ChrisCoffey/Qwen2-0.5B-test
The Model ChrisCoffey/Qwen2-0.5B-test was converted to MLX format from mlx-community/Qwen2-0.5B using mlx-lm version 0.15.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ChrisCoffey/Qwen2-0.5B-test")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 29
Model size
0.5B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized