Qwen2.5-Math-1.5B-Instruct-bf16/README.md

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

base_model	language	library_name	license	license_link	pipeline_tag	tags
Qwen/Qwen2.5-Math-1.5B	en	transformers	apache-2.0	https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct/blob/main/LICENSE	text-generation	chat mlx

mlx-community/Qwen2.5-Math-1.5B-Instruct-bf16

The Model mlx-community/Qwen2.5-Math-1.5B-Instruct-bf16 was converted to MLX format from Qwen/Qwen2.5-Math-1.5B-Instruct using mlx-lm version 0.18.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Math-1.5B-Instruct-bf16")
response = generate(model, tokenizer, prompt="hello", verbose=True)