introvoyz041/ERNIE-4.5-36B-A3B-Thinking-Brainstorm20x-mxfp4-mlx-mlx-4Bit

The Model introvoyz041/ERNIE-4.5-36B-A3B-Thinking-Brainstorm20x-mxfp4-mlx-mlx-4Bit was converted to MLX format from nightmedia/ERNIE-4.5-36B-A3B-Thinking-Brainstorm20x-mxfp4-mlx using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("introvoyz041/ERNIE-4.5-36B-A3B-Thinking-Brainstorm20x-mxfp4-mlx-mlx-4Bit")

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)