metadata
base_model: fdtn-ai/Foundation-Sec-1.1-8B-Instruct
language:
- en
library_name: transformers
license: other
pipeline_tag: text-generation
tags:
- security
- llama
- mlx
- mlx-my-repo
gjdeboer/Foundation-Sec-1.1-8B-Instruct-mlx-4Bit
The Model gjdeboer/Foundation-Sec-1.1-8B-Instruct-mlx-4Bit was converted to MLX format from fdtn-ai/Foundation-Sec-1.1-8B-Instruct using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("gjdeboer/Foundation-Sec-1.1-8B-Instruct-mlx-4Bit")
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)