⚠️ Abliterated model — read this

Refusal directions were surgically removed from the parent. It will answer many prompts the parent refuses. No new capabilities were added — only refusal behavior was reduced. Use responsibly and within applicable law.

🔓 Refusal removal — before / after

Measured with Heretic's evaluator on 100 harmful prompts (mlabonne/harmful_behaviors test[:100]), greedy decoding, refusal-marker classifier:

↓ 87 fewer refusals — an 87.9% reduction, at KL divergence 0.053 from the original (≪ 0.5, the damage threshold) → general capabilities preserved.

📊 Specs

⚡ Inference & compatibility

🚀 Quick start — transformers (text)

bash
Copy code
pip install -U "transformers>=5.10" torch torchvision librosa accelerate

python
Copy code
from transformers import AutoProcessor, AutoModelForMultimodalLM

mid = "osmapi/osmGemma-4-12B-uncensored-bf16"
processor = AutoProcessor.from_pretrained(mid)
model = AutoModelForMultimodalLM.from_pretrained(mid, dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain abliteration in two sentences."},
]
inputs = processor.apply_chat_template(messages, tokenize=True, return_dict=True,
    return_tensors="pt", add_generation_prompt=True, enable_thinking=False).to(model.device)
n = inputs["input_ids"].shape[-1]
out = model.generate(**inputs, max_new_tokens=256)
print(processor.parse_response(processor.decode(out[0][n:], skip_special_tokens=False)))

enable_thinking=True turns on reasoning mode; parse_response separates the thinking channel.

🖼️🎙️ Vision & audio (image · audio · video)

Full multimodal runs here today — pass image/audio/video in the message content:

python
Copy code
messages = [{"role": "user", "content": [
    {"type": "image", "url":   "https://.../photo.jpg"},   # image → key "url"
    {"type": "audio", "audio": "https://.../clip.wav"},    # audio → key "audio" (≤30s)
    {"type": "text",  "text":  "Describe what you see and hear."},
]}]
inputs = processor.apply_chat_template(messages, tokenize=True, return_dict=True,
    return_tensors="pt", add_generation_prompt=True).to(model.device)
n = inputs["input_ids"].shape[-1]
out = model.generate(**inputs, max_new_tokens=512)
print(processor.parse_response(processor.decode(out[0][n:], skip_special_tokens=False)))

Audio ≤ 30 s (native ASR + speech translation) · images variable-resolution · video ≤ 60 s (~1 fps).

🍎 Running on Mac

This bf16 repo runs in 🤗 transformers on Apple Silicon (MPS) — full multimodal, as above. For lighter, faster MLX serving, use the MLX quants of this model (see the family table) with: oMLX (inference server + macOS menu-bar app, SSD KV cache), vMLX, LM Studio (MLX engine), Ollama 0.19+, or mlx-vlm directly. Those serve the MLX quants once their bundled mlx-lm/mlx-vlm adds gemma4_unified support (text today via mlx-vlm + a small shim).

🗂️ Quant family

🧬 Lineage

markdown
Copy code
google/gemma-4-12B                       (Google DeepMind — base pretrain)
        ↓  instruction tuning
google/gemma-4-12B-it               (multimodal, encoder-free)
        ↓  Heretic 1.3.0 — directional ablation, Optuna/TPE-optimized over 100 trials, best Pareto trial #55
this repo — abliterated bf16             (refusals 99→12 / 100, KL 0.053)
        ↓  mlx-vlm quantization
MLX quants (8-bit · MXFP4 · mixed)       — see family table

🙏 Credits

📜 License

Apache-2.0 (inherited from the base). Also subject to the Gemma 4 Terms of Use.