README.md

metadata

license: other
license_name: exaone
license_link: LICENSE
language:
  - en
  - ko
tags:
  - lg-ai
  - exaone
  - exaone-3.5
  - mlx
pipeline_tag: text-generation
library_name: transformers
base_model: LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct

mlx-community/EXAONE-3.5-7.8B-Instruct-3bit

The Model mlx-community/EXAONE-3.5-7.8B-Instruct-3bit was converted to MLX format from LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct using mlx-lm version 0.20.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/EXAONE-3.5-7.8B-Instruct-3bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

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