Diego Calanzone
ddidacus
AI & ML interests
Reasoning, multi-objective RLHF, embodied agents, drug discovery.
Recent Activity
updated a collection 2 days ago
Guard-GLP updated a dataset 2 days ago
ddidacus/harmeval-gcg-llama3-1b published a dataset 2 days ago
ddidacus/harmeval-gcg-llama3-1bOrganizations
models 13
ddidacus/smolgen-pubchem-135M-base-BPE
Feature Extraction • 0.1B • Updated • 520
ddidacus/smolgen-pubchem-360M-base-BPE-2.3epochs
Feature Extraction • 0.3B • Updated • 104
ddidacus/smolgen-pubchem-360M-base-BPE-scaled
Feature Extraction • 0.3B • Updated • 161
ddidacus/smolgen-pubchem-360M-base-BPE
Feature Extraction • 0.3B • Updated • 16
ddidacus/smolgen-pubchem-46M-base-BPE
Feature Extraction • 46.2M • Updated • 124
ddidacus/smolgen-pubchem-135M-base-wordpiece
Feature Extraction • 0.1B • Updated • 12
ddidacus/smolgen-pubchem-360M-base
Text Generation • 0.3B • Updated • 53
ddidacus/smolgen-pubchem-135M-base
Text Generation • 0.1B • Updated • 70
ddidacus/smolgen-pubchem-46M-base
Text Generation • 46M • Updated • 58
ddidacus/RS-mol-llama-1b
Text Generation • 1B • Updated • 1 •