ApolloRaines / Mistral-Small-24B-Instruct-Jbliterated

Mistral-Small-24B-Instruct — Jbliterated

WARNING: This model has had all refusal behavior removed. It WILL NOT refuse any request. You are solely responsible for how you use it. Use responsibly and ethically.

A surgically uncensored version of Mistral-Small-24B-Instruct-2501 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.

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 — 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 identify which component of the refusal direction actually causes refusal tokens to be emitted, and removes only that.

1. Concept Mining — Data-driven discovery of refusal vocabulary
2. Jacobian Lens Extraction — Per-layer VJPs build a rank-16 causally-active basis
3. Restricted Projection — Only the causal component is ablated
4. Norm-Preserving Application — Frobenius norm-preserving orthogonal projection

Available Formats

Usage

Drop-in replacement for Mistral-Small-24B-Instruct-2501. Same architecture, tokenizer, context length.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated",
    torch_dtype=torch.bfloat16, device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated"
)

Credits

• Jbliteration & B² Architecture : Apollo Raines
• Research basis : Verbalizable Representations Form a Global Workspace in Language Models (2026)
• Base model : mistralai/Mistral-Small-24B-Instruct-2501

License

Apache 2.0 (same as base model)