MiniCPM5-1B-mlx-fp16/README.md

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

license	language	library_name	pipeline_tag	tags	datasets	base_model
apache-2.0	en zh	transformers	text-generation	minicpm minicpm5 llama text-generation long-context tool-calling on-device edge-ai mlx mlx-my-repo	openbmb/Ultra-FineWeb openbmb/Ultra-FineWeb-L3 openbmb/UltraData-Math openbmb/UltraData-SFT-2605	openbmb/MiniCPM5-1B

usermma/MiniCPM5-1B-mlx-fp16

The Model usermma/MiniCPM5-1B-mlx-fp16 was converted to MLX format from openbmb/MiniCPM5-1B using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("usermma/MiniCPM5-1B-mlx-fp16")

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)