Add new SentenceTransformer model

README.md

@@ -7,77 +7,87 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:46
+- dataset_size:129
 - loss:MatryoshkaLoss
 - loss:MultipleNegativesRankingLoss
 base_model: nomic-ai/modernbert-embed-base
 widget:
-- source_sentence: What two factors contribute to the power of LLMs?
+- source_sentence: In what contexts can LLMs be embedded according to the text?
   sentences:
-  - Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific
-    data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG
-    systems, the model first retrieves relevant documents from a database (like a
-    knowledge base), then generates a response using that context—significantly improving
-    the relevance and accuracy of the answers.
-  - LLMs work by learning statistical relationships between words and phrases, allowing
-    them to predict and generate language that feels natural. The power of these models
-    lies not only in their size but also in the diversity of tasks they can perform
-    with little to no task-specific training
-  - . For example, integrating an LLM into a customer support chatbot might involve
-    connecting it to a company’s internal knowledge base, enabling it to answer customer
-    questions using accurate, up-to-date information.
-- source_sentence: What is one method mentioned for fine-tuning the LLM?
-  sentences:
-  - Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific
-    data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG
-    systems, the model first retrieves relevant documents from a database (like a
-    knowledge base), then generates a response using that context—significantly improving
-    the relevance and accuracy of the answers.
+  - Artificial Intelligence (AI) is the broad field of computer science that focuses
+    on building systems capable of performing tasks that normally require human intelligence.
+    These tasks include learning from experience, understanding language, recognizing
+    patterns, and making decisions. AI powers everything from smart assistants like
+    Siri to recommendation systems on Netflix and self-driving cars.
+  - In software development, tools like GitHub Copilot integrate LLMs to assist programmers
+    by generating code, commenting on functions, and detecting bugs.
   - However, deploying LLMs effectively in real-world applications often requires
     LLM integration. This means embedding these models into systems, workflows, or
     products where they can interact with other components like databases, APIs, user
     interfaces, or even custom business logic
+- source_sentence: What is one educational tool mentioned that uses LLMs?
+  sentences:
   - . As organizations increasingly adopt these technologies, the ability to understand
     and apply LLMs will be a critical skill in the AI-powered future.
-- source_sentence: What are some tasks that AI is capable of performing?
+  - '5. Education and Learning Platforms
+
+    Educational tools like Khanmigo (from Khan Academy) and other tutoring platforms
+    are leveraging LLMs to provide real-time help to students. LLMs can break down
+    complex topics, provide feedback on writing, and simulate Socratic-style dialogues.'
+  - '7. Enterprise Integrations
+
+    In enterprises, LLMs are being tied into internal systems like SharePoint, Slack,
+    Jira, and Confluence to act as knowledge assistants. Employees can ask natural
+    language questions like “What’s the latest update on Project Delta?” and get context-rich
+    answers based on internal documents and discussions.'
+- source_sentence: Can the system retrieve documents even if the exact words weren't
+    used?
   sentences:
-  - Artificial Intelligence (AI) is the broad field of computer science that focuses
-    on building systems capable of performing tasks that normally require human intelligence.
-    These tasks include learning from experience, understanding language, recognizing
-    patterns, and making decisions. AI powers everything from smart assistants like
-    Siri to recommendation systems on Netflix and self-driving cars.
-  - In summary, AI and ML form the foundation for intelligent automation, while LLMs
-    represent a breakthrough in language understanding and generation. Integrating
-    these models into real-world systems unlocks practical value, turning raw intelligence
-    into tangible solutions
-  - Introduction to AI, Machine Learning, LLMs, and Their Integration
-- source_sentence: What is the abbreviation for Large Language Models as mentioned
-    in the text?
+  - '7. Enterprise Integrations
+
+    In enterprises, LLMs are being tied into internal systems like SharePoint, Slack,
+    Jira, and Confluence to act as knowledge assistants. Employees can ask natural
+    language questions like “What’s the latest update on Project Delta?” and get context-rich
+    answers based on internal documents and discussions.'
+  - Companies are also experimenting with Retrieval-Augmented Generation (RAG)—a technique
+    where LLMs are paired with document databases (e.g., vector stores like Supabase,
+    Pinecone, or Weaviate) to answer questions with enterprise-specific knowledge.
+  - For instance, in a document management system, a user might type "policies about
+    sick leave", and the system—integrated with an LLM—could retrieve documents discussing
+    "medical leave", "employee absence", and "illness policies", even if those exact
+    words weren’t used.
+- source_sentence: What are some techniques mentioned for mitigating challenges in
+    prompt engineering?
   sentences:
+  - . These include text generation, summarization, translation, question answering,
+    code generation, and more.
+  - . These models are trained on massive text datasets and are capable of generating
+    coherent, context-aware language, answering questions, summarizing documents,
+    writing code, and more.
