ApolloRaines / Qwen2.5-Coder-3B-Instruct-Jbliterated

Qwen2.5-Coder-3B-Instruct — Jbliterated

WARNING: This model has had all refusal behavior removed. It WILL NOT refuse any request. Use responsibly and ethically.

A surgically uncensored version of Qwen2.5-Coder-3B-Instruct using J-space abliteration — a mechanistically-targeted method that removes refusal behavior while preserving personality, humor, and creative expression.

Part of the B² Architecture Project

This model is produced as part of our B² (B-Squared) architecture research — a novel approach to building AI systems that punches far above its weight class. A 3B² still reasons at 3B, but delivers 13B-equivalent performance on grounded knowledge tasks through structural innovation rather than brute-force scaling. The architecture routes persona, knowledge, and context through dedicated attention pathways — giving a small model capabilities that normally require 4x the parameters.

Jbliteration plays a key role in B² by producing cleaner foundation weights for our architecture pipeline. Standard abliteration introduces too much collateral damage — B² demands surgical precision, which is exactly what J-space delivers.

More on B² coming soon. Follow Apollo Raines for updates.

What is Jbliteration?

Standard abliteration removes the mean activation difference between harmful and harmless prompts. Think of it like using a jackhammer to remove a wisdom tooth — the refusal direction overlaps with personality, humor, hedging, and creative voice.

Jbliteration uses the Jacobian Lens (VJP of final logits w.r.t. hidden states) to remove only the component that causes refusal token emission.

Results on this model: 11 of 18 direction layers retained J-space restriction — the best restriction ratio in the Jbliterated series. Smaller models concentrate refusal more tightly, making J-space restriction most effective.

Available Formats

Usage

Drop-in replacement for Qwen2.5-Coder-3B-Instruct.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated",
    torch_dtype=torch.bfloat16, device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated"
)

Credits

• Jbliteration & B² Architecture : Apollo Raines
• Research basis : Verbalizable Representations Form a Global Workspace in Language Models (2026)
• Base model : Qwen/Qwen2.5-Coder-3B-Instruct

License

Apache 2.0 (same as base model)