lmbelo/Phi-3-mini-4k-Function-Calling
The Model lmbelo/Phi-3-mini-4k-Function-Calling was converted to MLX format from lmbelo/Phi-3-mini-4k-instruct using mlx-lm version 0.13.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("lmbelo/Phi-3-mini-4k-Function-Calling")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 2
Model size
4B params
Tensor type
BF16
·
Hardware compatibility
Log In
to add your hardware
Quantized