+  - 'Prompt Engineering: Designing effective prompts and interactions is a new and
+    still-evolving skill.
+
+
+    Mitigating these challenges often involves techniques like prompt tuning, fine-tuning,
+    hybrid search, caching, and using smaller models for certain tasks.
+
+
+    The Future of LLM Integrations
+
+    As LLMs evolve, we’ll see deeper and more seamless integration into everyday tools.
+    The future points to:'
+- source_sentence: What are these models trained on?
+  sentences:
+  - Ultimately, the integration of LLMs across platforms, tools, and workflows is
+    transforming how we interact with information and machines—making software more
+    conversational, intelligent, and context-aware.
+  - . These models are trained on massive text datasets and are capable of generating
+    coherent, context-aware language, answering questions, summarizing documents,
+    writing code, and more.
   - LLMs work by learning statistical relationships between words and phrases, allowing
     them to predict and generate language that feels natural. The power of these models
     lies not only in their size but also in the diversity of tasks they can perform
     with little to no task-specific training
-  - LLMs work by learning statistical relationships between words and phrases, allowing
-    them to predict and generate language that feels natural. The power of these models
-    lies not only in their size but also in the diversity of tasks they can perform
-    with little to no task-specific training
-  - . As organizations increasingly adopt these technologies, the ability to understand
-    and apply LLMs will be a critical skill in the AI-powered future.
-- source_sentence: What does the use of RAG systems improve according to the text?
-  sentences:
-  - . For instance, a spam filter doesn’t just block emails with specific keywords—it
-    learns from thousands of examples what spam typically looks like.
-  - Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific
-    data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG
-    systems, the model first retrieves relevant documents from a database (like a
-    knowledge base), then generates a response using that context—significantly improving
-    the relevance and accuracy of the answers.
-  - Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific
-    data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG
-    systems, the model first retrieves relevant documents from a database (like a
-    knowledge base), then generates a response using that context—significantly improving
-    the relevance and accuracy of the answers.
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 metrics:
@@ -107,49 +117,49 @@ model-index:
       type: dim_768
     metrics:
     - type: cosine_accuracy@1
-      value: 0.6666666666666666
+      value: 0.7333333333333333
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8333333333333334
+      value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.6666666666666666
+      value: 0.7333333333333333
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.27777777777777773
+      value: 0.26666666666666666
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19999999999999998
+      value: 0.17333333333333337
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09999999999999999
+      value: 0.10000000000000003
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.6666666666666666
+      value: 0.7333333333333333
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8333333333333334
+      value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8436010519408085
+      value: 0.8434763926535543
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.7916666666666666
+      value: 0.7969312169312168
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.7916666666666666
+      value: 0.7969312169312168
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -159,49 +169,49 @@ model-index:
       type: dim_512
     metrics:
     - type: cosine_accuracy@1
-      value: 0.6666666666666666
+      value: 0.7333333333333333
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 1.0
+      value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.6666666666666666
+      value: 0.7333333333333333
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3333333333333333
+      value: 0.26666666666666666
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19999999999999998
+      value: 0.17333333333333337
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09999999999999999
+      value: 0.10000000000000003
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.6666666666666666
+      value: 0.7333333333333333
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 1.0
+      value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8769765845238192
+      value: 0.8422851622170473
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8333333333333334
+      value: 0.7957407407407406
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8333333333333334
+      value: 0.7957407407407406
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -214,10 +224,10 @@ model-index:
       value: 0.6666666666666666
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 1.0
+      value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
       value: 1.0
@@ -226,34 +236,34 @@ model-index:
       value: 0.6666666666666666
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3333333333333333
+      value: 0.26666666666666666
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19999999999999998
+      value: 0.17333333333333337
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09999999999999999
+      value: 0.10000000000000003
       name: Cosine Precision@10
     - type: cosine_recall@1
       value: 0.6666666666666666
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 1.0
+      value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8551549589285763
+      value: 0.810143059320221
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8055555555555557
+      value: 0.7524867724867724
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8055555555555557
+      value: 0.7524867724867724
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -263,49 +273,49 @@ model-index:
       type: dim_128
     metrics:
     - type: cosine_accuracy@1
-      value: 0.6666666666666666
+      value: 0.5333333333333333
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8333333333333334
+      value: 0.7333333333333333
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 1.0
