ADPQ quantized weights using auto-adpq library
Thomas
Tfloow
·
AI & ML interests
Where HW & SW meets
Developing the next generation of compute aware accelerators for fast, efficient and flexible computation.
Organizations
None yet
models 34
Tfloow/OmniQuant
Updated
Tfloow/Llama-3.1-8B-Instruct-adpq-4bit-sim
8B • Updated • 2
Tfloow/Llama-3.2-3B-Instruct-adpq-4bit-sim
3B • Updated • 3
Tfloow/Llama-3.2-3B-adpq-4bit-sim
3B • Updated • 1
Tfloow/Llama-3.2-1B-Instruct-adpq-4bit-sim
1B • Updated • 1
Tfloow/Llama-3.2-1B-adpq-4bit-sim-0.02
1B • Updated • 1
Tfloow/Meta-Llama-3.1-8B-adpq-4bit-sim
8B • Updated • 1
Tfloow/Llama-3.2-1B-adpq-4bit-sim
1B • Updated • 14
Tfloow/Llama-3.2-1B-adpq-4bit-sim-16workers
1B • Updated • 2
Tfloow/llama-3.1-8B-adpq-4bit-sim
8B • Updated • 2
datasets 0
None public yet