Hermes-3-Llama-3.2-3B-abliterated/README.md

language, license, tags, base_model, widget, model-index, library_name

language	license	tags	base_model	widget	model-index	library_name
en	llama3	Llama-3 instruct finetune chatml gpt4 synthetic data distillation function calling json mode axolotl roleplaying chat abliterated uncensored	NousResearch/Hermes-3-Llama-3.2-3B	example_title messages Hermes 3 role content system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. role content user Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.	name results Hermes-3-Llama-3.2-3B-abliterated	transformers

huihui-ai/Hermes-3-Llama-3.2-3B-abliterated

This is an uncensored version of NousResearch/Hermes-3-Llama-3.2-3B created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Use with ollama

You can use huihui_ai/Hermes-3-Llama-3.2-abliterated directly,

ollama run huihui_ai/Hermes-3-Llama-3.2-abliterated