dheeraj1508/phi-2-4bit
The Model dheeraj1508/phi-2-4bit was converted to MLX format from microsoft/phi-2 using mlx-lm version 0.14.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("dheeraj1508/phi-2-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 8
Inference API (serverless) does not yet support mlx models for this pipeline type.