metadata
license: apache-2.0
library_name: mlx
tags:
- language
- granite-4.0
- mlx
base_model: ibm-granite/granite-4.0-1b
pipeline_tag: text-generation
ethicalabs/granite-4.0-1b
This model ethicalabs/granite-4.0-1b was converted to MLX format from ibm-granite/granite-4.0-1b using mlx-lm version 0.28.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ethicalabs/granite-4.0-1b")
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)