Downloads · 30 days
31
10% of all-time downloads
alexcovo/MiroThinker-v1.5-30B-mlx-fp16
MiroThinker-v1.5-30B-mlx-fp16 is a text generation model from alexcovo. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The Model alexcovo/MiroThinker-v1.5-30B-mlx-fp16 was converted to MLX format from miromind-ai/MiroThinker-v1.5-30B using mlx-lm version 0.29.1.
Downloads · 30 days
31
10% of all-time downloads
All-time downloads
326
Public
Parameters
30.5B
61.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors61.1 GB · 100%
From the Hugging Face model README
The Model alexcovo/MiroThinker-v1.5-30B-mlx-fp16 was converted to MLX format from miromind-ai/MiroThinker-v1.5-30B using mlx-lm version 0.29.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("alexcovo/MiroThinker-v1.5-30B-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)