Add new SentenceTransformer model

README.md

@@ -7,87 +7,92 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:129
+- dataset_size:127
 - loss:MatryoshkaLoss
 - loss:MultipleNegativesRankingLoss
 base_model: nomic-ai/modernbert-embed-base
 widget:
-- source_sentence: In what contexts can LLMs be embedded according to the text?
+- source_sentence: What does 'multi-modal' refer to in the context of the services
+    mentioned?
   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 software development, tools like GitHub Copilot integrate LLMs to assist programmers
-    by generating code, commenting on functions, and detecting bugs.
+  - '1. Chatbots and Virtual Assistants
+
+    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.'
+  - For example, e-commerce websites can deploy LLM-powered assistants to help customers
+    find products, track orders, or get personalized recommendations—much more effectively
+    than traditional rule-based bots.
+  - Some services, like ColBERT, Marqo, and ColQwen, specialize in integrating LLMs
+    into search pipelines for both text and multi-modal (text + image) content.
+- source_sentence: What is one method mentioned for deploying LLMs?
+  sentences:
+  - 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
+  - Some services, like ColBERT, Marqo, and ColQwen, specialize in integrating LLMs
+    into search pipelines for both text and multi-modal (text + image) content.
   - 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?
+- source_sentence: What will an LLM likely respond with when prompted about the capital
+    of France?
   sentences:
-  - . As organizations increasingly adopt these technologies, the ability to understand
-    and apply LLMs will be a critical skill in the AI-powered future.
-  - '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?
+  - . For instance, a spam filter doesn’t just block emails with specific keywords—it
+    learns from thousands of examples what spam typically looks like.
+  - Over the past few years, the field of ML has advanced rapidly, especially in the
+    area of Natural Language Processing (NLP)—the ability of machines to understand
+    and generate human language. At the forefront of this progress are Large Language
+    Models (LLMs), such as OpenAI’s GPT (Generative Pre-trained Transformer), Google’s
+    PaLM, and Meta’s LLaMA
+  - For example, given a prompt like "The capital of France is", an LLM trained on
+    a wide range of texts will likely respond with "Paris". But beyond trivia, LLMs
+    can write essays, draft emails, simulate conversations, generate code snippets,
+    and much more.
+- source_sentence: What might an LLM be connected to in a customer support chatbot?
   sentences:
-  - '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?
+  - . For instance, a spam filter doesn’t just block emails with specific keywords—it
+    learns from thousands of examples what spam typically looks like.
+  - . 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.
+  - Large Language Models (LLMs) and Their Integrations
+- source_sentence: What type of dialogues can LLMs simulate?
   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.
+  - 'Hallucinations: LLMs can sometimes generate plausible-sounding but incorrect
+    or fictional information.
 
 
-    Mitigating these challenges often involves techniques like prompt tuning, fine-tuning,
-    hybrid search, caching, and using smaller models for certain tasks.
+    Data Privacy: Sending sensitive data to third-party models raises privacy and
+    compliance concerns.
 
 
-    The Future of LLM Integrations
+    Cost and Latency: Running LLMs, especially large ones, can be computationally
+    expensive and slow.'
+  - '6. APIs and Developer Tools
 
