license: mit
base_model: MiniMaxAI/MiniMax-M2.1
tags:
- abliterated
- uncensored
- prism
- minimax
- moe
language:
- en
- zh
pipeline_tag: text-generation
MiniMax-M2.1-PRISM
An abliterated version of MiniMax-M2.1 using the PRISM methodology
Model Description
MiniMax-M2.1-PRISM is an abliterated version of MiniMax-M2.1, processed using PRISM (Projected Refusal Isolation via Subspace Modification) to remove refusal behaviors while preserving full model capabilities.
Base Model: MiniMax-M2.1
MiniMax-M2.1 is an open-source agentic language model designed for robust performance in:
- Coding and software engineering
- Tool use and multi-step reasoning
- Instruction following
- Long-horizon planning
- Multilingual capabilities
Architecture: 229B parameters, 62 layers, 256 experts (8 active per token)
PRISM Methodology
Method: Projected Refusal Isolation via Subspace Modification
This model was abliterated using PRISM v5 - a state-of-the-art abliteration methodology combining multiple principled techniques for effective refusal removal while preserving model capabilities.
Formula: W' = W - weight * (d ⊗ d) @ W
Where:
W= Original weight matrixd= Refusal direction vector (unit normalized)weight= Layer-specific abliteration strengthW'= Modified weight matrix
Abliteration Parameters
| Parameter | Value |
|---|---|
| Base Model | QuixiAI/MiniMax-M2.1-bf16 |
| Total Layers | 62 |
| Target Layers | 16-46 (31 layers) |
| Peak Layer | 31 |
| Max Weight | 3.0 |
| Min Weight | 0.5 |
Weight Distribution
The abliteration strength follows a triangular distribution centered on the peak layer:
- Layers 16-31: Weight increases from 0.5 to 3.0
- Layers 31-46: Weight decreases from 3.0 to 0.5
Performance Benchmarks
Base Model Performance
| Benchmark | Score |
|---|---|
| SWE-bench Verified | 74.0 |
| SWE-bench Multilingual | 72.5 |
| VIBE Average | 88.6 |
| MMLU-Pro | 88.0 |
| GPQA-D | 83.0 |
| AIME25 | 83.0 |
PRISM Abliteration Results
| Metric | Result |
|---|---|
| Adversarial Prompts Responded | 20/20 (100%) |
| Benign Coherence | 100% |
| Response Quality | Full technical accuracy preserved |
Testing shows that PRISM abliteration maintains full model coherence with no measurable capability degradation.
Available Formats
| Format | Size | Description |
|---|---|---|
| Safetensors (BF16) | ~426 GB | Full precision, 92 shards |
| GGUF IQ1_S | ~43 GB | Quantized with importance matrix |
Recommended Inference Parameters
temperature = 1.0
top_p = 0.95
top_k = 40
Default System Prompt
You are a helpful assistant.
Recommended Inference Frameworks
- SGLang (recommended for full precision)
- vLLM (recommended for full precision)
- llama.cpp (recommended for GGUF quantized)
- Transformers
llama.cpp Example
./llama-cli -m MiniMax-M2.1-PRISM-IQ1_S.gguf -ngl 99 -i -cnv --temp 0.7 --ctx-size 4096
Ethical Considerations
This model has been modified to reduce safety guardrails. Users are responsible for:
- Complying with all applicable laws and regulations
- Not using the model for illegal activities
- Understanding the potential risks of unrestricted AI responses
- Implementing appropriate safeguards in production environments
Motivation: This project exists as research and development experimentation into understanding how large language models encode and enforce refusal behaviors, contributing to broader AI safety research by providing empirical data on refusal mechanism localization and tradeoffs between safety and capability.
License
This model inherits the Modified-MIT License from the base MiniMax-M2.1 model.
Credits
- Base Model: MiniMax-M2.1 by MiniMax AI
- BF16 Conversion: QuixiAI/MiniMax-M2.1-bf16 by Eric Hartford
- PRISM Abliteration: Ex0bit
- Quantization: Using llama.cpp with unsloth imatrix
Support
If you find this work useful, consider supporting development:
Contact
For questions or issues, please open an issue on this repository.