Pre-computed Q-Filters for efficient KV cache compression.
Nathan Godey
nthngdy
AI & ML interests
None yet
Recent Activity
updated
a dataset
2 days ago
nthngdy/medmcqa
published
a dataset
2 days ago
nthngdy/medmcqa
updated
a model
3 days ago
nthngdy/llama2-0b-unit-test_qfilt
Organizations
Collections
1
models
49

nthngdy/llama2-0b-unit-test_qfilt
Updated
•
156

nthngdy/Llama-3.1-70B-Instruct_qfilt
Updated
•
28

nthngdy/olmo24b-random
Updated
•
20

nthngdy/DeepSeek-R1-Distill-Qwen-1.5B_qfilt
Updated
•
19

nthngdy/DeepSeek-R1-Distill-Llama-8B_qfilt
Updated
•
15

nthngdy/llama24b-random
Updated
•
35

nthngdy/olmo2-1B-random
Updated
•
9

nthngdy/Qwen2.5-7B-Instruct_qfilt
Updated
•
19

nthngdy/Qwen2.5-7B_qfilt
Updated
•
21

nthngdy/phi-4_qfilt
Updated
•
15
datasets
18
nthngdy/medmcqa
Viewer
•
Updated
•
193k
•
8
nthngdy/CheeseQA
Viewer
•
Updated
•
46.9k
•
100
nthngdy/mmlu_no_train
Viewer
•
Updated
•
31.7k
•
829
nthngdy/lambada_openai
Viewer
•
Updated
•
5.15k
•
51
nthngdy/crows_pairs_multilingual
Viewer
•
Updated
•
1.68k
•
54
nthngdy/ai2_arc
Viewer
•
Updated
•
7.79k
•
123
nthngdy/piqa
Viewer
•
Updated
•
21k
•
139
•
1
nthngdy/hellaswag
Viewer
•
Updated
•
60k
•
71
nthngdy/culturax_fr_metrics
Viewer
•
Updated
•
100k
•
65
nthngdy/pile_small_miniLM
Viewer
•
Updated
•
100k
•
75