Pre-computed Q-Filters for efficient KV cache compression.
Nathan Godey
nthngdy
AI & ML interests
None yet
Recent Activity
updated
a dataset
less than a minute ago
nthngdy/penicillin_plus
updated
a dataset
4 minutes ago
nthngdy/penicillin_plus
updated
a dataset
4 minutes ago
nthngdy/penicillin_plus
Organizations
Collections
1
models
49

nthngdy/llama2-0b-unit-test_qfilt
Updated
•
272

nthngdy/Llama-3.1-70B-Instruct_qfilt
Updated
•
124

nthngdy/olmo24b-random
Updated

nthngdy/DeepSeek-R1-Distill-Qwen-1.5B_qfilt
Updated
•
167

nthngdy/DeepSeek-R1-Distill-Llama-8B_qfilt
Updated
•
130

nthngdy/llama24b-random
Updated
•
1

nthngdy/olmo2-1B-random
Updated

nthngdy/Qwen2.5-7B-Instruct_qfilt
Updated
•
3.53k

nthngdy/Qwen2.5-7B_qfilt
Updated
•
121

nthngdy/phi-4_qfilt
Updated
•
121
datasets
21
nthngdy/penicillin_plus
Viewer
•
Updated
•
779k
•
93
nthngdy/penicillin
Updated
•
93
nthngdy/frenchmedmcqa
Viewer
•
Updated
•
1.08k
•
124
nthngdy/medmcqa
Viewer
•
Updated
•
193k
•
43
nthngdy/CheeseQA
Viewer
•
Updated
•
46.9k
•
41
nthngdy/mmlu_no_train
Viewer
•
Updated
•
31.7k
•
528
nthngdy/lambada_openai
Viewer
•
Updated
•
5.15k
•
19
nthngdy/crows_pairs_multilingual
Viewer
•
Updated
•
1.68k
•
20
nthngdy/ai2_arc
Viewer
•
Updated
•
7.79k
•
18
nthngdy/piqa
Viewer
•
Updated
•
21k
•
537
•
1