces prefill compute by up to 50% by combining model rewiring and knowledge-preserving self-distillation.
Snowflake
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
3
A collection of text embedding models optimized for retrieval accuracy and efficiency
-
Snowflake/snowflake-arctic-embed-m
Sentence Similarity • Updated • 747k • 148 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 36.4k • 90 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 28.6k • 33 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 197k • 32
models
14
Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
36.4k
•
90
Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
62k
•
53
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
79.3k
•
107
Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
23.5k
•
54
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
197k
•
32
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
28.6k
•
33
Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
747k
•
148
Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
70
Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
102
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
339
•
8