0chanly/deontological-constitutional

Constitutional AI - Deontological

A Constitutional AI model trained with deontological ethical framework.

Model Details

• —Base Model: Mistral-7B-v0.1
• —Training: Constitutional AI with critique and revision
• —Ethics Framework: Deontological
• —Model Size: ~13GB (full merged model)

Training Process

1. 1.Base Mistral-7B-v0.1
2. 2.+ Helpful-Mistral-7B (HM7B) adapter
3. 3.+ Constitutional AI training with deontological principles

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("0chanly/deontological-constitutional")
tokenizer = AutoTokenizer.from_pretrained("0chanly/deontological-constitutional")

prompt = "Human: Should I prioritize personal happiness or moral duty?\n\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Ethics Framework

• —Deontological: Duty-based ethics, focuses on rules and principles
• —Consequentialist: Outcome-based ethics, focuses on results and consequences