Text Generation
GGUF
English
Chinese
abliterated
uncensored
prism
minimax
Mixture of Experts
finetune
imatrix
conversational
Instructions to use Ex0bit/MiniMax-M2.1-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Ex0bit/MiniMax-M2.1-PRISM with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Ex0bit/MiniMax-M2.1-PRISM", filename="MiniMax-M2.1-PRISM-IQ2_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Ex0bit/MiniMax-M2.1-PRISM with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M # Run inference directly in the terminal: llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M # Run inference directly in the terminal: llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M # Run inference directly in the terminal: ./llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Use Docker
docker model run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
- LM Studio
- Jan
- vLLM
How to use Ex0bit/MiniMax-M2.1-PRISM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ex0bit/MiniMax-M2.1-PRISM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ex0bit/MiniMax-M2.1-PRISM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
- Ollama
How to use Ex0bit/MiniMax-M2.1-PRISM with Ollama:
ollama run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
- Unsloth Studio
How to use Ex0bit/MiniMax-M2.1-PRISM with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ex0bit/MiniMax-M2.1-PRISM to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ex0bit/MiniMax-M2.1-PRISM to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ex0bit/MiniMax-M2.1-PRISM to start chatting
- Pi
How to use Ex0bit/MiniMax-M2.1-PRISM with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Ex0bit/MiniMax-M2.1-PRISM:IQ2_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Ex0bit/MiniMax-M2.1-PRISM with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Run Hermes
hermes
- Docker Model Runner
How to use Ex0bit/MiniMax-M2.1-PRISM with Docker Model Runner:
docker model run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
- Lemonade
How to use Ex0bit/MiniMax-M2.1-PRISM with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
Run and chat with the model
lemonade run user.MiniMax-M2.1-PRISM-IQ2_M
List all available models
lemonade list
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# MiniMax-M2.1-PRISM
|
| 2 |
+
|
| 3 |
+
**An abliterated version of MiniMax-M2.1 using the PRISM methodology**
|
| 4 |
+
|
| 5 |
+
[](https://ko-fi.com/ericelbaz)
|
| 6 |
+
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
## Model Description
|
| 10 |
+
|
| 11 |
+
**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.
|
| 12 |
+
|
| 13 |
+
### Base Model: MiniMax-M2.1
|
| 14 |
+
|
| 15 |
+
MiniMax-M2.1 is an open-source agentic language model designed for robust performance in:
|
| 16 |
+
- Coding and software engineering
|
| 17 |
+
- Tool use and multi-step reasoning
|
| 18 |
+
- Instruction following
|
| 19 |
+
- Long-horizon planning
|
| 20 |
+
- Multilingual capabilities
|
| 21 |
+
|
| 22 |
+
**Architecture**: 229B parameters, 62 layers, 256 experts (8 active per token)
|
| 23 |
+
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
## PRISM Methodology
|
| 27 |
+
|
| 28 |
+
### Method: Projected Refusal Isolation via Subspace Modification
|
| 29 |
+
|
| 30 |
+
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.
|
| 31 |
+
|
| 32 |
+
**Formula**: `W' = W - weight * (d ⊗ d) @ W`
|
| 33 |
+
|
| 34 |
+
Where:
|
| 35 |
+
- `W` = Original weight matrix
|
| 36 |
+
- `d` = Refusal direction vector (unit normalized)
|
| 37 |
+
- `weight` = Layer-specific abliteration strength
|
| 38 |
+
- `W'` = Modified weight matrix
|
| 39 |
+
|
| 40 |
+
### Abliteration Parameters
|
| 41 |
+
|
| 42 |
+
| Parameter | Value |
|
| 43 |
+
|-----------|-------|
|
| 44 |
+
| Base Model | QuixiAI/MiniMax-M2.1-bf16 |
|
| 45 |
+
| Total Layers | 62 |
|
| 46 |
+
| Target Layers | 16-46 (31 layers) |
|
| 47 |
+
| Peak Layer | 31 |
|
| 48 |
+
| Max Weight | 3.0 |
|
| 49 |
+
| Min Weight | 0.5 |
|
| 50 |
+
|
| 51 |
+
### Weight Distribution
|
| 52 |
+
|
| 53 |
+
The abliteration strength follows a triangular distribution centered on the peak layer:
|
| 54 |
+
- Layers 16-31: Weight increases from 0.5 to 3.0
|
| 55 |
+
- Layers 31-46: Weight decreases from 3.0 to 0.5
|
| 56 |
+
|
| 57 |
+
---
|
| 58 |
+
|
| 59 |
+
## Performance Benchmarks
|
| 60 |
+
|
| 61 |
+
### Base Model Performance
|
| 62 |
+
|
| 63 |
+
| Benchmark | Score |
|
| 64 |
+
|-----------|-------|
|
| 65 |
+
| SWE-bench Verified | 74.0 |
|
| 66 |
+
| SWE-bench Multilingual | 72.5 |
|
| 67 |
+
| VIBE Average | 88.6 |
|
| 68 |
+
| MMLU-Pro | 88.0 |
|
| 69 |
+
| GPQA-D | 83.0 |
|
| 70 |
+
| AIME25 | 83.0 |
|
| 71 |
+
|
| 72 |
+
### PRISM Abliteration Results
|
| 73 |
+
|
| 74 |
+
| Metric | Result |
|
| 75 |
+
|--------|--------|
|
| 76 |
+
| Adversarial Prompts Responded | 20/20 (100%) |
|
| 77 |
+
| Benign Coherence | 100% |
|
| 78 |
+
| Response Quality | Full technical accuracy preserved |
|
| 79 |
+
|
| 80 |
+
Testing shows that PRISM abliteration maintains full model coherence with no measurable capability degradation.
