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 • 516k • 147 -
Snowflake/snowflake-arctic-embed-l
Sentence Similarity • Updated • 15.6k • 89 -
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity • Updated • 34.8k • 33 -
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity • Updated • 132k • 32
models
14
Snowflake/snowflake-arctic-embed-l
Sentence Similarity
•
Updated
•
15.6k
•
89
Snowflake/snowflake-arctic-embed-m-v2.0
Sentence Similarity
•
Updated
•
9.86k
•
50
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity
•
Updated
•
75.1k
•
97
Snowflake/snowflake-arctic-embed-m-v1.5
Sentence Similarity
•
Updated
•
24.5k
•
54
Snowflake/snowflake-arctic-embed-xs
Sentence Similarity
•
Updated
•
132k
•
32
Snowflake/snowflake-arctic-embed-m-long
Sentence Similarity
•
Updated
•
34.8k
•
33
Snowflake/snowflake-arctic-embed-m
Sentence Similarity
•
Updated
•
516k
•
147
Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8
Updated
•
79
Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8
Updated
•
10
Snowflake/Llama-3.1-SwiftKV-8B-Instruct
Updated
•
240
•
8