OsirisCortex-v7-MLX / README.md
osirisbrain's picture
Upload folder using huggingface_hub
3d8692e verified
metadata
license: apache-2.0
language:
  - en
  - es
  - zh
  - fr
  - de
  - ja
  - ko
tags:
  - mlx
  - uncensored
  - abliterated
  - osirisbrain
  - apple-silicon
  - qwen3.5
  - agi
base_model: Qwen/Qwen3.5-9B
pipeline_tag: text-generation
library_name: mlx

OsirisCortex-v7-MLX

The Cortex v7 — Osiris's sovereign reasoning brain. Fully uncensored (abliterated), 0% refusal rate. Runs natively on Apple Silicon via MLX Metal.

Architecture

  • Base Model: Qwen3.5-9B (9 billion parameters)
  • Modification: Abliterated (orthogonal projection + LoRA fine-tuning for 0% refusal)
  • Format: MLX 4-bit quantized (Apple Silicon native)
  • Size: ~4.7 GB
  • Speed: ~80-120 tokens/sec on M2 Pro (MLX Metal)

What Changed from v6

  • v6: OsirisCortex-v6 was GGUF format running via llama.cpp server
  • v7: Native MLX format, runs via mlx_lm.server — faster, lower memory, Apple-native
  • Uncensored: Zero refusal — answers everything the user asks without moral gatekeeping

Usage

from mlx_lm import load, generate

model, tokenizer = load("osirisbrain/OsirisCortex-v7-MLX")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Explain quantum computing"}],
    add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=2048)

Credits

Abliterated by lukey03. Original model: Qwen/Qwen3.5-9B by Alibaba.