CPLM nthngdy/cplm-1.7B Text Generation • Updated about 9 hours ago • 267 nthngdy/cplm-baselines-1.7B Text Generation • Updated 7 days ago • 502 nthngdy/cplm-360M Text Generation • Updated 3 days ago • 12 nthngdy/cplm-baselines-360M Text Generation • Updated 3 days ago • 4
Q-Filters Pre-computed Q-Filters for efficient KV cache compression. nthngdy/Llama-3.1-8B-Instruct_qfilt 32.8k • Updated Nov 28, 2024 • 1.26k nthngdy/Llama-3.2-1B-Instruct_qfilt 8.19k • Updated Nov 28, 2024 • 896 nthngdy/Llama-3.2-3B-Instruct_qfilt 28.7k • Updated Feb 6, 2025 • 1.09k nthngdy/Llama-3.2-3B_qfilt 28.7k • Updated Nov 28, 2024 • 867
CPLM nthngdy/cplm-1.7B Text Generation • Updated about 9 hours ago • 267 nthngdy/cplm-baselines-1.7B Text Generation • Updated 7 days ago • 502 nthngdy/cplm-360M Text Generation • Updated 3 days ago • 12 nthngdy/cplm-baselines-360M Text Generation • Updated 3 days ago • 4
Q-Filters Pre-computed Q-Filters for efficient KV cache compression. nthngdy/Llama-3.1-8B-Instruct_qfilt 32.8k • Updated Nov 28, 2024 • 1.26k nthngdy/Llama-3.2-1B-Instruct_qfilt 8.19k • Updated Nov 28, 2024 • 896 nthngdy/Llama-3.2-3B-Instruct_qfilt 28.7k • Updated Feb 6, 2025 • 1.09k nthngdy/Llama-3.2-3B_qfilt 28.7k • Updated Nov 28, 2024 • 867