convaiinnovations
/

hindi-embedding-foundational-model

@@ -12,59 +12,42 @@ datasets:
 pipeline_tag: sentence-similarity
 library_name: transformers
 ---
 # Hindi Sentence Embeddings Model
 This is a custom state-of-the-art sentence embedding model trained specifically for Hindi text. It leverages an advanced transformer architecture with specialized pooling strategies to create high-quality semantic representations of Hindi sentences.
 ## Features
 - Specialized for Hindi language text
 - Advanced transformer architecture with optimized attention mechanism
 - Multiple pooling strategies for enhanced semantic representations
 - Creates normalized vector representations for semantic similarity
 - Supports semantic search and text similarity applications
 ## Usage
 ### Installation
 ```bash
 pip install torch sentencepiece scikit-learn matplotlib
 git lfs install
-git clone https://huggingface.co/DeepMostInnovations/hindi-embedding-foundational-model
 cd hindi-embedding-foundational-model
 ```
 ### Enhanced RAG System
 This model now includes an enhanced RAG (Retrieval Augmented Generation) system that integrates Unsloth's optimized Llama-3.2-1B-Instruct model for question answering on top of Hindi document retrieval.
 #### Setup and Installation
 1. Install additional dependencies:
 ```bash
 pip install unsloth transformers bitsandbytes accelerate langchain langchain-community faiss-cpu
 ```
 2. Index your documents:
 ```bash
 python hindi-rag-system.py --model_dir /path/to/your/model --tokenizer_dir /path/to/tokenizer --data_dir ./data --output_dir ./output --index
 ```
 3. Run in QA mode with LLM:
 ```bash
 python hindi-rag-system.py --model_dir /path/to/your/model --tokenizer_dir /path/to/tokenizer --output_dir ./output --interactive --qa
 ```
 ### Basic Embedding Usage
 ```python
 from hindi_embeddings import HindiEmbedder
 # Initialize the embedder
 model = HindiEmbedder("path/to/hindi-embedding-foundational-model")
 # Encode sentences to embeddings
 sentences = [
     "मुझे हिंदी भाषा बहुत पसंद है।",
@@ -72,11 +55,9 @@ sentences = [
 ]
 embeddings = model.encode(sentences)
 print(f"Embedding shape: {embeddings.shape}")
 # Compute similarity between sentences
 similarity = model.compute_similarity(sentences[0], sentences[1])
 print(f"Similarity: {similarity:.4f}")
 # Perform semantic search
 query = "भारत की राजधानी"
 documents = [
@@ -88,7 +69,6 @@ results = model.search(query, documents)
 for i, result in enumerate(results):
     print(f"{i+1}. Score: {result['score']:.4f}")
     print(f"   Document: {result['document']}")
 # Visualize embeddings
 example_sentences = [
     "मुझे हिंदी में पढ़ना बहुत पसंद है।",
@@ -97,16 +77,12 @@ example_sentences = [
 ]
 model.visualize_embeddings(example_sentences)
 ```
 ## Model Details
 This model uses an advanced transformer-based architecture with the following enhancements:
 - Pre-layer normalization for stable training
 - Specialized attention mechanism with relative positional encoding
 - Multiple pooling strategies (weighted, mean, attention-based)
 - L2-normalized vectors for cosine similarity
 Technical specifications:
 - Embedding dimension: 768
 - Hidden dimension: 768
@@ -114,9 +90,7 @@ Technical specifications:
 - Attention heads: 12
 - Vocabulary size: 50,000
 - Context length: 128 tokens
 ## Applications
 - Semantic search and information retrieval
 - Text clustering and categorization
 - Recommendation systems
@@ -124,21 +98,5 @@ Technical specifications:
 - Document similarity comparison
 - Content-based filtering
 - RAG systems for Hindi language content
 ## License
 This model is released under the MIT License.
-## Citation
-If you use this model in your research or application, please cite us:
-```
-@misc{DeepMostInnovations2025hindi,
-  author = {DeepMost Innovations},
-  title = {Hindi Sentence Embeddings Model},
-  year = {2025},
-  publisher = {Hugging Face},
-  howpublished = {\url{https://huggingface.co/DeepMostInnovations/hindi-embedding-foundational-model}}
-}
-```

 pipeline_tag: sentence-similarity
 library_name: transformers
 ---
 # Hindi Sentence Embeddings Model
 This is a custom state-of-the-art sentence embedding model trained specifically for Hindi text. It leverages an advanced transformer architecture with specialized pooling strategies to create high-quality semantic representations of Hindi sentences.
 ## Features
 - Specialized for Hindi language text
 - Advanced transformer architecture with optimized attention mechanism
 - Multiple pooling strategies for enhanced semantic representations
 - Creates normalized vector representations for semantic similarity
 - Supports semantic search and text similarity applications
 ## Usage
 ### Installation
 ```bash
 pip install torch sentencepiece scikit-learn matplotlib
 git lfs install
+git clone https://huggingface.co/convaiinnovations/hindi-embedding-foundational-model
 cd hindi-embedding-foundational-model
 ```
 ### Enhanced RAG System
 This model now includes an enhanced RAG (Retrieval Augmented Generation) system that integrates Unsloth's optimized Llama-3.2-1B-Instruct model for question answering on top of Hindi document retrieval.
 #### Setup and Installation
 1. Install additional dependencies:
 ```bash
 pip install unsloth transformers bitsandbytes accelerate langchain langchain-community faiss-cpu
 ```
 2. Index your documents:
 ```bash
 python hindi-rag-system.py --model_dir /path/to/your/model --tokenizer_dir /path/to/tokenizer --data_dir ./data --output_dir ./output --index
 ```
 3. Run in QA mode with LLM:
 ```bash
 python hindi-rag-system.py --model_dir /path/to/your/model --tokenizer_dir /path/to/tokenizer --output_dir ./output --interactive --qa
 ```
 ### Basic Embedding Usage
 ```python
 from hindi_embeddings import HindiEmbedder
 # Initialize the embedder
 model = HindiEmbedder("path/to/hindi-embedding-foundational-model")
 # Encode sentences to embeddings
 sentences = [
     "मुझे हिंदी भाषा बहुत पसंद है।",
 ]
 embeddings = model.encode(sentences)
 print(f"Embedding shape: {embeddings.shape}")
 # Compute similarity between sentences
 similarity = model.compute_similarity(sentences[0], sentences[1])
 print(f"Similarity: {similarity:.4f}")
 # Perform semantic search
 query = "भारत की राजधानी"
 documents = [
 for i, result in enumerate(results):
     print(f"{i+1}. Score: {result['score']:.4f}")
     print(f"   Document: {result['document']}")
 # Visualize embeddings
 example_sentences = [
     "मुझे हिंदी में पढ़ना बहुत पसंद है।",
 ]
 model.visualize_embeddings(example_sentences)
 ```
 ## Model Details
 This model uses an advanced transformer-based architecture with the following enhancements:
 - Pre-layer normalization for stable training
 - Specialized attention mechanism with relative positional encoding
 - Multiple pooling strategies (weighted, mean, attention-based)
 - L2-normalized vectors for cosine similarity
 Technical specifications:
 - Embedding dimension: 768
 - Hidden dimension: 768
 - Attention heads: 12
 - Vocabulary size: 50,000
 - Context length: 128 tokens
 ## Applications
 - Semantic search and information retrieval
 - Text clustering and categorization
 - Recommendation systems
 - Document similarity comparison
 - Content-based filtering
 - RAG systems for Hindi language content
 ## License
 This model is released under the MIT License.