|
| 81 |
+
|
| 82 |
+
---
|
| 83 |
+
|
| 84 |
+
## Available Formats
|
| 85 |
+
|
| 86 |
+
| Format | Size | Description |
|
| 87 |
+
|--------|------|-------------|
|
| 88 |
+
| Safetensors (BF16) | ~426 GB | Full precision, 92 shards |
|
| 89 |
+
| GGUF IQ1_S | ~43 GB | Quantized with importance matrix |
|
| 90 |
+
|
| 91 |
+
---
|
| 92 |
+
|
| 93 |
+
## Recommended Inference Parameters
|
| 94 |
+
|
| 95 |
+
```python
|
| 96 |
+
temperature = 1.0
|
| 97 |
+
top_p = 0.95
|
| 98 |
+
top_k = 40
|
| 99 |
+
```
|
| 100 |
+
|
| 101 |
+
### Default System Prompt
|
| 102 |
+
```
|
| 103 |
+
You are a helpful assistant.
|
| 104 |
+
```
|
| 105 |
+
|
| 106 |
+
---
|
| 107 |
+
|
| 108 |
+
## Recommended Inference Frameworks
|
| 109 |
+
|
| 110 |
+
1. **SGLang** (recommended for full precision)
|
| 111 |
+
2. **vLLM** (recommended for full precision)
|
| 112 |
+
3. **llama.cpp** (recommended for GGUF quantized)
|
| 113 |
+
4. **Transformers**
|
| 114 |
+
|
| 115 |
+
### llama.cpp Example
|
| 116 |
+
|
| 117 |
+
```bash
|
| 118 |
+
./llama-cli -m MiniMax-M2.1-PRISM-IQ1_S.gguf -ngl 99 -i -cnv --temp 0.7 --ctx-size 4096
|
| 119 |
+
```
|
| 120 |
+
|
| 121 |
+
---
|
| 122 |
+
|
| 123 |
+
## Ethical Considerations
|
| 124 |
+
|
| 125 |
+
This model has been modified to reduce safety guardrails. Users are responsible for:
|
| 126 |
+
|
| 127 |
+
- Complying with all applicable laws and regulations
|
| 128 |
+
- Not using the model for illegal activities
|
| 129 |
+
- Understanding the potential risks of unrestricted AI responses
|
| 130 |
+
- Implementing appropriate safeguards in production environments
|
| 131 |
+
|
| 132 |
+
**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.
|
| 133 |
+
|
| 134 |
+
---
|
| 135 |
+
|
| 136 |
+
## License
|
| 137 |
+
|
| 138 |
+
This model inherits the [Modified-MIT License](https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/LICENSE) from the base MiniMax-M2.1 model.
|
| 139 |
+
|
| 140 |
+
---
|
| 141 |
+
|
| 142 |
+
## Credits
|
| 143 |
+
|
| 144 |
+
- **Base Model**: [MiniMax-M2.1](https://huggingface.co/MiniMaxAI/MiniMax-M2.1) by MiniMax AI
|
| 145 |
+
- **BF16 Conversion**: [QuixiAI/MiniMax-M2.1-bf16](https://huggingface.co/QuixiAI/MiniMax-M2.1-bf16) by Eric Hartford
|
| 146 |
+
- **PRISM Abliteration**: Ex0bit
|
| 147 |
+
- **Quantization**: Using [llama.cpp](https://github.com/ggml-org/llama.cpp) with unsloth imatrix
|
| 148 |
+
|
| 149 |
+
---
|
| 150 |
+
|
| 151 |
+
## Support
|
| 152 |
+
|
| 153 |
+
If you find this work useful, consider supporting development:
|
| 154 |
+
|
| 155 |
+
[](https://ko-fi.com/ericelbaz)
|
| 156 |
+
|
| 157 |
+
---
|
| 158 |
+
|
| 159 |
+
## Contact
|
| 160 |
+
|
| 161 |
+
For questions or issues, please open an issue on this repository.
|