Pre-computed Q-Filters for efficient KV cache compression.
Nathan Godey
nthngdy
AI & ML interests
None yet
Recent Activity
updated
a model
2 days ago
nthngdy/olmo2-1B-random
published
a model
2 days ago
nthngdy/olmo2-1B-random
updated
a collection
3 days ago
Q-Filters
Organizations
Collections
1
models
44
nthngdy/olmo2-1B-random
Updated
•
4
nthngdy/Qwen2.5-7B-Instruct_qfilt
Updated
nthngdy/Qwen2.5-7B_qfilt
Updated
nthngdy/phi-4_qfilt
Updated
nthngdy/Mistral-Small-24B-Instruct-2501_qfilt
Updated
nthngdy/Meta-Llama-3.1-405B_qfilt
Updated
nthngdy/Llama-3.2-3B-Instruct_qfilt
Updated
nthngdy/Llama-3.1-70B_qfilt
Updated
nthngdy/Llama-3.1-70B-Instruct_qfilt
Updated
nthngdy/Llama-3.2-1B-Instruct_qfilt
Updated
•
2
datasets
16
nthngdy/mmlu_no_train
Viewer
•
Updated
•
31.7k
•
340
nthngdy/lambada_openai
Viewer
•
Updated
•
5.15k
•
35
nthngdy/crows_pairs_multilingual
Viewer
•
Updated
•
1.68k
•
37
nthngdy/ai2_arc
Viewer
•
Updated
•
7.79k
•
35
nthngdy/piqa
Viewer
•
Updated
•
21k
•
466
•
1
nthngdy/hellaswag
Viewer
•
Updated
•
60k
•
40
nthngdy/culturax_fr_metrics
Viewer
•
Updated
•
100k
•
47
nthngdy/pile_small_miniLM
Viewer
•
Updated
•
100k
•
41
nthngdy/babylm_10M
Viewer
•
Updated
•
1.02M
•
36
nthngdy/wikipedia-22-12-concat-split
Viewer
•
Updated
•
93.5M
•
350