Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,1024 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:127731
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: Qwen/Qwen3-Embedding-0.6B
+widget:
+- source_sentence: How does the Session Description Protocol (SDP) typically facilitate
+    media session setup?
+  sentences:
+  - The Serving GPRS Support Node (SGSN) typically initiates a PDP context activation
+    procedure towards the GGSN after receiving a request from the mobile device.
+  - SDP is used to describe the parameters for media streams, such as codecs, transport
+    protocols, and IP addresses, enabling endpoints to agree on how to exchange media.
+  - They show the order of the bits produced by the speech encoder.
+- source_sentence: What is the primary function of an encoder in digital signal processing?
+  sentences:
+  - An encoder converts raw data into a specific digital format, often for compression
+    or transmission.
+  - A packetization time of 20ms is specified for GSM_HR within the Circuit Switched
+    Core Network.
+  - No, a fixed line may not always accept a hook flash, for instance, if it is an
+    ISDN line.
+- source_sentence: What are the three distinct categories of Integration Reference
+    Point (IRP) specifications?
+  sentences:
+  - The three categories are Interface IRPs, NRM IRPs, and Data Definition IRPs.
+  - Certain categories of UEs may be configured for uplink MIMO operation in CELL_DCH
+    state.
+  - MCData private emergency alerts are targeted to an MCData user.
+- source_sentence: What security requirement applies to the management connection
+    between a Home NodeB/Home eNodeB and the operator's management platform?
+  sentences:
+  - The management connection between a Home NodeB/Home eNodeB and the operator's
+    management platform must be end-to-end secure.
+  - The gprsSSF sends the ApplyChargingReportGPRS operation to report charging-related
+    information to the gsmSCF as previously requested.
+  - The Voice Activity Detection (VAD) algorithm uses these results.
+- source_sentence: What is the provisioning scope for the eMLPP service?
+  sentences:
+  - eMLPP is provisioned per subscriber.
+  - The main objective is to verify that the User Equipment (UE) tracks channel variations
+    and selects the optimal transport format for frequency non-selective scheduling.
+  - SDP is used in SIP communications to describe the parameters and media capabilities
+    of a session, such as audio/video codecs, transport protocols, and IP addresses,
+    enabling participants to agree on the media types to be used.
+datasets:
+- KayaTechAI/Telecom-Technical-Documents-Retrieval-Embedding-Dataset
+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: Qwen3-Telecom-Retrieval-Embedding
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7988
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.912
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9404
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9636
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7988
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.304
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18808
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09635999999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7988
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.912
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9404
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9636
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8859618086372658
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8605523809523802
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8621275446802356
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7996
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9148
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9408
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9624
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7996
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30493333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18816
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09623999999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7996
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9148
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9408
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9624
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8858790284237884
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8607868253968247
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8624659694868436
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7968
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9128
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9388
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.962
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7968
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3042666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18775999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0962
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7968
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9128
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9388
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.962
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8843651226363695
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8589399999999993
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8605751171152864
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7804
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.912
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9316
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9584
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7804
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.304
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18631999999999999
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09584
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7804
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.912
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9316
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9584
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8752571815294748
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8479898412698406
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8496344353490233
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7696
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.898
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9268
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9524
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7696
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2993333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18536
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09523999999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7696
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.898
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9268
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9524
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8663037855066872
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.838086349206348
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8398504688016839
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.75
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8816
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9124
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9456
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.75
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2938666666666666
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18247999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09455999999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.75
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8816
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9124
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9456
