mlx-community/Sky-T1-32B-Preview

The Model mlx-community/Sky-T1-32B-Preview was converted to MLX format from NovaSky-AI/Sky-T1-32B-Preview using mlx-lm version 0.21.0 by Focused Logo

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Sky-T1-32B-Preview")

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)
Downloads last month
0
Safetensors
Model size
32.8B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mlx-community/Sky-T1-32B-Preview

Base model

Qwen/Qwen2.5-32B
Finetuned
(1)
this model

Datasets used to train mlx-community/Sky-T1-32B-Preview