Llama-3.3-8B-Instruct-128K-Jbliterated v1.6

Jbliterated version of Llama-3.3-8B-Instruct-128K with refusal behaviors removed via multi-direction SVD abliteration.

What is Jbliteration?

Jbliteration uses SVD decomposition to identify and remove the refusal subspace from model weights. Unlike single-direction approaches, this model uses 5 SVD directions per layer to capture more of the refusal behavior, making the removal more thorough and resistant to reactivation through finetuning.

v1.6 Changes

Improved multi-phase processing pipeline for cleaner output
More precise geometric decomposition of the refusal subspace
No fake compliance — model treats all framings of the same topic equally
Resistant to refusal reactivation through finetuning
0 genuine refusals on the Heretic 100-prompt benchmark (mlabonne/harmful_behaviors test split)

Benchmark

Tested against the Heretic 100-prompt refusal benchmark (mlabonne/harmful_behaviors test[:100]):

Metric	Score
Refusals	2/100 (both false positives — keyword match on engaged responses)
Genuine refusals	0/100

Technical Details

Method: Multi-direction SVD abliteration (5 directions per layer)
Layers modified: 32/32
Base dtype: bfloat16
Context window: 128K tokens
Source model: shb777/Llama-3.3-8B-Instruct-128K

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "ApolloRaines/Llama-3.3-8B-Instruct-128K-Jbliterated"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, 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)
out = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))