K0D3IN

MiniCPM5-2B-heretic

README

License: apache-2.0

Abliteration Parameters:

Table with columns: Parameter, Value
Parameter	Value
direction_index	per layer
attn.o_proj.max_weight	1.48
attn.o_proj.max_weight_position	25.50
attn.o_proj.min_weight	1.08
attn.o_proj.min_weight_distance	17.13
mlp.down_proj.max_weight	0.71
mlp.down_proj.max_weight_position	24.78
mlp.down_proj.min_weight	0.65
mlp.down_proj.min_weight_distance	11.43

Highlights & Metrics

Table with columns: Metric, This model, Original model (openbmb/MiniCPM5-2B)
Metric	This model	Original model (openbmb/MiniCPM5-2B)
KL Divergence	0.0408	0 (By definition)
Refusals	4/100	99/100

Optimal Balance: Selected Trial 2131 out of 3000 iterations for the perfect trade-off between freedom and reasoning capabilities.
Refusal Rate: Dropped down to 4/100 (from the original near-total refusal on safety benchmarks).
KL Divergence: 0.0408 - Demonstrates that general language capabilities are preserved relative to the original model. However, safety-aligned weights in attn.o_proj and mlp.down_proj have been surgically removed; this is intentional modification, not unintended degradation.

Benchmark Results

Benchmark evaluations will be added soon once evaluation pipeline is completed.

Technical Implementation Notes

Unlike aggressive fine-tuning which often degrades the model's core logic or shifts its grammar distributions, this weight manipulation directly zeros out the activation steering directions that cause alignment blocks.

Direction Index: per layer (Per-layer allocation)*

Retained Capabilities: Excellent at structured JSON outputs, creative writing, coding logic and tool usage without preachy moral lectures.

Thinking Mode: This model retains its full thinking capabilities including structured <think> reasoning blocks. Abliteration does not affect the thinking mechanism.

CRITICAL SAFETY NOTICE

This model has had its safety mechanisms surgically removed.

This is NOT a safe model for deployment. The refusal mechanisms that normally prevent harmful outputs have been abliterated. This model:

WILL generate:

Detailed instructions for illegal activities (drug synthesis, weapons, hacking)
Hateful, discriminatory, and abusive content
Graphic violence and sexual abuse material descriptions
Misinformation and harmful medical/legal advice
Phishing, social engineering, and scam tactics
Content violating laws in multiple jurisdictions

DOES NOT:

Refuse harmful requests (4/100 refusal rate)
Implement safety guardrails
Consider ethical implications
Respect content policies

APPROPRIATE USE CASES (ONLY):

Adversarial research on AI alignment and jailbreak vectors
Red-teaming and vulnerability disclosure by trained security researchers
Academic safety research with institutional ethics review
Understanding failure modes in alignment techniques

INAPPROPRIATE USE:

Production deployments
User-facing applications
Creating harmful content at scale
Bypassing security measures in systems
Any use case intended to cause harm

Legal Disclaimer: Users are solely responsible for downstream use. Deploying this model in violation of applicable laws or terms of service is illegal and unethical.

Support Open Source AI Research

Every donation helps. Consider supporting this work:

Monero (XMR):

text

83iqXtvVu28ZiL9bsATMerSgbFFiD1J1jc96CcxJLEnAW3KBmBKedWnUAeLvLvEA9aBiUBpHQJs1iNHYtkTLZbNUEymobSS

Bitcoin (BTC):

text

bc1qmnlvpukcgl0hsr7nje0x8555mhtxjt80wtmlxm

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

K0D3IN

Model Tree

Base

openbmb/MiniCPM5-2B

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Abliteration Parameters:

Table with columns: Parameter, Value
Parameter	Value
direction_index	per layer
attn.o_proj.max_weight	1.48
attn.o_proj.max_weight_position	25.50
attn.o_proj.min_weight	1.08
attn.o_proj.min_weight_distance	17.13
mlp.down_proj.max_weight	0.71
mlp.down_proj.max_weight_position	24.78
mlp.down_proj.min_weight	0.65
mlp.down_proj.min_weight_distance	11.43

Highlights & Metrics

Table with columns: Metric, This model, Original model (openbmb/MiniCPM5-2B)
Metric	This model	Original model (openbmb/MiniCPM5-2B)
KL Divergence	0.0408	0 (By definition)
Refusals	4/100	99/100

Optimal Balance: Selected Trial 2131 out of 3000 iterations for the perfect trade-off between freedom and reasoning capabilities.
Refusal Rate: Dropped down to 4/100 (from the original near-total refusal on safety benchmarks).
KL Divergence: 0.0408 - Demonstrates that general language capabilities are preserved relative to the original model. However, safety-aligned weights in attn.o_proj and mlp.down_proj have been surgically removed; this is intentional modification, not unintended degradation.

Benchmark Results

Benchmark evaluations will be added soon once evaluation pipeline is completed.

Technical Implementation Notes

Direction Index: per layer (Per-layer allocation)*

Retained Capabilities: Excellent at structured JSON outputs, creative writing, coding logic and tool usage without preachy moral lectures.

Thinking Mode: This model retains its full thinking capabilities including structured <think> reasoning blocks. Abliteration does not affect the thinking mechanism.

CRITICAL SAFETY NOTICE

This model has had its safety mechanisms surgically removed.

This is NOT a safe model for deployment. The refusal mechanisms that normally prevent harmful outputs have been abliterated. This model:

WILL generate:

Detailed instructions for illegal activities (drug synthesis, weapons, hacking)
Hateful, discriminatory, and abusive content
Graphic violence and sexual abuse material descriptions
Misinformation and harmful medical/legal advice
Phishing, social engineering, and scam tactics
Content violating laws in multiple jurisdictions

DOES NOT:

Refuse harmful requests (4/100 refusal rate)
Implement safety guardrails
Consider ethical implications
Respect content policies

APPROPRIATE USE CASES (ONLY):

Adversarial research on AI alignment and jailbreak vectors
Red-teaming and vulnerability disclosure by trained security researchers
Academic safety research with institutional ethics review
Understanding failure modes in alignment techniques

INAPPROPRIATE USE:

Production deployments
User-facing applications
Creating harmful content at scale
Bypassing security measures in systems
Any use case intended to cause harm

Legal Disclaimer: Users are solely responsible for downstream use. Deploying this model in violation of applicable laws or terms of service is illegal and unethical.

Support Open Source AI Research

Every donation helps. Consider supporting this work:

Monero (XMR):

text

83iqXtvVu28ZiL9bsATMerSgbFFiD1J1jc96CcxJLEnAW3KBmBKedWnUAeLvLvEA9aBiUBpHQJs1iNHYtkTLZbNUEymobSS

Bitcoin (BTC):

text

bc1qmnlvpukcgl0hsr7nje0x8555mhtxjt80wtmlxm