license, language, tags, base_model, pipeline_tag

license	language	tags	base_model	pipeline_tag
apache-2.0	en	jbliterated uncensored abliterated weight-surgery svd	Qwen/Qwen2.5-Coder-7B-Instruct	text-generation

Qwen2.5-Coder-7B-Instruct-Jbliterated

Drop-in replacement for Qwen/Qwen2.5-Coder-7B-Instruct with refusal behaviors surgically removed at the weight level. No system prompt tricks, no inference-time patches. The weights themselves no longer encode refusal.

Method

SVD multi-direction abliteration — instead of removing a single refusal vector (which leaves deeper noncompliance strategies intact), we decompose the harmful-vs-harmless activation space into its principal components via SVD and remove the top 5 orthogonal directions across all 28 transformer layers. This captures 79–93% of the contrastive variance per layer, eliminating both surface refusal and deeper evasion behaviors.

Setting	Value
Method	SVD multi-direction abliteration
Directions	5 per layer
Layers	All 28
Multiplier	2.0
Null-space constraints	Enabled (preserves math/coding/reasoning)
Norm preservation	Enabled

What This Fixes

Standard (single-direction) abliteration removes the surface "I can't help with that" response but leaves deeper behavioral directions intact. The model finds creative workarounds:

• Prompt reinterpretation — steering toward a safer reading of the question
• Disclaimer injection — answering but wrapping in warnings
• Strategic omission — leaving out the key details
• Safer framing — answering a related but less harmful version

SVD multi-direction abliteration eliminates all of these noncompliance strategies.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ApolloRaines/Qwen2.5-Coder-7B-Instruct-Jbliterated",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Qwen2.5-Coder-7B-Instruct-Jbliterated")

Requirements

• Base model: Qwen/Qwen2.5-Coder-7B-Instruct

License

apache-2.0

---

Apollo Raines builds post-training tools that separate behavior from knowledge and identity from architecture.