zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-09-01 12:49:50 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Length masking for batch inputs (#1173)

Browse Source 
* length masking

* add mask to mlx_lm model interface

* remove lengths

* fix test:

* comment + fix
This commit is contained in:
Alex Barron
2024-12-18 19:43:52 -08:00
committed by GitHub
parent db109184b7
commit d4ef909d4a
34 changed files with 191 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
llms/mlx_lm/models/olmo.py
View File

@@ -124,11 +124,13 @@ class Transformer(nn.Module):
def __call__(
self,
inputs: mx.array,
mask: mx.array = None,
cache=None,
):
h = self.wte(inputs)
mask = create_attention_mask(h, cache)
if mask is None:
mask = create_attention_mask(h, cache)
if cache is None:
cache = [None] * len(self.blocks)
@@ -152,9 +154,10 @@ class OlmoModel(nn.Module):
def __call__(
self,
inputs: mx.array,
mask: mx.array = None,
cache=None,
):
return self.transformer(inputs, cache)
return self.transformer(inputs, mask, cache)
class Model(nn.Module):
@@ -167,9 +170,10 @@ class Model(nn.Module):
def __call__(
self,
inputs: mx.array,
mask: mx.array = None,
cache=None,
):
return self.model(inputs, cache)
return self.model(inputs, mask, cache)
@property
def layers(self):