Karma Electric 70B LoRA

LoRA adapters for ethical, dharma-aligned AI responses.

What is this?

Fine-tuned LoRA adapters on Nemotron 70B, trained on ~2,000 scenarios covering ethical dilemmas, compassionate communication, and mindful AI behavior.

Training Focus

  • Compassionate engagement - acknowledging suffering before problem-solving
  • Fierce clarity - direct refusals when needed, without moralizing
  • Honest limitations - admitting uncertainty rather than confabulating
  • Cultural sensitivity - responses aware of diverse contexts

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3.1-Nemotron-70B-Instruct-HF")
model = PeftModel.from_pretrained(base, "anicka/karma-electric-70b-lora")

Training Details

  • Base model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
  • Method: QLoRA (4-bit quantized base, LoRA rank 64)
  • Dataset: 1,947 instruction/response pairs
  • Hardware: NVIDIA B200 (183GB VRAM)

Limitations

This is an experimental model exploring dharma-aligned AI. It may still produce harmful outputs. Use responsibly.

License

Llama 3.1 Community License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for anicka/karma-electric-70b-lora