mlx-community/phi-2-super-4bit

This model was converted to MLX format from abacaj/phi-2-super. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/phi-2-super-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
3
Safetensors
Model size
546M params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.

Evaluation results

  • prompt_level_loose_acc on Instruction Following Eval
    LightEval
    0.272