Felipe Florez

moralogyengine

·

https://doi.org/10.5281/zenodo.19652794

AI & ML interests

AI alignment, axiomatic ethics, DPO training, moral reasoning, explainability

Organizations

None yet

spaces 3

Morlaogy Evaluation

Analyze moral dilemmas with formal ethical reasoning

Moralogy Engine

Generate custom alignment vectors and datasets for AI training

Desbicho

Axiomatic debugging engine.

models 10

moralogyengine/TinyLlama-1.1B-Chat-moralogy-dpo-v4

1B • Updated Apr 27 • 3

moralogyengine/TinyLlama-1.1B-Chat-moralogy-dpo-v3

Text Generation • 1B • Updated Apr 18

moralogyengine/TinyLlama-finetuned-with-LoRA

moralogyengine/results

moralogyengine/Mistral-7B-crystallized

moralogyengine/TinyLlama-1.1B-Chat-v1.0-crystallized

moralogyengine/TinyLlama-1.1B-Chat-v1.0-dpo

Text Generation • Updated Feb 25 • 2

moralogyengine/dpo_results

Updated Feb 25 • 9

moralogyengine/tiny_llama_heavy_v4

Text Generation • Updated Feb 23 • 3

moralogyengine/tiny_llama_trained

1B • Updated Feb 22 • 7

datasets 1

moralogyengine/moralogy-1200

Viewer • Updated Apr 27 • 1.2k • 10