Angelos Katharopoulos
fd836d891b
Hashable dtype and mlx.core prefixed repr ( #89 )
...
* Make dtype hashable
* Add mlx.core prefix to our dtypes' repr
* Update the dtype test
2023-12-09 09:35:28 -08:00
Awni Hannun
2520dbcf0a
add losses to the docs, fix black failur ( #92 )
2023-12-09 06:06:52 -08:00
Abe Leininger
430bfb4944
Adds Nesterov momentum to SGD ( #87 )
2023-12-08 23:23:36 -08:00
ShiJZ
08d51bf232
Make it easier to test new optimizers implemented: no need to change test file manually ( #90 )
...
* add helper function get_all_optimizers() in test_optimizers.py
* remove unused import
2023-12-08 21:39:08 -08:00
Kai Ma
cb9e585b8e
Style fix for loss functions ( #91 )
...
* MLE and L1 loss functions
* logsoftmax change and tests
* subtract max logit for numerical stability
* l1 name change
* cross entropy reduction + unit tests
* docstrings
* l1 test name change
* old loss impl + default none
* style
2023-12-08 21:11:56 -08:00
Kai Ma
641d316484
MLE and L1 loss functions ( #88 )
...
* MLE and L1 loss functions
* logsoftmax change and tests
* subtract max logit for numerical stability
* l1 name change
* cross entropy reduction + unit tests
* docstrings
* l1 test name change
* old loss impl + default none
2023-12-08 20:21:37 -08:00
Angelos Katharopoulos
2b714714e1
Add the remainder op ( #85 )
...
* Add remainder in the C++ backend
* Add the python binding and test
2023-12-08 15:08:52 -08:00
Joe Barrow
69a24e6a1e
AdamW implementation ( #72 )
...
* AdamW implementation without bias correction
* Makes use of the underlying Adam implementation
2023-12-08 14:45:34 -08:00
Zach Schillaci
5b9be57ac3
Add isort pre-commit and run ( #68 )
2023-12-08 11:31:47 -08:00
Angelos Katharopoulos
209404239b
Fix the accelerate dispatch for the power op ( #70 )
...
- The exponent and base were swapped because accelerate is using
exponent-base instead of base-exponent
- Fix also the test for binary ops as it was testing op(x, x) which
couldn't catch ordering errors like that
2023-12-08 10:58:03 -08:00
Zach Schillaci
d11d77e581
Spelling fixes in transformer.py ( #59 )
2023-12-07 13:32:09 -08:00
rushyam
2e126aeb7e
Feature Addition: Encoder-Decoder Transformer Architecture ( #50 )
...
* Implemented decoder-transformer-layer, decoder-transformer and introduce encoder-decoder transformer
* added relu layer
* add src, tgt, memory mask
---------
Co-authored-by: rushyam <rushyam@rushyams-MacBook-Air.local>
2023-12-07 07:37:36 -08:00
Jagrit Digani
2440fe0124
NPY loading segfault bug ( #34 )
...
* Fixed Gil semantics in loading and saving from python file streams
2023-12-06 12:03:47 -08:00
Markus Enzweiler
2ffaee0c0d
Updated default argument for stride to 1 in Conv2d() in the docstring ( #22 )
2023-12-06 07:17:58 -08:00
Jagrit Digani
d518b3b6a5
Fix gemv broadcasting bug ( #6 )
...
* Fix broadcasting bug in gemv
* Add relevant tests in test_blas.py
2023-12-05 14:15:43 -08:00
Angelos Katharopoulos
7546fdb100
Add CircleCI configuration ( #4 )
...
* Add CircleCI configuration
2023-12-04 16:04:11 -08:00
Awni Hannun
db487e6b1a
format
2023-11-30 11:50:50 -08:00
Awni Hannun
46a39e5b1f
copyright + ack
2023-11-30 11:12:53 -08:00
Jagrit Digani
e6306cfee9
jagrit's commit files
2023-11-29 10:52:08 -08:00
Angelos Katharopoulos
d1f86272a2
angelos's commit files
2023-11-29 10:42:59 -08:00
Awni Hannun
8ca7f9e8e9
awni's commit files
2023-11-29 10:30:41 -08:00
