Pre-computed Q-Filters for efficient KV cache compression.
Nathan Godey
nthngdy
AI & ML interests
None yet
Organizations
models
49
nthngdy/llama2-0b-unit-test_qfilt
0.0B
•
Updated
•
134
nthngdy/Llama-3.1-70B-Instruct_qfilt
0.0B
•
Updated
•
103
nthngdy/olmo24b-random
Updated
•
6
nthngdy/DeepSeek-R1-Distill-Qwen-1.5B_qfilt
0.0B
•
Updated
•
107
nthngdy/DeepSeek-R1-Distill-Llama-8B_qfilt
0.0B
•
Updated
•
148
nthngdy/llama24b-random
Updated
•
6
nthngdy/olmo2-1B-random
Updated
•
2
nthngdy/Qwen2.5-7B-Instruct_qfilt
0.0B
•
Updated
•
103
nthngdy/Qwen2.5-7B_qfilt
0.0B
•
Updated
•
100
nthngdy/phi-4_qfilt
0.0B
•
Updated
•
103
datasets
26
nthngdy/pile_small_deduped_tokenized
Viewer
•
Updated
•
100k
•
12
nthngdy/mmlu_olmo_decontaminated
Viewer
•
Updated
•
11.8k
•
189
nthngdy/mmlu_olmo_contaminated
Viewer
•
Updated
•
3.76k
•
250
nthngdy/mmlu_olmo_contamination
Viewer
•
Updated
•
15.9k
•
65
nthngdy/mmlu_shuffled
Viewer
•
Updated
•
31.7k
•
228
nthngdy/mmlu
Viewer
•
Updated
•
116k
•
21
nthngdy/penicillin
Updated
•
1
nthngdy/frenchmedmcqa
Viewer
•
Updated
•
1.08k
•
62
•
1
nthngdy/medmcqa
Viewer
•
Updated
•
193k
•
6
nthngdy/CheeseQA
Viewer
•
Updated
•
46.9k
•
5