Diego Calanzone's picture

2

Diego Calanzone

ddidacus

·

https://halixness.github.io

AI & ML interests

Reasoning, multi-objective RLHF, embodied agents, drug discovery.

Recent Activity

liked a model 1 day ago

unsloth/Llama-3.2-1B

liked a dataset 18 days ago

rbiswasfc/ruler

updated a model 19 days ago

ddidacus/RS-mol-llama-1b

View all activity

Organizations

ddidacus's activity

liked a model 1 day ago

unsloth/Llama-3.2-1B

Text Generation • Updated Jan 22 • 92.3k • • 32

liked a dataset 18 days ago

rbiswasfc/ruler

Viewer • Updated Jun 27, 2024 • 4k • 326 • 3

updated 4 models 19 days ago

ddidacus/RS-mol-llama-1b

Text Generation • Updated 19 days ago • 48

ddidacus/RiC-mol-llama-1b

Text Generation • Updated 19 days ago • 40

ddidacus/MORLHF-mol-llama-1b

Text Generation • Updated 19 days ago • 31

ddidacus/Mol-MoE-6x1b

Text Generation • Updated 19 days ago • 42

updated a collection about 2 months ago

Molecule Generation Models

Models involved in the analysis from "Training Preference-Guided Routers for Molecule Generation". • 4 items • Updated Feb 7

published 4 models about 2 months ago

ddidacus/MORLHF-mol-llama-1b

Text Generation • Updated 19 days ago • 31

ddidacus/RS-mol-llama-1b

Text Generation • Updated 19 days ago • 48

ddidacus/RiC-mol-llama-1b

Text Generation • Updated 19 days ago • 40

ddidacus/Mol-MoE-6x1b

Text Generation • Updated 19 days ago • 42