feat: Upload Python package structure and model artifacts

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 Lorg0n
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,48 +1,33 @@
----
-license: mit
-language:
-- en
-- uk
-- ja
-tags:
-- anime
-- embeddings
-- semantic-search
-- vector-arithmetic
-- pytorch
-datasets:
-- private
-author: Lorg0n
----
-
 # hikka-forge-anime2vec
 
 This repository contains `hikka-forge-anime2vec`, a sophisticated semantic vector space model for anime, created by [Lorg0n](https://huggingface.co/Lorg0n).
 
-The model is trained to understand deep connections between titles based on multilingual textual descriptions, genres, studios, and other metadata. It supports vector arithmetic, allowing for creative queries like `"Show me something like 'Spirited Away' - 'Ghibli Style' + 'Cyberpunk'"`.
-
-## Model Details
+This repository is also a directly installable Python package.
 
-- **Model Version**: v12
-- **Architecture**: A multi-input neural network with separate processing streams for text, genres, and other categorical/numerical features. It uses attention mechanisms to weigh the importance of different text fields and genres.
-- **Training**: Trained using a combination of Triplet Loss (from explicit user recommendations), Cosine Similarity Loss for vector arithmetic examples, and a Diversity Loss to ensure a well-distributed embedding space.
-- **Data**: Trained on a private, non-public database of anime titles.
+## Installation
 
-## How to Use
+```bash
+pip install git+https://huggingface.co/Lorg0n/hikka-forge-anime2vec
+```
 
-*This model requires custom code for loading and inference due to its unique architecture and preprocessing steps.*
+## Usage
 
-A full usage example will be provided soon. The general workflow involves:
-1. Loading the model, config, and pickled `LabelEncoder` objects.
-2. Preprocessing new anime data (fetching from a data source, encoding text with a SentenceTransformer, etc.).
-3. Using the model to generate a 512-dimensional embedding.
-4. Performing similarity search or vector arithmetic in the embedding space.
+```python
+from hikka_forge import Anime2Vec
 
-## Files in this Repository
+# Initialize the model. All artifacts will be downloaded on first run.
+anime2vec = Anime2Vec()
 
-This repository contains all files necessary for model inference:
+# Prepare data for a target anime
+frieren_data = {
+    "en_title": "Frieren: Beyond Journey's End",
+    "genres": ["Adventure", "Drama", "Fantasy"],
+    "studio": "Madhouse",
+    "type": "TV",
+    # ... other relevant fields
+}
 
-- `pytorch_model.bin`: The trained model weights.
-- `config.json`: Configuration file specifying model architecture and vocabulary sizes.
-- `model.py`: The Python code defining the `AnimeEmbeddingModel` class.
-- `le_genre.pkl`, `le_studio.pkl`, `le_type.pkl`: Pickled Scikit-learn `LabelEncoder` objects required for preprocessing new data.
+# Generate the 512-dimensional vector representation
+frieren_vector = anime2vec.encode(frieren_data)
+print(f"Resulting vector shape: {frieren_vector.shape}")
+```

pyproject.toml

@@ -0,0 +1,31 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "hikka-forge-anime2vec"
+version = "0.1.0"
+authors = [ { name="Lorg0n" } ]
+description = "A semantic vector space model for anime with vector arithmetic capabilities."
+readme = "README.md"
+requires-python = ">=3.8"
+license = { file="LICENSE" }
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "torch",
+    "huggingface_hub",
+    "sentence-transformers",
+    "scikit-learn",
+    "numpy",
+]
+
+[project.urls]
+"Homepage" = "https://huggingface.co/Lorg0n/hikka-forge-anime2vec"
+
+[tool.setuptools.packages.find]
+where = ["src"]