-    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
+    Developers can integrate LLMs into their own apps using APIs provided by companies
+    like OpenAI, Anthropic, and Cohere. These APIs allow developers to send prompts
+    and receive intelligent outputs in return.
+
+
+    This enables custom applications like:
+
+
+    Smart assistants in mobile apps
+
+
+    AI-powered research tools
+
+
+    Voice interfaces'
+  - '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.'
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 metrics:
@@ -117,10 +122,10 @@ model-index:
       type: dim_768
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7333333333333333
+      value: 0.6
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.8
+      value: 0.8666666666666667
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 0.8666666666666667
@@ -129,10 +134,10 @@ model-index:
       value: 1.0
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7333333333333333
+      value: 0.6
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.26666666666666666
+      value: 0.28888888888888886
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.17333333333333337
@@ -141,10 +146,10 @@ model-index:
       value: 0.10000000000000003
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7333333333333333
+      value: 0.6
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.8
+      value: 0.8666666666666667
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 0.8666666666666667
@@ -153,13 +158,13 @@ model-index:
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8434763926535543
+      value: 0.8025374182760189
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.7969312169312168
+      value: 0.74
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.7969312169312168
+      value: 0.74
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -169,49 +174,49 @@ model-index:
       type: dim_512
     metrics:
     - type: cosine_accuracy@1
-      value: 0.7333333333333333
+      value: 0.6666666666666666
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
       value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 1.0
+      value: 0.9333333333333333
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.7333333333333333
+      value: 0.6666666666666666
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.26666666666666666
+      value: 0.2666666666666667
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.17333333333333337
+      value: 0.16000000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.10000000000000003
+      value: 0.09333333333333335
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.7333333333333333
+      value: 0.6666666666666666
       name: Cosine Recall@1
     - type: cosine_recall@3
       value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 1.0
+      value: 0.9333333333333333
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.8422851622170473
+      value: 0.7955687714024445
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.7957407407407406
+      value: 0.7527777777777779
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.7957407407407406
+      value: 0.7583333333333333
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -227,7 +232,7 @@ model-index:
       value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
       value: 1.0
@@ -236,10 +241,10 @@ model-index:
       value: 0.6666666666666666
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.26666666666666666
+      value: 0.2666666666666667
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.17333333333333337
+      value: 0.16000000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
       value: 0.10000000000000003
@@ -251,19 +256,19 @@ model-index:
       value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Recall@5
     - type: cosine_recall@10
       value: 1.0
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.810143059320221
+      value: 0.7985736897839496
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.7524867724867724
+      value: 0.7384126984126984
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.7524867724867724
+      value: 0.7384126984126984
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -273,49 +278,49 @@ model-index:
       type: dim_128
     metrics:
     - type: cosine_accuracy@1
-      value: 0.5333333333333333
+      value: 0.6666666666666666
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.7333333333333333
+      value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9333333333333333
+      value: 0.8666666666666667
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.5333333333333333
+      value: 0.6666666666666666
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2444444444444445
+      value: 0.2666666666666667
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.17333333333333337
+      value: 0.16000000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09333333333333335
+      value: 0.08666666666666668
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.5333333333333333
+      value: 0.6666666666666666
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.7333333333333333
+      value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9333333333333333
+      value: 0.8666666666666667
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.7245635799179159
+      value: 0.7700616222307202
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.6588888888888889
+      value: 0.74
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.6630555555555555
+      value: 0.7479365079365079
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -325,49 +330,49 @@ model-index:
       type: dim_64
     metrics:
     - type: cosine_accuracy@1
-      value: 0.4666666666666667
+      value: 0.6
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.6
+      value: 0.8
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 0.8
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.4666666666666667
+      value: 0.6
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2
+      value: 0.2666666666666667
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.16000000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.08666666666666668
+      value: 0.08000000000000002
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.4666666666666667
+      value: 0.6
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.6
+      value: 0.8
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 0.8
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.8666666666666667
+      value: 0.8
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.6490228576040539
+      value: 0.7174573004761944
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.58
+      value: 0.6888888888888889
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.5892352092352092
+      value: 0.7003968253968255
       name: Cosine Map@100
 ---
 