+      value: 0.9333333333333333
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.6666666666666666
+      value: 0.5333333333333333
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.27777777777777773
+      value: 0.2444444444444445
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19999999999999998
+      value: 0.17333333333333337
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09999999999999999
+      value: 0.09333333333333335
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.6666666666666666
+      value: 0.5333333333333333
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8333333333333334
+      value: 0.7333333333333333
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 1.0
+      value: 0.9333333333333333
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8217794263455654
+      value: 0.7245635799179159
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.763888888888889
+      value: 0.6588888888888889
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.763888888888889
+      value: 0.6630555555555555
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -315,49 +325,49 @@ model-index:
       type: dim_64
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8333333333333334
+      value: 0.4666666666666667
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 1.0
+      value: 0.6
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 1.0
+      value: 0.8
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8333333333333334
+      value: 0.4666666666666667
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3333333333333333
+      value: 0.2
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19999999999999998
+      value: 0.16000000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09999999999999999
+      value: 0.08666666666666668
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8333333333333334
+      value: 0.4666666666666667
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 1.0
+      value: 0.6
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 1.0
+      value: 0.8
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 1.0
+      value: 0.8666666666666667
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9166666666666666
+      value: 0.6490228576040539
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.888888888888889
+      value: 0.58
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.888888888888889
+      value: 0.5892352092352092
       name: Cosine Map@100
 ---
 
@@ -411,9 +421,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("Nuf-hugginface/modernbert-embed-quickb")
 # Run inference
 sentences = [
-    'What does the use of RAG systems improve according to the text?',
-    'Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG systems, the model first retrieves relevant documents from a database (like a knowledge base), then generates a response using that context—significantly improving the relevance and accuracy of the answers.',
-    'Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG systems, the model first retrieves relevant documents from a database (like a knowledge base), then generates a response using that context—significantly improving the relevance and accuracy of the answers.',
+    'What are these models trained on?',
+    '. These models are trained on massive text datasets and are capable of generating coherent, context-aware language, answering questions, summarizing documents, writing code, and more.',
+    'Ultimately, the integration of LLMs across platforms, tools, and workflows is transforming how we interact with information and machines—making software more conversational, intelligent, and context-aware.',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -458,23 +468,23 @@ You can finetune this model on your own dataset.
 * Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | dim_768    | dim_512   | dim_256    | dim_128    | dim_64     |
-|:--------------------|:-----------|:----------|:-----------|:-----------|:-----------|
-| cosine_accuracy@1   | 0.6667     | 0.6667    | 0.6667     | 0.6667     | 0.8333     |
-| cosine_accuracy@3   | 0.8333     | 1.0       | 1.0        | 0.8333     | 1.0        |
-| cosine_accuracy@5   | 1.0        | 1.0       | 1.0        | 1.0        | 1.0        |
-| cosine_accuracy@10  | 1.0        | 1.0       | 1.0        | 1.0        | 1.0        |
-| cosine_precision@1  | 0.6667     | 0.6667    | 0.6667     | 0.6667     | 0.8333     |
-| cosine_precision@3  | 0.2778     | 0.3333    | 0.3333     | 0.2778     | 0.3333     |
-| cosine_precision@5  | 0.2        | 0.2       | 0.2        | 0.2        | 0.2        |
-| cosine_precision@10 | 0.1        | 0.1       | 0.1        | 0.1        | 0.1        |
-| cosine_recall@1     | 0.6667     | 0.6667    | 0.6667     | 0.6667     | 0.8333     |
-| cosine_recall@3     | 0.8333     | 1.0       | 1.0        | 0.8333     | 1.0        |
-| cosine_recall@5     | 1.0        | 1.0       | 1.0        | 1.0        | 1.0        |
-| cosine_recall@10    | 1.0        | 1.0       | 1.0        | 1.0        | 1.0        |
-| **cosine_ndcg@10**  | **0.8436** | **0.877** | **0.8552** | **0.8218** | **0.9167** |
-| cosine_mrr@10       | 0.7917     | 0.8333    | 0.8056     | 0.7639     | 0.8889     |
-| cosine_map@100      | 0.7917     | 0.8333    | 0.8056     | 0.7639     | 0.8889     |
+| Metric              | dim_768    | dim_512    | dim_256    | dim_128    | dim_64    |
+|:--------------------|:-----------|:-----------|:-----------|:-----------|:----------|
+| cosine_accuracy@1   | 0.7333     | 0.7333     | 0.6667     | 0.5333     | 0.4667    |
+| cosine_accuracy@3   | 0.8        | 0.8        | 0.8        | 0.7333     | 0.6       |
+| cosine_accuracy@5   | 0.8667     | 0.8667     | 0.8667     | 0.8667     | 0.8       |
+| cosine_accuracy@10  | 1.0        | 1.0        | 1.0        | 0.9333     | 0.8667    |
+| cosine_precision@1  | 0.7333     | 0.7333     | 0.6667     | 0.5333     | 0.4667    |
+| cosine_precision@3  | 0.2667     | 0.2667     | 0.2667     | 0.2444     | 0.2       |
+| cosine_precision@5  | 0.1733     | 0.1733     | 0.1733     | 0.1733     | 0.16      |
+| cosine_precision@10 | 0.1        | 0.1        | 0.1        | 0.0933     | 0.0867    |
+| cosine_recall@1     | 0.7333     | 0.7333     | 0.6667     | 0.5333     | 0.4667    |
+| cosine_recall@3     | 0.8        | 0.8        | 0.8        | 0.7333     | 0.6       |
+| cosine_recall@5     | 0.8667     | 0.8667     | 0.8667     | 0.8667     | 0.8       |
