reader-lm-0.5b/README.md

pipeline_tag, language, inference, license, library_name, tags, base_model

pipeline_tag	language	inference	license	library_name	tags	base_model
text-generation	multilingual	false	cc-by-nc-4.0	transformers	mlx	jinaai/reader-lm-0.5b

mlx-community/reader-lm-0.5b

The Model mlx-community/reader-lm-0.5b was converted to MLX format from jinaai/reader-lm-0.5b using mlx-lm version 0.21.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/reader-lm-0.5b")

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)