myrkur
/

sentence-transformer-parsbert-fa

@@ -48,7 +48,7 @@ license: apache-2.0
 # SentenceTransformer based on HooshvareLab/bert-base-parsbert-uncased
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 ## Model Details
@@ -99,68 +99,57 @@ similarities = model.similarity(embeddings, embeddings)
 print(similarities.shape)
 # [3, 3]
 ```
-### Training Logs
-| Epoch      | Step    | Training Loss | loss       |
-|:----------:|:-------:|:-------------:|:----------:|
-| 0.0265     | 20      | 0.7506        | -          |
-| 0.0530     | 40      | 0.6701        | -          |
-| 0.0530     | 20      | 0.5843        | -          |
-| 0.1060     | 40      | 0.4591        | -          |
-| 0.1591     | 60      | 0.3316        | -          |
-| 0.2121     | 80      | 0.2856        | -          |
-| 0.2651     | 100     | 0.2599        | -          |
-| 0.3181     | 120     | 0.2478        | -          |
-| 0.3712     | 140     | 0.214         | -          |
-| 0.4242     | 160     | 0.1996        | -          |
-| 0.4772     | 180     | 0.1929        | -          |
-| 0.5302     | 200     | 0.193         | 0.1766     |
-| 0.5833     | 220     | 0.1798        | -          |
-| 0.6363     | 240     | 0.1794        | -          |
-| 0.6893     | 260     | 0.1735        | -          |
-| 0.7423     | 280     | 0.1713        | -          |
-| 0.7954     | 300     | 0.1547        | -          |
-| 0.8484     | 320     | 0.1545        | -          |
-| 0.9014     | 340     | 0.1577        | -          |
-| 0.9544     | 360     | 0.1575        | -          |
-| 1.0075     | 380     | 0.1431        | -          |
-| 1.0605     | 400     | 0.1498        | 0.1489     |
-| 1.1135     | 420     | 0.1327        | -          |
-| 1.1665     | 440     | 0.1223        | -          |
-| 1.2196     | 460     | 0.1154        | -          |
-| 1.2726     | 480     | 0.1059        | -          |
-| 1.3256     | 500     | 0.1068        | -          |
-| 1.3786     | 520     | 0.0959        | -          |
-| 1.4316     | 540     | 0.0884        | -          |
-| 1.4847     | 560     | 0.0896        | -          |
-| 1.5377     | 580     | 0.0899        | -          |
-| **1.5907** | **600** | **0.0814**    | **0.1445** |
-| 1.6437     | 620     | 0.0877        | -          |
-| 1.6968     | 640     | 0.0816        | -          |
-| 1.7498     | 660     | 0.0846        | -          |
-| 1.8028     | 680     | 0.0783        | -          |
-| 1.8558     | 700     | 0.0787        | -          |
-| 1.9089     | 720     | 0.0874        | -          |
-| 1.9619     | 740     | 0.0883        | -          |
-* The bold row denotes the saved checkpoint.
-<!--
-## Glossary
-*Clearly define terms in order to be accessible across audiences.*
--->
-<!--
-## Model Card Authors
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
-<!--
-## Model Card Contact
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->

 # SentenceTransformer based on HooshvareLab/bert-base-parsbert-uncased
+This [sentence-transformers](https://www.SBERT.net) model is finetuned from [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) with a focus on enhancing Retrieval-Augmented Generation (RAG) systems. It maps sentences and paragraphs to a 768-dimensional dense vector space, making it highly effective for retrieving contextually relevant information to generate accurate and coherent responses in various applications such as QA systems, chatbots, and content generation.
 ## Model Details
 print(similarities.shape)
 # [3, 3]
 ```
+### Usage in Retrieval-Augmented Generation (RAG) Systems
+Retrieval-Augmented Generation (RAG) systems leverage a combination of retrieval and generation techniques to enhance the quality and accuracy of generated responses. This model can be effectively used to retrieve relevant information from a large corpus, which can then be used to generate more informed and contextually accurate responses. Here's how you can integrate this model into a RAG system:
+Install Necessary Libraries:
+Ensure you have the required libraries:
+```bash
+pip install -U sentence-transformers transformers
+```
+```python
+from sentence_transformers import SentenceTransformer, util
+import torch
+# Load the model
+model = SentenceTransformer("myrkur/sentence-transformer-parsbert-fa")
+# Example corpus
+corpus = [
+    'پرتغالی، در وطن اصلی خود، پرتغال، تقریباً توسط ۱۰ میلیون نفر جمعیت صحبت می‌شود...',
+    'اشکانیان حدود دو قرن بر ایران حکومت کردند...',
+    'عباس جدیدی، کشتی‌گیر سابق ایرانی است...',
+    # ... (more documents)
+]
+# Encode the corpus
+corpus_embeddings = model.encode(corpus, convert_to_tensor=True)
+```
+Retrieve Relevant Information:
+Given a user query, retrieve the most relevant documents from the corpus:
+```python
+# User query
+query = "عباس جدیدی که بود؟"
+query_embedding = model.encode(query, convert_to_tensor=True)
+# Retrieve the top-k most similar documents
+top_k = 5
+hits = util.semantic_search(query_embedding, corpus_embeddings, top_k=top_k)
+hits = hits[0]
+# Print the retrieved documents
+for hit in hits:
+    print(f"Score: {hit['score']:.4f}")
+    print(corpus[hit['corpus_id']])
+```
+## Conclusion
+This sentence-transformer model is a powerful tool for various NLP applications, particularly in retrieval-augmented generation systems, enabling more accurate and contextually relevant information retrieval and generation.
+## Contact
+For questions or further information, please contact:
+- Amir Masoud Ahmadi: [amirmasoud.ahkol@gmail.com](mailto:amirmasoud.ahkol@gmail.com)