jafermarq/finetuned_mlx

The Model jafermarq/finetuned_phi3_mlx was converted to MLX format from microsoft/Phi-3-mini-128k-instruct using mlx-lm version 0.15.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("jafermarq/finetuned_phi3_mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
8
Safetensors
Model size
3.82B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the HF Inference API does not support mlx models with pipeline type text-generation

Dataset used to train jafermarq/finetuned_phi3_mlx