README.md

metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
library_name: mlx
base_model: ibm-granite/granite-guardian-3.1-2b
tags:
  - mlx

exoplanet/ibm-granite-guardian-3.1-2b-4bit

This model exoplanet/ibm-granite-guardian-3.1-2b-4bit was converted to MLX format from ibm-granite/granite-guardian-3.1-2b using mlx-lm version 0.26.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("exoplanet/ibm-granite-guardian-3.1-2b-4bit")

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)