Downloads · 30 days
22
3% of all-time downloads
nightmedia/gemma-3-12b-it-vl-Polaris-Heretic-AIExpert-qx86-hi-mlx
gemma-3-12b-it-vl-Polaris-Heretic-AIExpert-qx86-hi-mlx is a image-text-to-text model from nightmedia. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
This is a nuslerp merge of: - GXMZU/gemma-3-12b-it-ai-expert - DavidAU/gemma-3-12b-it-vl-Polaris-Heretic-Uncensored-Thinking
Downloads · 30 days
22
3% of all-time downloads
All-time downloads
630
Public
Parameters
13.2B
23.4 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors12.4 GB · 100%
How the weights are stored.
U3212.8B · 97%
From the Hugging Face model README
This is a nuslerp merge of:
Brainwaves
arc arc/e boolq hswag obkqa piqa wino
qx86-hi 0.619,0.798,0.865,0.714,0.486,0.774,0.695
gemma-3-27b-it-heretic
q8 0.557,0.711,0.868,0.533,0.452,0.706,0.695
gemma-3-12b-it-heretic
qx86-hi 0.534,0.699,0.872,0.603,0.448,0.733,0.658
gemma-3-12b-it-vl-Polaris-Heretic-Uncensored-Thinking
qx86-hi 0.619,0.791,0.859,0.705,0.482,0.765,0.714
Perplexity:
polaris 14.909 ± 0.155
ai-expert 254.352 ± 6.333
AIExpert 12.412 ± 0.125
-G
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("gemma-3-12b-it-vl-Polaris-Heretic-AIExpert-qx86-hi-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)