sky-2002
/

deepseek-tinystories-60M

Text Generation

mixture-of-experts

Mixture of Experts

multi-head-latent-attention

Model card Files Files and versions

sky-2002 commited on Oct 5, 2025

Commit

10abcc2

·

verified ·

1 Parent(s): 33e0082

Upload deepseek_tinystories/init.py

Files changed (1) hide show

deepseek_tinystories/__init__.py +2 -2

deepseek_tinystories/__init__.py CHANGED Viewed

@@ -6,14 +6,14 @@ architecture, trained on the TinyStories dataset.
 """
 from .modeling_deepseek import DeepseekInspiredModel, DeepSeekModelConfig
-from .processor import TinyStoriesProcessor
 from .utils import load_model, generate_text
 __version__ = "1.0.0"
 __all__ = [
     "DeepseekInspiredModel",
     "DeepSeekModelConfig",
-    "TinyStoriesProcessor",
     "load_model",
     "generate_text"
 ]

 """
 from .modeling_deepseek import DeepseekInspiredModel, DeepSeekModelConfig
+from .processor import TinyStoriesProcesssor
 from .utils import load_model, generate_text
 __version__ = "1.0.0"
 __all__ = [
     "DeepseekInspiredModel",
     "DeepSeekModelConfig",
+    "TinyStoriesProcesssor",
     "load_model",
     "generate_text"
 ]