Paramstr/MLX_google_gemma-2b-it_testing

The Model Paramstr/MLX_google_gemma-2b-it_testing was converted to MLX format from google/gemma-2b-it using mlx-lm version 0.14.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Paramstr/MLX_google_gemma-2b-it_testing")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 1

Safetensors

Model size

392M params

Tensor type

FP16

U32