Pre-computed Q-Filters for efficient KV cache compression.
Nathan Godey
nthngdy
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
nthngdy/Llama-3.1-70B-Instruct_qfilt:Tag model as `q-filter`
upvoted
a
paper
4 days ago
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
commented on
a paper
4 days ago
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
Organizations
Collections
1
models
48
nthngdy/Llama-3.1-70B-Instruct_qfilt
Updated
•
14
nthngdy/olmo24b-random
Updated
•
14
nthngdy/DeepSeek-R1-Distill-Qwen-1.5B_qfilt
Updated
•
12
nthngdy/DeepSeek-R1-Distill-Llama-8B_qfilt
Updated
•
9
nthngdy/llama24b-random
Updated
•
28
nthngdy/olmo2-1B-random
Updated
•
11
nthngdy/Qwen2.5-7B-Instruct_qfilt
Updated
•
12
nthngdy/Qwen2.5-7B_qfilt
Updated
•
15
nthngdy/phi-4_qfilt
Updated
•
10
nthngdy/Mistral-Small-24B-Instruct-2501_qfilt
Updated
•
11
datasets
17
nthngdy/CheeseQA
Viewer
•
Updated
•
46.9k
•
56
nthngdy/mmlu_no_train
Viewer
•
Updated
•
31.7k
•
868
nthngdy/lambada_openai
Viewer
•
Updated
•
5.15k
•
51
nthngdy/crows_pairs_multilingual
Viewer
•
Updated
•
1.68k
•
57
nthngdy/ai2_arc
Viewer
•
Updated
•
7.79k
•
116
nthngdy/piqa
Viewer
•
Updated
•
21k
•
128
•
1
nthngdy/hellaswag
Viewer
•
Updated
•
60k
•
73
nthngdy/culturax_fr_metrics
Viewer
•
Updated
•
100k
•
69
nthngdy/pile_small_miniLM
Viewer
•
Updated
•
100k
•
82
nthngdy/babylm_10M
Viewer
•
Updated
•
1.02M
•
106