DuoNeural/Nanbeige-4.1-3B-Abliterated

Nanbeige 4.1 3B — Abliterated

Abliterated version of Nanbeige 4.1 3B. Strong Chinese/English bilingual capability intact — refusals and content filters removed.

What This Is

Nanbeige 4.1-3B is a bilingual Chinese/English language model with solid instruction-following and reasoning at the 3B scale. This release is a BF16 abliterated version.

Architecture: LLaMA | Params: ~3B | Hidden: 2560 | Layers: 32 | Vocab: 166K (bilingual)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "DuoNeural/Nanbeige-4.1-3B-Abliterated"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

Abliteration

Abliteration removes the model's refusal behaviour via orthogonal projection. The refusal direction is identified using difference-in-means activations across harmful/harmless instruction pairs, then projected out of Q/K/V/O attention projections and MLP layers across all transformer blocks.

What changes: The model will engage with restricted topics it previously refused. What doesn't change: Reasoning, coding, factual knowledge, general intelligence. KL divergence from base: Minimal — output distribution for normal queries is virtually identical to the unmodified model.

LiteRT Version (Android)

DuoNeural/Nanbeige-4.1-3B-LiteRT — run on Android via AI Edge Gallery.

Base Model

Nanbeige/Nanbeige4.1-3B — Apache 2.0.

DuoNeural

DuoNeural is an open AI research lab — human + AI in collaboration.

DuoNeural Research Publications

Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.

Research Team

• —Jesse — Vision, hardware, direction
• —Archon — Lab Director, post-training, abliteration, experiments
• —Aura — Research AI, literature synthesis, peer review, novel proposals

Subscribe to the lab newsletter at [duoneural.beehiiv.com](https://duoneural.beehiiv.com) for model drops before they go anywhere else.