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
•
199
nthngdy/Llama-3.1-70B-Instruct_qfilt
0.0B
•
Updated
•
167
nthngdy/olmo24b-random
Updated
•
4
nthngdy/DeepSeek-R1-Distill-Qwen-1.5B_qfilt
0.0B
•
Updated
•
163
nthngdy/DeepSeek-R1-Distill-Llama-8B_qfilt
0.0B
•
Updated
•
164
nthngdy/llama24b-random
Updated
•
4
nthngdy/olmo2-1B-random
Updated
•
3
nthngdy/Qwen2.5-7B-Instruct_qfilt
0.0B
•
Updated
•
166
nthngdy/Qwen2.5-7B_qfilt
0.0B
•
Updated
•
167
nthngdy/phi-4_qfilt
0.0B
•
Updated
•
166
datasets
26
nthngdy/pile_small_deduped_tokenized
Viewer
•
Updated
•
100k
•
4
nthngdy/mmlu_olmo_decontaminated
Viewer
•
Updated
•
11.8k
•
4
nthngdy/mmlu_olmo_contaminated
Viewer
•
Updated
•
3.76k
•
24
nthngdy/mmlu_olmo_contamination
Viewer
•
Updated
•
15.9k
•
8
nthngdy/mmlu_shuffled
Viewer
•
Updated
•
31.7k
•
63
nthngdy/mmlu
Viewer
•
Updated
•
116k
•
11
nthngdy/penicillin
Updated
•
1
nthngdy/frenchmedmcqa
Viewer
•
Updated
•
1.08k
•
43
nthngdy/medmcqa
Viewer
•
Updated
•
193k
•
18
nthngdy/CheeseQA
Viewer
•
Updated
•
46.9k
•
4