verbiate/Marco-o1-Q8-mlx

The Model verbiate/Marco-o1-Q8-mlx was converted to MLX format from AIDC-AI/Marco-o1 using mlx-lm version 0.19.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("verbiate/Marco-o1-Q8-mlx")

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)
Downloads last month
36
Safetensors
Model size
2.14B params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for verbiate/Marco-o1-Q8-mlx

Base model

AIDC-AI/Marco-o1
Quantized
(40)
this model