src/hikka_forge/__init__.py

@@ -0,0 +1 @@
+from .vectorizer import Anime2Vec

src/hikka_forge/vectorizer.py

@@ -0,0 +1,106 @@
+import torch
+import pickle
+import json
+from huggingface_hub import hf_hub_download
+from sentence_transformers import SentenceTransformer
+import numpy as np
+import importlib.util
+from pathlib import Path
+
+class Anime2Vec:
+    """
+    A high-level wrapper to easily use the hikka-forge-anime2vec model.
+    It automatically downloads all required artifacts from the Hugging Face Hub.
+    """
+    def __init__(self, repo_id: str = "Lorg0n/hikka-forge-anime2vec", device: str = None):
+        print(f"🚀 Initializing Anime2Vec from repository: {repo_id}")
+        
+        self.device = device if device else ("cuda" if torch.cuda.is_available() else "cpu")
+        print(f"   - Using device: {self.device}")
+        
+        cache_dir = Path.home() / ".cache" / "hikka-forge"
+        
+        # Download all necessary files from the repo root
+        config_path = hf_hub_download(repo_id=repo_id, filename="config.json", cache_dir=cache_dir)
+        model_path = hf_hub_download(repo_id=repo_id, filename="pytorch_model.bin", cache_dir=cache_dir)
+        model_code_path = hf_hub_download(repo_id=repo_id, filename="model.py", cache_dir=cache_dir)
+        le_genre_path = hf_hub_download(repo_id=repo_id, filename="le_genre.pkl", cache_dir=cache_dir)
+        le_studio_path = hf_hub_download(repo_id=repo_id, filename="le_studio.pkl", cache_dir=cache_dir)
+        le_type_path = hf_hub_download(repo_id=repo_id, filename="le_type.pkl", cache_dir=cache_dir)
+        
+        # Load configuration and encoders
+        with open(config_path, 'r') as f:
+            self.config = json.load(f)
+        with open(le_genre_path, 'rb') as f:
+            self.le_genre = pickle.load(f)
+        with open(le_studio_path, 'rb') as f:
+            self.le_studio = pickle.load(f)
+        with open(le_type_path, 'rb') as f:
+            self.le_type = pickle.load(f)
+
+        # Dynamically import the model class from the downloaded model.py
+        spec = importlib.util.spec_from_file_location("AnimeEmbeddingModel", model_code_path)
+        model_module = importlib.util.module_from_spec(spec)
+        spec.loader.exec_module(model_module)
+        AnimeEmbeddingModel = model_module.AnimeEmbeddingModel
+        
+        # Initialize the model and load its weights
+        self.model = AnimeEmbeddingModel(
+            vocab_sizes=self.config['vocab_sizes'],
+            embedding_dims=self.config['embedding_dims'],
+            text_embedding_size=self.config['text_embedding_size']
+        )
+        self.model.load_state_dict(torch.load(model_path, map_location=self.device))
+        self.model.to(self.device)
+        self.model.eval()
+        
+        # Initialize the text encoder
+        self.text_encoder = SentenceTransformer(
+            'Lorg0n/hikka-forge-paraphrase-multilingual-MiniLM-L12-v2',
+            device=self.device
+        )
+        print("✅ Initialization complete. Model is ready to use.")
+
+    @torch.no_grad()
+    def encode(self, anime_data: dict) -> np.ndarray:
+        """
+        Encodes a dictionary of anime data into a 512-dimensional vector.
+        """
+        text_fields = [
+            anime_data.get('ua_description', ''), anime_data.get('en_description', ''),
+            anime_data.get('ua_title', ''), anime_data.get('en_title', ''),
+            anime_data.get('original_title', ''), "; ".join(anime_data.get('alternate_names', []))
+        ]
+        text_embeddings = self.text_encoder.encode(text_fields, convert_to_tensor=True)
+        
+        known_genres = [g for g in anime_data.get('genres', []) if g in self.le_genre.classes_]
+        genre_ids = self.le_genre.transform(known_genres) if known_genres else [0]
+        
+        try:
+            studio_id = self.le_studio.transform([anime_data.get('studio', 'UNKNOWN')])[0]
+        except ValueError:
+            studio_id = self.le_studio.transform(['UNKNOWN'])[0]
+
+        try:
+            type_id = self.le_type.transform([anime_data.get('type', 'UNKNOWN')])[0]
+        except ValueError:
+            type_id = self.le_type.transform(['UNKNOWN'])[0]
+            
+        numerical = torch.tensor(anime_data.get('numerical_features', [0.0]*6), dtype=torch.float32)
+
+        batch = {
+            'precomputed_ua_desc': text_embeddings[0], 'precomputed_en_desc': text_embeddings[1],
+            'precomputed_ua_title': text_embeddings[2], 'precomputed_en_title': text_embeddings[3],
+            'precomputed_original_title': text_embeddings[4], 'precomputed_alternate_names': text_embeddings[5],
+            'genres': torch.tensor(genre_ids, dtype=torch.long),
+            'studio': torch.tensor(studio_id, dtype=torch.long),
+            'type': torch.tensor(type_id, dtype=torch.long),
+            'numerical': numerical
+        }
+
+        for key, tensor in batch.items():
+            batch[key] = tensor.unsqueeze(0).to(self.device)
+        batch['genres_mask'] = (batch['genres'] != 0).long()
+        
+        embedding = self.model(batch)
+        return embedding.squeeze().cpu().numpy()