@@ -421,9 +426,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("Nuf-hugginface/modernbert-embed-quickb")
 # Run inference
 sentences = [
-    '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.',
+    'What type of dialogues can LLMs simulate?',
+    '5. Education and Learning Platforms\nEducational 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.',
+    '6. APIs and Developer Tools\nDevelopers can integrate LLMs into their own apps using APIs provided by companies like OpenAI, Anthropic, and Cohere. These APIs allow developers to send prompts and receive intelligent outputs in return.\n\nThis enables custom applications like:\n\nSmart assistants in mobile apps\n\nAI-powered research tools\n\nVoice interfaces',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -468,23 +473,23 @@ 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   | 0.7333     | 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    |
+| Metric              | dim_768    | dim_512    | dim_256    | dim_128    | dim_64     |
+|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1   | 0.6        | 0.6667     | 0.6667     | 0.6667     | 0.6        |
+| cosine_accuracy@3   | 0.8667     | 0.8        | 0.8        | 0.8        | 0.8        |
+| cosine_accuracy@5   | 0.8667     | 0.8        | 0.8        | 0.8        | 0.8        |
+| cosine_accuracy@10  | 1.0        | 0.9333     | 1.0        | 0.8667     | 0.8        |
+| cosine_precision@1  | 0.6        | 0.6667     | 0.6667     | 0.6667     | 0.6        |
+| cosine_precision@3  | 0.2889     | 0.2667     | 0.2667     | 0.2667     | 0.2667     |
+| cosine_precision@5  | 0.1733     | 0.16       | 0.16       | 0.16       | 0.16       |
+| cosine_precision@10 | 0.1        | 0.0933     | 0.1        | 0.0867     | 0.08       |
+| cosine_recall@1     | 0.6        | 0.6667     | 0.6667     | 0.6667     | 0.6        |
+| cosine_recall@3     | 0.8667     | 0.8        | 0.8        | 0.8        | 0.8        |
+| cosine_recall@5     | 0.8667     | 0.8        | 0.8        | 0.8        | 0.8        |
+| cosine_recall@10    | 1.0        | 0.9333     | 1.0        | 0.8667     | 0.8        |
+| **cosine_ndcg@10**  | **0.8025** | **0.7956** | **0.7986** | **0.7701** | **0.7175** |
+| cosine_mrr@10       | 0.74       | 0.7528     | 0.7384     | 0.74       | 0.6889     |
+| cosine_map@100      | 0.74       | 0.7583     | 0.7384     | 0.7479     | 0.7004     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -504,19 +509,19 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 129 training samples
+* Size: 127 training samples
 * Columns: <code>anchor</code> and <code>positive</code>
-* Approximate statistics based on the first 129 samples:
+* Approximate statistics based on the first 127 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> |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 13.2 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 53.85 tokens</li><li>max: 86 tokens</li></ul> |
 * Samples:
-  | 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> |
+  | anchor                                                                           | positive                                                                                                                                                                                                                                                                                             |
+  |:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What documents could the system retrieve in relation to sick leave?</code> | <code>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.</code>            |
+  | <code>What is one of the most visible integrations of LLM technology?</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> |
+  | <code>What does AI stand for?</code>                                             | <code>Introduction to AI, Machine Learning, LLMs, and Their Integration</code>                                                                                                                                                                                                                       |
 * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
   ```json
   {
@@ -675,12 +680,13 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| 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                |
+| 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     | 4     | -             | 0.7853                 | 0.8214                 | 0.7673                 | 0.7586                 | 0.6883                |
+| **2.0** | **8** | **-**         | **0.7764**             | **0.7902**             | **0.7686**             | **0.7701**             | **0.7321**            |
+| 2.5     | 10    | 13.8004       | -                      | -                      | -                      | -                      | -                     |
+| 3.0     | 12    | -             | 0.8028                 | 0.7710                 | 0.7932                 | 0.7701                 | 0.7175                |
+| 4.0     | 16    | -             | 0.8025                 | 0.7956                 | 0.7986                 | 0.7701                 | 0.7175                |
 
 * The bold row denotes the saved checkpoint.
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940b2d4ff23ed21583158f999073c662a4aef925a21b9ce34e0d4737565b9db3
+oid sha256:e7fa83288c96da5c91a8d0a7f680fa88e3010ec41496910019839fb29c898aa3
 size 596070136