mrs83's picture
Update README.md
3005b60 verified
metadata
license: apache-2.0
library_name: mlx
tags:
  - language
  - granite-4.0
  - mlx
base_model:
  - ethicalabs/granite-4.0-1b-MLX
  - ethicalabs/kurtis-e1-granite-4.0-1b-adapter-MLX
pipeline_tag: text-generation
datasets:
  - ethicalabs/Kurtis-E1-SFT
  - ethicalabs/kurtis-v2-sft-mix-tiny
base_model_relation: merge

ethicalabs/kurtis-e1-granite-4.0-1b-MLX

This model ethicalabs/kurtis-e1-granite-4.0-1b-MLX was converted to MLX format from ethicalabs/granite-4.0-1b-MLX using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("ethicalabs/kurtis-e1-granite-4.0-1b-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
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)