Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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
+}

README.md

@@ -0,0 +1,987 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2048
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-distilroberta-v1
+widget:
+- source_sentence: Can you provide the link to the Discrete Math final exam from 2024?
+  sentences:
+  - 'The final exam for Discrete Math course, offered by the general department, from
+    2024, is available at the following link: [https://drive.google.com/file/d/1pCpnVt6IiOTMlGTYw3sUZ8NEnI3thwO5/view?usp=sharing'
+  - 'The final exam for internet of things course, offered by the computer science
+    department, from 2025, is available at the following link: [https://drive.google.com/file/d/1UjtShx1hFNg8_gB5NsqGDGKAvpkkBfm9/view?usp=sharing'
+  - 'The final exam for the physics1 course, offered by the general department, from
+    2018, is available at the following link: [https://drive.google.com/file/d/1T-KLo2JW3fLFSu1hT7WtGOnmXFQTqMin/view].'
+- source_sentence: Can you provide the exam link for the Physics 1 course from 2023?
+  sentences:
+  - 'The final exam for the physics1 course, offered by the general department, from
+    2023, is available at the following link: [https://drive.google.com/file/d/1TrlV8yBdNHJjGVsDBD6EU2A4G80nU1kV/view?usp=sharing].'
+  - 'The final exam for the Probability & Statistics course, offered by the general
+    department, from 2021, is available at the following link: [https://drive.google.com/drive/u/2/folders/1c2w87tPBcFazujOmQ1ZKmiuR__EIsQd3].'
+  - Dr. Noran el sayed is part of the Unknown department and can be reached at [email protected].
+- source_sentence: How can I access the final exam for the Software Engineering class
+    from 2015?
+  sentences:
+  - 'The final exam for Software Engineering course, offered by the information system
+    department, from 2015, is available at the following link: [https://drive.google.com/file/d/1ve8sh5HhCeQqr_swbADxYiYvJRkFBiAi/view'
+  - Dr. Ahmed Soliman (Ahmed Nagiub) is part of the Unknown department and can be
+    reached at [email protected].
+  - 'The final exam for Software Engineering course, offered by the information system
+    department, from 2020, is available at the following link: [https://drive.google.com/file/d/1qYvsJGm5FWTq9L7TlJOGg85vPHtu7G6d/view'
+- source_sentence: Is there a link available for the 2023 Probability & Stats course
+    exam?
+  sentences:
+  - 'The final exam for operating system course, offered by the computer science department,
+    from 2024, is available at the following link: [https://drive.google.com/file/d/1ITc9Hs3s0sw8SPEfKSAlE-sQTngL5oaL/view?usp=sharing'
+  - 'The final exam for the Probability & Statistics course, offered by the general
+    department, from 2023, is available at the following link: [https://drive.google.com/file/d/1kh3KbahqTnCSNwqDyB8iSPSIMQ9B9ZUZ/view?usp=sharing].'
+  - 'The final exam for computer Architecture and organization course, offered by
+    the general department, from 2024, is available at the following link: [https://drive.google.com/file/d/1BBVB6U8nnEA8sLUlmR3J52TD8kjWlGWM/view?usp=sharing'
+- source_sentence: How do I access the final exam for the Digital Image Processing
+    course from 2016?
