OLMoE-1B-7B-0125-Instruct/README.md

license, language, pipeline_tag, base_model, library_name, datasets, tags

license	language	pipeline_tag	base_model	library_name	datasets	tags
apache-2.0	en	text-generation	allenai/OLMoE-1B-7B-0125-Instruct	transformers	allenai/RLVR-GSM	mlx

mlx-community/OLMoE-1B-7B-0125-Instruct

The Model mlx-community/OLMoE-1B-7B-0125-Instruct was converted to MLX format from allenai/OLMoE-1B-7B-0125-Instruct using mlx-lm version 0.21.6.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/OLMoE-1B-7B-0125-Instruct")

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)