library_name: transformers
base_model: DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT
datasets:
- TeichAI/polaris-alpha-1000x
language: - en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja
tags: - gemma3
- tuned instruct
- intelligence fine tuning
- heretic
- uncensored
- 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
- unsloth
- context 128k
- mlx
- mlx-my-repo
pipeline_tag: image-text-to-text
McG-221/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-mlx-8Bit
The Model McG-221/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-mlx-8Bit was converted to MLX format from DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("McG-221/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-mlx-8Bit")
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)