Diego Calanzone
ddidacus
AI & ML interests
Reasoning, multi-objective RLHF, embodied agents, drug discovery.
Organizations
models 30
ddidacus/olmoe-base
Text Generation • 7B • Updated • 58
ddidacus/olmoe-prompt-conditioned
Text Generation • Updated • 5
ddidacus/olmoe-melinoe
Text Generation • Updated • 6
ddidacus/olmoe-controller
Text Generation • Updated • 5
ddidacus/olmoe-cache-reward
Text Generation • Updated • 5
ddidacus/olmoe-sft
Text Generation • Updated • 7
ddidacus/phi-tiny-moe-melinoe
Text Generation • Updated • 7
ddidacus/phi-tiny-moe-controller
Text Generation • Updated • 10
ddidacus/phi-tiny-moe-prompt-conditioned
Text Generation • Updated • 7
ddidacus/phi-tiny-moe-cache-reward
Text Generation • Updated • 7
datasets 6
ddidacus/guard-glp-benign
Viewer • Updated • 4.12M • 50
ddidacus/nemotron-moe-exam
Viewer • Updated • 175k • 3
ddidacus/nuevamol-chembl-eval-set
Viewer • Updated • 1.7k • 6
ddidacus/guard-glp-data
Viewer • Updated • 12.8k • 26
ddidacus/harmeval-gcg-llama3-1b
Viewer • Updated • 550 • 9
ddidacus/SG-Bench-malicious-instructions
Viewer • Updated • 1.44k • 25 • 2