Update README.md

README.md

@@ -7,135 +7,96 @@ base_model: sentence-transformers/all-MiniLM-L6-v2
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 ---
+# SentenceTransformer: tabularisai/all-MiniLM-L2-v2
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This model was [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2), achieving **nearly 2× faster inference** while retaining high accuracy.
 
 ## Model Details
 
-### Model Description
+### Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
-- **Maximum Sequence Length:** 512 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Base Model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384
 - **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
-
-### Model Sources
-
-- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
-- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
-- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
-
-### Full Model Architecture
-
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-)
-```
 
 ## Usage
 
-### Direct Usage (Sentence Transformers)
-
-First install the Sentence Transformers library:
+### Retrieval-Augmented Generation (RAG) Example
 
-```bash
-pip install -U sentence-transformers
-```
+Use this model as a retriever in a RAG pipeline:
 
-Then you can load this model and run inference.
 ```python
-from sentence_transformers import SentenceTransformer
+from sentence_transformers import SentenceTransformer, util
+import faiss
+import numpy as np
 
-# Download from the 🤗 Hub
+# Load embedding model
 model = SentenceTransformer("tabularisai/all-MiniLM-L2-v2")
-# Run inference
-sentences = [
-    'The weather is lovely today.',
-    "It's so sunny outside!",
-    'He drove to the stadium.',
-]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 384]
-
-# Get the similarity scores for the embeddings
-similarities = model.similarity(embeddings, embeddings)
-print(similarities.shape)
-# [3, 3]
-```
-
-<!--
-### Direct Usage (Transformers)
 
-<details><summary>Click to see the direct usage in Transformers</summary>
-
-</details>
--->
-
-<!--
-### Downstream Usage (Sentence Transformers)
-
-You can finetune this model on your own dataset.
-
-<details><summary>Click to expand</summary>
-
-</details>
--->
+# Your 5 simple documents
+documents = [
+    "Renewable energy comes from natural sources.",
+    "Solar panels convert sunlight into electricity.",
+    "Wind turbines harness wind power.",
+    "Fossil fuels are non-renewable sources of energy.",
+    "Hydropower uses water to generate electricity."
+]
 
-<!--
-### Out-of-Scope Use
+# Embed documents
+doc_embeddings = model.encode(documents, convert_to_numpy=True)
 
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
+# Create FAISS index
+dim = doc_embeddings.shape[1]
+index = faiss.IndexFlatL2(dim)
+index.add(doc_embeddings)
 
-<!--
-## Bias, Risks and Limitations
+# Query
+query = "What are the benefits of renewable energy?"
+query_embedding = model.encode([query], convert_to_numpy=True)
 
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
+# Search top 3 similar docs
+D, I = index.search(query_embedding, k=3)
 
-<!--
-### Recommendations
+# Print results
+print("Query:", query)
+print("\nTop 3 similar documents:")
+for rank, idx in enumerate(I[0]):
+    print(f"{rank+1}. {documents[idx]} (score: {D[0][rank]:.4f})")
 
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
+```
 
-## Training Details
+### Sentence Embedding Example
 
-### Framework Versions
-- Python: 3.10.10
-- Sentence Transformers: 4.1.0
-- Transformers: 4.51.3
-- PyTorch: 2.7.0+cu128
-- Accelerate: 
-- Datasets: 3.5.1
-- Tokenizers: 0.21.1
+Install the library:
 
-## Citation
+```bash
+pip install -U sentence-transformers
+```
 
-### BibTeX
+Load the model and encode sentences:
 
-<!--
-## Glossary
+```python
+from sentence_transformers import SentenceTransformer
 
-*Clearly define terms in order to be accessible across audiences.*
--->
+model = SentenceTransformer("tabularisai/all-MiniLM-L2-v2")
 
-<!--
-## Model Card Authors
+sentences = [
+    "The weather is lovely today.",
+    "It's so sunny outside!",
+    "He drove to the stadium.",
+]
 
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
+embeddings = model.encode(sentences)
+print(embeddings.shape)  # [3, 384]
 
-<!--
-## Model Card Contact
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)  # [3, 3]
+```
 
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+## ✅ Key Takeaways
+- Based on MiniLM-L6-v2, distilled from a 12-layer model
+- 2× faster inference
+- 384-dimensional output
+- Compatible with SentenceTransformers and Hugging Face RAG