license: gemma
library_name: mlx
pipeline_tag: text-generation
base_model: grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated
tags:
- mlx
CallMcMargin/gemma-3-12b-it-norm-preserved-biprojected-abliterated-mlx-bf16-affine-qgroup32-q8
This model CallMcMargin/gemma-3-12b-it-norm-preserved-biprojected-abliterated-mlx-bf16-affine-qgroup32-q8 was
converted to MLX format from grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated
using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("CallMcMargin/gemma-3-12b-it-norm-preserved-biprojected-abliterated-mlx-bf16-affine-qgroup32-q8")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)