mlx-community/Qwen2-72B-Instruct-unquantized

The Model mlx-community/Qwen2-72B-Instruct-unquantized was converted to MLX format from Qwen/Qwen2-72B-Instruct using mlx-lm version 0.14.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2-72B-Instruct-unquantized")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 13

Safetensors

Model size

72.7B params

Tensor type

FP16