tiny-recursive-model 0.0.4__py3-none-any.whl → 0.0.6__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -86,7 +86,7 @@ class Trainer(Module):
86
86
 
87
87
  self.optim = optim_klass(
88
88
  model.parameters(),
89
- lr = learning_rate,
89
+ lr = learning_rate / (batch_size * max_recurrent_steps),
90
90
  weight_decay = weight_decay
91
91
  )
92
92
 
@@ -220,4 +220,4 @@ class TinyRecursiveModel(Module):
220
220
 
221
221
  losses = (loss, halt_loss)
222
222
 
223
- return (total_loss.mean(), losses, *return_package)
223
+ return (total_loss.sum(), losses, *return_package)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tiny-recursive-model
3
- Version: 0.0.4
3
+ Version: 0.0.6
4
4
  Summary: Tiny Recursive Model
5
5
  Project-URL: Homepage, https://pypi.org/project/tiny-recursive-model/
6
6
  Project-URL: Repository, https://github.com/lucidrains/tiny-recursive-model
@@ -38,7 +38,7 @@ Requires-Dist: accelerate
38
38
  Requires-Dist: einops>=0.8.1
39
39
  Requires-Dist: ema-pytorch
40
40
  Requires-Dist: torch>=2.4
41
- Requires-Dist: x-transformers
41
+ Requires-Dist: x-transformers>=2.8.4
42
42
  Provides-Extra: examples
43
43
  Provides-Extra: test
44
44
  Requires-Dist: pytest; extra == 'test'
@@ -47,7 +47,7 @@ Description-Content-Type: text/markdown
47
47
 
48
48
  <img width="300" alt="trm-fig1" src="https://github.com/user-attachments/assets/950db79e-5f9c-4fec-a4e4-7b9355b39ce8" />
49
49
 
50
- ## Tiny Recursive Model (TRM) wip
50
+ ## Tiny Recursive Model (TRM)
51
51
 
52
52
  Implementation of [Tiny Recursive Model](https://arxiv.org/abs/2510.04871) (TRM), improvement to [HRM](https://github.com/lucidrains/hrm) from Sapient AI, by [Alexia Jolicoeur-Martineau](https://ajolicoeur.wordpress.com/about/)
53
53
 
@@ -0,0 +1,8 @@
1
+ tiny_recursive_model/__init__.py,sha256=zuMcrofGu7DnvJM2Mb-O3tqBJF5q8L-8X8OTmq7_o5w,189
2
+ tiny_recursive_model/mlp_mixer_1d.py,sha256=6ivDK9dgHdVl1axg2ayifJ7H5QI3hXptHnb6lfNrno0,1398
3
+ tiny_recursive_model/trainer.py,sha256=tWDILDnNpMeGl-4oEMcjIxtjSxLQle-KOSWOp3FX1eo,4255
4
+ tiny_recursive_model/trm.py,sha256=3ppupakxFtPIkdjeof4J-4k2piz5SvL4ojuFnvoCBXg,6047
5
+ tiny_recursive_model-0.0.6.dist-info/METADATA,sha256=LaiNz1kSWiZnlyHZEMbWqigZ6bN6_6Joi3_zfY5G_ck,4122
6
+ tiny_recursive_model-0.0.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
7
+ tiny_recursive_model-0.0.6.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
8
+ tiny_recursive_model-0.0.6.dist-info/RECORD,,
@@ -1,8 +0,0 @@
1
- tiny_recursive_model/__init__.py,sha256=zuMcrofGu7DnvJM2Mb-O3tqBJF5q8L-8X8OTmq7_o5w,189
2
- tiny_recursive_model/mlp_mixer_1d.py,sha256=6ivDK9dgHdVl1axg2ayifJ7H5QI3hXptHnb6lfNrno0,1398
3
- tiny_recursive_model/trainer.py,sha256=6dQPmRaQZWI6527OvlOdgHKCFsufkZnjSHClRdHjs20,4218
4
- tiny_recursive_model/trm.py,sha256=pvhXZjDFoLQR-bc8ZDc_ikklF-s21cY5o6xYAwSDoL8,6048
5
- tiny_recursive_model-0.0.4.dist-info/METADATA,sha256=dZKb8mPxFPRghjSG7ZCofEI80nSDlAjFVQAB8JvUAi0,4119
6
- tiny_recursive_model-0.0.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
7
- tiny_recursive_model-0.0.4.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
8
- tiny_recursive_model-0.0.4.dist-info/RECORD,,