base_model, language, library_name, license, pipeline_tag, tags, arxiv

base_model	language	library_name	license	pipeline_tag	tags	arxiv
fdtn-ai/Foundation-Sec-8B-Reasoning	en	transformers	other	text-generation	security llama fdtn-sec mlx mlx-my-repo	2601.21051

gjdeboer/Foundation-Sec-8B-Reasoning-mlx-fp16

The Model gjdeboer/Foundation-Sec-8B-Reasoning-mlx-fp16 was converted to MLX format from fdtn-ai/Foundation-Sec-8B-Reasoning using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("gjdeboer/Foundation-Sec-8B-Reasoning-mlx-fp16")

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)