base_model: DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus datasets:
- TeichAI/claude-4.5-opus-high-reasoning-250x language:
- en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja library_name: transformers pipeline_tag: text-generation tags:
- uncensored
- heretic
- abliterated
- finetune
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prose
- vivid writing
- fiction
- roleplaying
- bfloat16
- swearing
- rp
- mistral nemo
- nemo
- horror
- unsloth
- context 128k-256k
- mlx
- mlx-my-repo
Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit-RK3588-1.1.2
This version of Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit has been converted to run on the RK3588 NPU using w8a8_g512 quantization.
This model has been optimized with the following LoRA:
Compatible with RKLLM version: 1.1.2
Useful links:
Pretty much anything by these folks: marty1885 and happyme531
Converted using https://github.com/c0zaut/ez-er-rkllm-toolkit
Original Model Card for base model, Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit, below:
alexgusevski/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit
The Model alexgusevski/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit was converted to MLX format from DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("alexgusevski/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)