AbstractIntegratedModule 0.3.8__tar.gz → 0.3.9__tar.gz

{abstractintegratedmodule-0.3.8 → abstractintegratedmodule-0.3.9/AbstractIntegratedModule.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AbstractIntegratedModule
-Version: 0.3.8
+Version: 0.3.9
 Summary: Framework for Advanced Integrated Non-LLM AI Module library - Backend Framework for Non-LLM AI Agent Framework
 Author: Micro-Novelty
 Author-email: hernikpuspita5@gmail.com
@@ -42,7 +42,7 @@ https://github.com/Micro-Novelty/IntegratedPipeline-Specialized-Non-LLM-AI-Agent
 #### Note: The README here you are reading is a direct copy from my README Repository, to download the necessary files, you can visit my Repository with the provided link above.
 
 ### Library Short Description:
-- Development Stage: Beta, 0.3.8.
+- Development Stage: Beta, 0.3.9.
 - Maintainer: Micro-Novelty.
 - library Source-Code is Open-sourced on github.
 - Purpose: Specifically Designed for providing Non-LLM AI Agent Framework for edge Devices, Optimized for ARM64 architecture.
@@ -66,7 +66,7 @@ https://github.com/Micro-Novelty/IntegratedPipeline-Specialized-Non-LLM-AI-Agent
 -----
 
 <img width="1280" height="600" alt="WhatsApp Image 2026-05-27 at 07 16 32" src="https://github.com/user-attachments/assets/4b58a556-45a3-419b-96fd-9c1b76cac574" />
-
+[![PyPI Downloads](https://static.pepy.tech/personalized-badge/abstractintegratedmodule?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/abstractintegratedmodule)
 
 ## [+] MANN Intro
 [=] Memory augmented Neural network (MANN) is a neural network architecture coupled with an external, dynamic memory module, allowing it to store, retrieve, and update information similarly to a computer's RAM. Unlike traditional networks that store knowledge only in weight parameters, MANNs excel at fast learning, long-term dependency handling, and episodic recall, In IntegratedPipeline, Its memory is stored in a custom database inside your local machine, then later used for memory retrieval, transfered to the AI Dictionary where it can finnaly recall its memory when input condition matched with memory. 

{abstractintegratedmodule-0.3.8 → abstractintegratedmodule-0.3.9}/AbstractIntegratedModule.py

@@ -295,6 +295,7 @@ class Singleton(metaclass=SingletonMeta):
 #  allowing it to better process data with varying geometric complexity, and providing a more stable training process in scarce data environment. 
 # It can be used as a general weight initialization and shaping method for various models, especially in scenarios where data geometry is complex and data is scarce.
 
+
 class GeometricWeightShaping:
     def __init__(self, input_size, output_size):
         self.input_size = input_size
@@ -313,7 +314,7 @@ class GeometricWeightShaping:
 
         anisotropy = self.anisotropy_measurement(raw_X)
 
-        structured_noise = np.random.uniform(0, mag, size=raw_X.shape)
+        structured_noise = np.random.uniform(eps, mag, size=raw_X.shape)
         X = np.vstack((raw_X, structured_noise))
         if X.ndim == 2 and X.shape[1] == 1:
             X = np.hstack((raw_X, structured_noise))
@@ -336,7 +337,7 @@ class GeometricWeightShaping:
         if np.isnan(trC) or np.isinf(trC):
             trC = anisotropy * (1.0 - np.std(x)) + eps
 
-        floating_point = np.random.uniform(0, trC, size=X.shape)        
+        floating_point = np.random.uniform(1e-10, trC, size=X.shape)        
         return k, floating_point, structured_noise
 
 
@@ -417,7 +418,7 @@ class GeometricWeightShaping:
         if np.isnan(efficient_distributed_energy) or np.isinf(efficient_distributed_energy):
             efficient_distributed_energy = (1 - AMR) + eps
 
-        floating_context = rng.uniform(0, efficient_distributed_energy, size=(input_size, output_size)) 
+        floating_context = rng.uniform(1e-10, efficient_distributed_energy, size=(input_size, output_size)) 
         self.floating_context = floating_context
 
         return floating_context
@@ -439,7 +440,6 @@ class GeometricWeightShaping:
         return floating_context
 
