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 • 745k • 149 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 40.9k • 90 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 27.4k • 33 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 224k • 32
models
14
Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
40.9k
•
90
Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
167k
•
56
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
86.3k
•
110
Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
29.7k
•
54
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
224k
•
32
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
27.4k
•
33
Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
745k
•
149
Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
37
Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
104
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
386
•
8