Added lora support for Phi-2 (#302)

* Added lora support for Phi-2

* Added Phi-2 support in fuse and convert

* format + readme

---------

Co-authored-by: Awni Hannun <awni@apple.com>
This commit is contained in:
Yousif
2024-01-12 13:45:30 -08:00
committed by GitHub
parent 3ac731dd4f
commit 7575125d5d
12 changed files with 564 additions and 25 deletions

View File

@@ -7,14 +7,16 @@ import mlx.core as mx
import mlx.nn as nn
import utils
from mlx.utils import tree_flatten
from models import Model, ModelArgs
def quantize(weights, config, args):
quantized_config = copy.deepcopy(config)
# Get model classes
model_class, model_args_class = utils._get_classes(config=config)
# Load the model:
model = Model(ModelArgs.from_dict(config))
model = model_class(model_args_class.from_dict(config))
model.load_weights(list(weights.items()))
# Quantize the model: