Diego Calanzone
ddidacus
AI & ML interests
Reasoning, multi-objective RLHF, embodied agents, drug discovery.
Recent Activity
updated a collection 21 days ago
CERP updated a model 21 days ago
ddidacus/olmoe-base published a model 21 days ago
ddidacus/olmoe-baseOrganizations
models 30
ddidacus/olmoe-base
Text Generation • 7B • Updated • 440
ddidacus/olmoe-prompt-conditioned
Text Generation • Updated • 13
ddidacus/olmoe-melinoe
Text Generation • Updated • 12
ddidacus/olmoe-controller
Text Generation • Updated • 11
ddidacus/olmoe-cache-reward
Text Generation • Updated • 11
ddidacus/olmoe-sft
Text Generation • Updated • 16
ddidacus/phi-tiny-moe-melinoe
Text Generation • Updated • 13
ddidacus/phi-tiny-moe-controller
Text Generation • Updated • 14
ddidacus/phi-tiny-moe-prompt-conditioned
Text Generation • Updated • 11
ddidacus/phi-tiny-moe-cache-reward
Text Generation • Updated • 19
datasets 6
ddidacus/guard-glp-benign
Viewer • Updated • 4.12M • 361
ddidacus/nemotron-moe-exam
Viewer • Updated • 175k • 41
ddidacus/nuevamol-chembl-eval-set
Viewer • Updated • 1.7k • 7
ddidacus/guard-glp-data
Viewer • Updated • 12.8k • 20
ddidacus/harmeval-gcg-llama3-1b
Viewer • Updated • 550 • 11
ddidacus/SG-Bench-malicious-instructions
Viewer • Updated • 1.44k • 40 • 2