+  sentences:
+  - 'The final exam for the Statistical Analysis course, offered by the general department,
+    from 2025, is available at the following link: [https://drive.google.com/file/d/14Fi9uMdy0JRw7Wp2j1-2eNoRd5CwS_ng/view?usp=sharing'
+  - 'The final exam for Digital Image Processing course, offered by the computer science
+    department, from 2016, is available at the following link: [https://drive.google.com/file/d/1dUDU-VM5_c7Wst98iTC83GhudfNL-r_G/view'
+  - 'The final exam for the Probability & Statistics course, offered by the general
+    department, from 2021, is available at the following link: [https://drive.google.com/drive/u/2/folders/1c2w87tPBcFazujOmQ1ZKmiuR__EIsQd3].'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-distilroberta-v1
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: ai college validation
+      type: ai-college-validation
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.55078125
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82421875
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.890625
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.95703125
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.55078125
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27473958333333326
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17812499999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.095703125
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.55078125
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82421875
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.890625
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.95703125
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7655983040473691
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7029761904761903
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7052547923124669
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.66015625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9453125
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.66015625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31510416666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.66015625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9453125
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8528799902335868
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8027994791666668
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8027994791666666
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.66015625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.94140625
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.99609375
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.66015625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3138020833333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19921875
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.66015625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.94140625
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.99609375
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8541928904310672
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8045572916666668
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8045572916666667
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.67578125
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9453125
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.67578125
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31510416666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.67578125
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9453125
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8605213037068725
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8130208333333334
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8130208333333334
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.68359375
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.95703125
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.68359375
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31901041666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.68359375
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.95703125
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8643861203886329
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8181640625000001
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8181640625
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.68359375
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.95703125
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.68359375
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31901041666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.68359375
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.95703125
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8655801956151241
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8196614583333336
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8196614583333333
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.69140625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9609375
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.98828125
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.69140625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3203125
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19765625000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.69140625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9609375
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.98828125
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8686343143993309
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8239908854166668
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8239908854166667
+      name: Cosine Map@100
+    - type: cosine_accuracy@1
+      value: 0.68359375
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.95703125
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.68359375
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31901041666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.68359375
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.95703125
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8655801956151241
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8196614583333336
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8196614583333333
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on sentence-transformers/all-distilroberta-v1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1). 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
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1) <!-- at revision 842eaed40bee4d61673a81c92d5689a8fed7a09f -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **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: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("Bo8dady/finetuned-College-embeddings")
+# Run inference
+sentences = [
+    'How do I access the final exam for the Digital Image Processing course from 2016?',
+    'The final exam for Digital Image Processing course, offered by the computer science department, from 2016, is available at the following link: [https://drive.google.com/file/d/1dUDU-VM5_c7Wst98iTC83GhudfNL-r_G/view',
+    'The final exam for the Statistical Analysis course, offered by the general department, from 2025, is available at the following link: [https://drive.google.com/file/d/14Fi9uMdy0JRw7Wp2j1-2eNoRd5CwS_ng/view?usp=sharing',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.5508     |
+| cosine_accuracy@3   | 0.8242     |
+| cosine_accuracy@5   | 0.8906     |
+| cosine_accuracy@10  | 0.957      |
+| cosine_precision@1  | 0.5508     |
+| cosine_precision@3  | 0.2747     |
+| cosine_precision@5  | 0.1781     |
+| cosine_precision@10 | 0.0957     |
+| cosine_recall@1     | 0.5508     |
+| cosine_recall@3     | 0.8242     |
+| cosine_recall@5     | 0.8906     |
+| cosine_recall@10    | 0.957      |
+| **cosine_ndcg@10**  | **0.7656** |
+| cosine_mrr@10       | 0.703      |
+| cosine_map@100      | 0.7053     |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6602     |
+| cosine_accuracy@3   | 0.9453     |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6602     |
+| cosine_precision@3  | 0.3151     |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6602     |
+| cosine_recall@3     | 0.9453     |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8529** |
+| cosine_mrr@10       | 0.8028     |
+| cosine_map@100      | 0.8028     |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6602     |
+| cosine_accuracy@3   | 0.9414     |
+| cosine_accuracy@5   | 0.9961     |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6602     |
+| cosine_precision@3  | 0.3138     |
+| cosine_precision@5  | 0.1992     |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6602     |
+| cosine_recall@3     | 0.9414     |
+| cosine_recall@5     | 0.9961     |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8542** |
