helium-1-preview-2b/README.md

library_name, license, language, pipeline_tag, base_model, tags

library_name	license	language	pipeline_tag	base_model	tags
transformers	cc-by-4.0	en fr de it pt es	text-generation	kyutai/helium-1-preview-2b	mlx

mlx-community/helium-1-preview-2b

The Model mlx-community/helium-1-preview-2b was converted to MLX format from kyutai/helium-1-preview-2b 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/helium-1-preview-2b")

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)