 
-
 # ________ UTILITY functions for activations and losses, can be used across different models and architectures _________
 
 def sigmoid(x):
@@ -1710,6 +1710,7 @@ class LSTMEngine:
                                         # cell state c is untouched —
                                         # preserves long-term memory
             if self.model.Wy is None:
+
                 self.model.Wy = self.model.weight_shaper.weight_shaping(x_seq)
 
             pred = h @ self.model.Wy.T + self.model.by

{abstractintegratedmodule-0.3.8/AbstractIntegratedModule.egg-info → abstractintegratedmodule-0.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AbstractIntegratedModule
-Version: 0.3.8
+Version: 0.3.9
 Summary: Framework for Advanced Integrated Non-LLM AI Module library - Backend Framework for Non-LLM AI Agent Framework
 Author: Micro-Novelty
 Author-email: hernikpuspita5@gmail.com
@@ -42,7 +42,7 @@ https://github.com/Micro-Novelty/IntegratedPipeline-Specialized-Non-LLM-AI-Agent
 #### Note: The README here you are reading is a direct copy from my README Repository, to download the necessary files, you can visit my Repository with the provided link above.
 
 ### Library Short Description:
-- Development Stage: Beta, 0.3.8.
+- Development Stage: Beta, 0.3.9.
 - Maintainer: Micro-Novelty.
 - library Source-Code is Open-sourced on github.
 - Purpose: Specifically Designed for providing Non-LLM AI Agent Framework for edge Devices, Optimized for ARM64 architecture.
@@ -66,7 +66,7 @@ https://github.com/Micro-Novelty/IntegratedPipeline-Specialized-Non-LLM-AI-Agent
 -----
 
 <img width="1280" height="600" alt="WhatsApp Image 2026-05-27 at 07 16 32" src="https://github.com/user-attachments/assets/4b58a556-45a3-419b-96fd-9c1b76cac574" />
-
+[![PyPI Downloads](https://static.pepy.tech/personalized-badge/abstractintegratedmodule?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/abstractintegratedmodule)
 
 ## [+] MANN Intro
 [=] Memory augmented Neural network (MANN) is a neural network architecture coupled with an external, dynamic memory module, allowing it to store, retrieve, and update information similarly to a computer's RAM. Unlike traditional networks that store knowledge only in weight parameters, MANNs excel at fast learning, long-term dependency handling, and episodic recall, In IntegratedPipeline, Its memory is stored in a custom database inside your local machine, then later used for memory retrieval, transfered to the AI Dictionary where it can finnaly recall its memory when input condition matched with memory. 

{abstractintegratedmodule-0.3.8 → abstractintegratedmodule-0.3.9}/README.md

@@ -10,7 +10,7 @@ https://github.com/Micro-Novelty/IntegratedPipeline-Specialized-Non-LLM-AI-Agent
 #### Note: The README here you are reading is a direct copy from my README Repository, to download the necessary files, you can visit my Repository with the provided link above.
 
 ### Library Short Description:
-- Development Stage: Beta, 0.3.8.
+- Development Stage: Beta, 0.3.9.
 - Maintainer: Micro-Novelty.
 - library Source-Code is Open-sourced on github.
 - Purpose: Specifically Designed for providing Non-LLM AI Agent Framework for edge Devices, Optimized for ARM64 architecture.
@@ -34,7 +34,7 @@ https://github.com/Micro-Novelty/IntegratedPipeline-Specialized-Non-LLM-AI-Agent
 -----
 
 <img width="1280" height="600" alt="WhatsApp Image 2026-05-27 at 07 16 32" src="https://github.com/user-attachments/assets/4b58a556-45a3-419b-96fd-9c1b76cac574" />
-
+[![PyPI Downloads](https://static.pepy.tech/personalized-badge/abstractintegratedmodule?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/abstractintegratedmodule)
 
 ## [+] MANN Intro
 [=] Memory augmented Neural network (MANN) is a neural network architecture coupled with an external, dynamic memory module, allowing it to store, retrieve, and update information similarly to a computer's RAM. Unlike traditional networks that store knowledge only in weight parameters, MANNs excel at fast learning, long-term dependency handling, and episodic recall, In IntegratedPipeline, Its memory is stored in a custom database inside your local machine, then later used for memory retrieval, transfered to the AI Dictionary where it can finnaly recall its memory when input condition matched with memory. 

{abstractintegratedmodule-0.3.8 → abstractintegratedmodule-0.3.9}/setup.py

@@ -8,7 +8,7 @@ class BinaryDistribution(Distribution):
 
 setup(
     name="AbstractIntegratedModule",
-    version="0.3.8",
+    version="0.3.9",
     description="Framework for Advanced Integrated Non-LLM AI Module library - Backend Framework for Non-LLM AI Agent Framework",
     long_description=open("README.md", encoding="utf-8").read(),
     long_description_content_type="text/markdown",