+| cosine_mrr@10       | 0.8046     |
+| cosine_map@100      | 0.8046     |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6758     |
+| cosine_accuracy@3   | 0.9453     |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6758     |
+| cosine_precision@3  | 0.3151     |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6758     |
+| cosine_recall@3     | 0.9453     |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8605** |
+| cosine_mrr@10       | 0.813      |
+| cosine_map@100      | 0.813      |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6836     |
+| cosine_accuracy@3   | 0.957      |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6836     |
+| cosine_precision@3  | 0.319      |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6836     |
+| cosine_recall@3     | 0.957      |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8644** |
+| cosine_mrr@10       | 0.8182     |
+| cosine_map@100      | 0.8182     |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6836     |
+| cosine_accuracy@3   | 0.957      |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6836     |
+| cosine_precision@3  | 0.319      |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6836     |
+| cosine_recall@3     | 0.957      |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8656** |
+| cosine_mrr@10       | 0.8197     |
+| cosine_map@100      | 0.8197     |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6914     |
+| cosine_accuracy@3   | 0.9609     |
+| cosine_accuracy@5   | 0.9883     |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6914     |
+| cosine_precision@3  | 0.3203     |
+| cosine_precision@5  | 0.1977     |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6914     |
+| cosine_recall@3     | 0.9609     |
+| cosine_recall@5     | 0.9883     |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8686** |
+| cosine_mrr@10       | 0.824      |
+| cosine_map@100      | 0.824      |
+
+#### Information Retrieval
+
+* Dataset: `ai-college-validation`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6836     |
+| cosine_accuracy@3   | 0.957      |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.6836     |
+| cosine_precision@3  | 0.319      |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.6836     |
+| cosine_recall@3     | 0.957      |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| **cosine_ndcg@10**  | **0.8656** |
+| cosine_mrr@10       | 0.8197     |
+| cosine_map@100      | 0.8197     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 2,048 training samples
+* Columns: <code>Question</code> and <code>chunk</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | Question                                                                           | chunk                                                                               |
+  |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                              |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 15.84 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 84.15 tokens</li><li>max: 467 tokens</li></ul> |
+* Samples:
+  | Question                                                                             | chunk                                                                                                                                                                                                                                                                                                                                                |
+  |:-------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Could you share the link to the 2020 Data Structures final exam?</code>        | <code>The final exam for Data Structures  course, offered by the general department, from 2020, is available at the following link: [https://drive.google.com/file/d/1U735N5tPHTyXtWgoSp0XI1zo9j2LN2Km/view</code>                                                                                                                                   |
+  | <code>Can you provide the exam link for the 2018 Software Engineering course?</code> | <code>The final exam for Software Engineering course, offered by the computer science department, from 2018, is available at the following link: [https://drive.google.com/file/d/1kqjCVWTBJVhr_JyiTmfrK1BrHy8_tVX2/view</code>                                                                                                                      |
+  | <code>- Who decides if an absence excuse is acceptable for a final exam?</code>      | <code>Topic: Absence from Written Exam<br>Summary: Unexcused absence from a final exam results in a failing grade (F).<br>Chunk: "Absence from the written exam<br>A student who is absent from the final exam for a course without an acceptable excuse from the College Council is considered a failure in the course and has a grade (F)."</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 256 evaluation samples
+* Columns: <code>Question</code> and <code>chunk</code>
+* Approximate statistics based on the first 256 samples:
+  |         | Question                                                                           | chunk                                                                               |
+  |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                              |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 16.01 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 27 tokens</li><li>mean: 79.97 tokens</li><li>max: 467 tokens</li></ul> |
+* Samples:
+  | Question                                                                                              | chunk                                                                                                                                                                                                                                            |
+  |:------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>How do I get to the final exam for the AI course in 2016?</code>                                | <code>The final exam for Artificial Intelligence course, offered by the general department, from 2016, is available at the following link: [https://drive.google.com/file/d/1vaZOQMuqe4qfzPzgvxiSz0rnGxzFwL-F/view?usp=sharing</code>            |
+  | <code>Can I get the URL for the 2024 Probability and Statistics final exam?</code>                    | <code>The final exam for the Probability & Statistics course, offered by the general department, from 2024, is available at the following link: [https://drive.google.com/file/d/1lAFwZRcgDl02zKwrFclAvmqr5k9Z_Ct2/view?usp=sharing].</code>     |
+  | <code>Where can I find the final exam link for the Digital Signal Processing course from 2024?</code> | <code>The final exam for Digital Signal Processing course, offered by the computer science department, from 2024, is available at the following link: [https://drive.google.com/file/d/1RO0aPoom-TA-qgsopwR9krszD_pQIzfJ/view?usp=sharing</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `learning_rate`: 1e-05
+- `warmup_ratio`: 0.2
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.2
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | ai-college-validation_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------------------------:|
+| 0      | 0    | -             | -               | 0.7656                               |
+| 1.0    | 64   | -             | -               | 0.8542                               |
+| 1.5469 | 100  | 0.0359        | 0.0239          | 0.8529                               |
+| 2.9688 | 192  | -             | -               | 0.8575                               |
+| 1.5469 | 100  | 0.0126        | 0.0306          | 0.8621                               |
+| 3.0781 | 200  | 0.0155        | 0.0267          | 0.8575                               |
+| 4.625  | 300  | 0.0195        | 0.0287          | 0.8542                               |
+| 4.9375 | 320  | -             | -               | 0.8556                               |
+| 1.5469 | 100  | 0.0034        | 0.0289          | 0.8605                               |
+| 2.9688 | 192  | -             | -               | 0.8615                               |
+| 1.5469 | 100  | 0.0014        | 0.0312          | 0.8644                               |
+| 2.9688 | 192  | -             | -               | 0.8656                               |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.0
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.2.1
+- Datasets: 3.3.1
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "sentence-transformers/all-distilroberta-v1",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.0",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e902315f4d340f0e1ad8531fe89903dffde8b6d452188429a942eb26058ffeda
+size 328485128

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}