base_model, base_model_relation, license, license_name, license_link, language, tags, pipeline_tag, library_name

base_model	base_model_relation	license	license_name	license_link	language	tags	pipeline_tag	library_name
LGAI-EXAONE/EXAONE-Deep-2.4B	finetune	other	exaone	LICENSE	en ko	lg-ai exaone exaone-deep mlx	text-generation	transformers

mlx-community/EXAONE-Deep-2.4B-bf16

The Model mlx-community/EXAONE-Deep-2.4B-bf16 was converted to MLX format from LGAI-EXAONE/EXAONE-Deep-2.4B using mlx-lm version 0.22.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/EXAONE-Deep-2.4B-bf16")

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)