metadata
library_name: mlx
license: apache-2.0
pipeline_tag: text-generation
tags:
- looped-language-model
- reasoning
- recurrent-depth
- mlx
base_model: ByteDance/Ouro-2.6B
mlx-community/Ouro-2.6B-4bit
This model mlx-community/Ouro-2.6B-4bit was converted to MLX format from ByteDance/Ouro-2.6B using mlx-lm version 0.28.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Ouro-2.6B-4bit")
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)