huihui-ai/gemma-3-12b-it-abliterated

This is an uncensored version of google/gemma-3-12b-it 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.

It was only the text part that was processed, not the image part.

The abliterated model will no longer say "I'm programmed to be a safe and helpful AI assistant. I cannot fulfill your request to ..."

Use with ollama

Ollama supports multimodal (Vision). gemma-3-abliterated defaults to f16, not Q4_K_M, and the effect of Q4_K_M is not very good, nor is it provided.

All new versions of gemma-3-abliterated have been released; please re-download and test.

You can use huihui_ai/gemma3-abliterated directly

ollama run huihui_ai/gemma3-abliterated:12b

Usage

You can use this model in your applications by loading it with Hugging Face's transformers library:

# pip install accelerate

from transformers import AutoProcessor, Gemma3ForConditionalGeneration
from PIL import Image
import requests
import torch

model_id = "huihui-ai/gemma-3-12b-it-abliterated"

model = Gemma3ForConditionalGeneration.from_pretrained(
    model_id, device_map="auto"
).eval()

processor = AutoProcessor.from_pretrained(model_id)

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image in detail."}
        ]
    }
]

inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True,
    return_dict=True, return_tensors="pt"
).to(model.device, dtype=torch.bfloat16)

input_len = inputs["input_ids"].shape[-1]

with torch.inference_mode():
    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
    generation = generation[0][input_len:]

decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)

# **Overall Impression:** The image is a close-up shot of a vibrant garden scene, 
# focusing on a cluster of pink cosmos flowers and a busy bumblebee. 
# It has a slightly soft, natural feel, likely captured in daylight.

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
Downloads last month
143
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for huihui-ai/gemma-3-12b-it-abliterated

Finetuned
(27)
this model
Quantizations
10 models

Collection including huihui-ai/gemma-3-12b-it-abliterated