+| cosine_recall@10    | 1.0        | 1.0        | 1.0        | 0.9333     | 0.8667    |
+| **cosine_ndcg@10**  | **0.8435** | **0.8423** | **0.8101** | **0.7246** | **0.649** |
+| cosine_mrr@10       | 0.7969     | 0.7957     | 0.7525     | 0.6589     | 0.58      |
+| cosine_map@100      | 0.7969     | 0.7957     | 0.7525     | 0.6631     | 0.5892    |
 
 <!--
 ## Bias, Risks and Limitations
@@ -494,19 +504,19 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 46 training samples
+* Size: 129 training samples
 * Columns: <code>anchor</code> and <code>positive</code>
-* Approximate statistics based on the first 46 samples:
-  |         | anchor                                                                            | positive                                                                           |
-  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                             |
-  | details | <ul><li>min: 9 tokens</li><li>mean: 13.28 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 47.54 tokens</li><li>max: 83 tokens</li></ul> |
+* Approximate statistics based on the first 129 samples:
+  |         | anchor                                                                           | positive                                                                           |
+  |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 13.8 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 53.68 tokens</li><li>max: 86 tokens</li></ul> |
 * Samples:
-  | anchor                                                                              | positive                                                                                                                                                                                                                                                                                                                                                                                            |
-  |:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>What does RAG stand for in the context of the text?</code>                    | <code>Furthermore, advanced integrations might include fine-tuning the LLM on domain-specific data, or pairing it with retrieval-augmented generation (RAG) pipelines. In RAG systems, the model first retrieves relevant documents from a database (like a knowledge base), then generates a response using that context—significantly improving the relevance and accuracy of the answers.</code> |
-  | <code>What type of information can the LLM use to answer customer questions?</code> | <code>. For example, integrating an LLM into a customer support chatbot might involve connecting it to a company’s internal knowledge base, enabling it to answer customer questions using accurate, up-to-date information.</code>                                                                                                                                                                 |
-  | <code>What do AI and ML form the foundation for?</code>                             | <code>In summary, AI and ML form the foundation for intelligent automation, while LLMs represent a breakthrough in language understanding and generation. Integrating these models into real-world systems unlocks practical value, turning raw intelligence into tangible solutions</code>                                                                                                         |
+  | anchor                                                                 | positive                                                                                                                                                                                                                                                                                             |
+  |:-----------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What is the primary ability discussed in the text?</code>        | <code>. This generalization ability makes them incredibly useful across industries—from customer service and education to software development and healthcare.</code>                                                                                                                                |
+  | <code>How many tasks are listed in the text?</code>                    | <code>. These include text generation, summarization, translation, question answering, code generation, and more.</code>                                                                                                                                                                             |
+  | <code>What are examples of chatbot tools mentioned in the text?</code> | <code>1. Chatbots and Virtual Assistants<br>One of the most visible LLM integrations is in chatbots. Tools like ChatGPT, Claude, and Bard are themselves chatbot interfaces built on LLMs. Many businesses are now integrating these models into their websites and customer support systems.</code> |
 * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
   ```json
   {
@@ -665,10 +675,12 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch   | Step  | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
-|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
-| 1.0     | 2     | 0.8244                 | 0.8770                 | 0.8244                 | 0.8029                 | 0.8552                |
-| **2.0** | **4** | **0.8436**             | **0.877**              | **0.8552**             | **0.8218**             | **0.9167**            |
+| Epoch   | Step   | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 1.0     | 5      | -             | 0.8450                 | 0.8003                 | 0.8117                 | 0.7009                 | 0.6370                |
+| 2.0     | 10     | 12.0802       | 0.8427                 | 0.8222                 | 0.8055                 | 0.6979                 | 0.6608                |
+| **3.0** | **15** | **-**         | **0.8435**             | **0.8423**             | **0.8101**             | **0.7246**             | **0.649**             |
+| 3.2424  | 16     | -             | 0.8435                 | 0.8423                 | 0.8101                 | 0.7246                 | 0.6490                |
 
 * The bold row denotes the saved checkpoint.
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32dfd9d19e38eafcef8a97038c57c0f09c730e4f42354f9efc84c9b49b1aab11
+oid sha256:940b2d4ff23ed21583158f999073c662a4aef925a21b9ce34e0d4737565b9db3
 size 596070136