mlx-community/phi-1_5
The Model mlx-community/phi-1_5 was converted to MLX format from microsoft/phi-1_5 using mlx-lm version 0.16.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/phi-1_5")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 40
Model size
1B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/phi-1_5") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True)