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8521807025695157
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8217822222222212
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8236280446503726
+      name: Cosine Map@100
+---
+
+# Qwen3-Telecom-Retrieval-Embedding
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) on the [telecom-technical-documents-retrieval-embedding-dataset](https://huggingface.co/datasets/KayaTechAI/Telecom-Technical-Documents-Retrieval-Embedding-Dataset) dataset. It maps sentences & paragraphs to a 1024-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:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 -->
+- **Maximum Sequence Length:** 32768 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [telecom-technical-documents-retrieval-embedding-dataset](https://huggingface.co/datasets/KayaTechAI/Telecom-Technical-Documents-Retrieval-Embedding-Dataset)
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, '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("KayaTechAI/Qwen3-0.6B-Fine-Tuned-Telecom-Technical-Documents-Retrieval-Embedding-Generalization-Baseline")
+# Run inference
+queries = [
+    "What is the provisioning scope for the eMLPP service?",
+]
+documents = [
+    'eMLPP is provisioned per subscriber.',
+    'The main objective is to verify that the User Equipment (UE) tracks channel variations and selects the optimal transport format for frequency non-selective scheduling.',
+    'SDP is used in SIP communications to describe the parameters and media capabilities of a session, such as audio/video codecs, transport protocols, and IP addresses, enabling participants to agree on the media types to be used.',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 1024] [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[ 0.6303, -0.0008, -0.0340]])
+```
+
+<!--
+### 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: `dim_1024`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 1024
+  }
+  ```
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.7988    |
+| cosine_accuracy@3   | 0.912     |
+| cosine_accuracy@5   | 0.9404    |
+| cosine_accuracy@10  | 0.9636    |
+| cosine_precision@1  | 0.7988    |
+| cosine_precision@3  | 0.304     |
+| cosine_precision@5  | 0.1881    |
+| cosine_precision@10 | 0.0964    |
+| cosine_recall@1     | 0.7988    |
+| cosine_recall@3     | 0.912     |
+| cosine_recall@5     | 0.9404    |
+| cosine_recall@10    | 0.9636    |
+| **cosine_ndcg@10**  | **0.886** |
+| cosine_mrr@10       | 0.8606    |
+| cosine_map@100      | 0.8621    |
+
+#### Information Retrieval
+
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7996     |
+| cosine_accuracy@3   | 0.9148     |
+| cosine_accuracy@5   | 0.9408     |
+| cosine_accuracy@10  | 0.9624     |
+| cosine_precision@1  | 0.7996     |
+| cosine_precision@3  | 0.3049     |
+| cosine_precision@5  | 0.1882     |
+| cosine_precision@10 | 0.0962     |
+| cosine_recall@1     | 0.7996     |
+| cosine_recall@3     | 0.9148     |
+| cosine_recall@5     | 0.9408     |
+| cosine_recall@10    | 0.9624     |
+| **cosine_ndcg@10**  | **0.8859** |
+| cosine_mrr@10       | 0.8608     |
+| cosine_map@100      | 0.8625     |
+
+#### Information Retrieval
+
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7968     |
+| cosine_accuracy@3   | 0.9128     |
+| cosine_accuracy@5   | 0.9388     |
+| cosine_accuracy@10  | 0.962      |
+| cosine_precision@1  | 0.7968     |
+| cosine_precision@3  | 0.3043     |
+| cosine_precision@5  | 0.1878     |
+| cosine_precision@10 | 0.0962     |
+| cosine_recall@1     | 0.7968     |
+| cosine_recall@3     | 0.9128     |
+| cosine_recall@5     | 0.9388     |
+| cosine_recall@10    | 0.962      |
+| **cosine_ndcg@10**  | **0.8844** |
+| cosine_mrr@10       | 0.8589     |
+| cosine_map@100      | 0.8606     |
+
+#### Information Retrieval
+
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7804     |
+| cosine_accuracy@3   | 0.912      |
+| cosine_accuracy@5   | 0.9316     |
+| cosine_accuracy@10  | 0.9584     |
+| cosine_precision@1  | 0.7804     |
+| cosine_precision@3  | 0.304      |
+| cosine_precision@5  | 0.1863     |
+| cosine_precision@10 | 0.0958     |
+| cosine_recall@1     | 0.7804     |
+| cosine_recall@3     | 0.912      |
+| cosine_recall@5     | 0.9316     |
+| cosine_recall@10    | 0.9584     |
+| **cosine_ndcg@10**  | **0.8753** |
+| cosine_mrr@10       | 0.848      |
+| cosine_map@100      | 0.8496     |
+
+#### Information Retrieval
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7696     |
+| cosine_accuracy@3   | 0.898      |
+| cosine_accuracy@5   | 0.9268     |
+| cosine_accuracy@10  | 0.9524     |
+| cosine_precision@1  | 0.7696     |
+| cosine_precision@3  | 0.2993     |
+| cosine_precision@5  | 0.1854     |
+| cosine_precision@10 | 0.0952     |
+| cosine_recall@1     | 0.7696     |
+| cosine_recall@3     | 0.898      |
+| cosine_recall@5     | 0.9268     |
+| cosine_recall@10    | 0.9524     |
+| **cosine_ndcg@10**  | **0.8663** |
+| cosine_mrr@10       | 0.8381     |
+| cosine_map@100      | 0.8399     |
+
+#### Information Retrieval
+
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 0.8816     |
+| cosine_accuracy@5   | 0.9124     |
+| cosine_accuracy@10  | 0.9456     |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.2939     |
+| cosine_precision@5  | 0.1825     |
+| cosine_precision@10 | 0.0946     |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 0.8816     |
+| cosine_recall@5     | 0.9124     |
+| cosine_recall@10    | 0.9456     |
+| **cosine_ndcg@10**  | **0.8522** |
+| cosine_mrr@10       | 0.8218     |
+| cosine_map@100      | 0.8236     |
+
+<!--
+## 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
+
+#### telecom-technical-documents-retrieval-embedding-dataset
+
+* Dataset: [telecom-technical-documents-retrieval-embedding-dataset](https://huggingface.co/datasets/KayaTechAI/Telecom-Technical-Documents-Retrieval-Embedding-Dataset) at [3ebf34a](https://huggingface.co/datasets/KayaTechAI/Telecom-Technical-Documents-Retrieval-Embedding-Dataset/tree/3ebf34ac897dfe81466bafbc12685ac2571eb8a1)
+* Size: 127,731 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 18.79 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.09 tokens</li><li>max: 77 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                           | positive                                                                                                                                                                                                                                                                                   |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What is the estimated Transmit power considered sufficient for achieving 95% Downlink coverage with a single Base Station?</code>                                                          | <code>Approximately 14 dBm Transmit power is considered sufficient.</code>                                                                                                                                                                                                                 |
+  | <code>What is the primary goal of the Nominal Accuracy requirement?</code>                                                                                                                       | <code>The primary goal of the Nominal Accuracy requirement is to ensure good accuracy when signal conditions are ideal.</code>                                                                                                                                                             |
+  | <code>What happens on the mobile station side if contention resolution fails because the G-RNTI value in the network's acknowledgement message differs from what the mobile station sent?</code> | <code>If the mobile station receives a PACKET UPLINK ACK/NACK message with a G-RNTI value different from the one it included in its first RLC data blocks, it signifies a contention resolution failure, and the mobile station will not transmit a PACKET CONTROL ACKNOWLEDGEMENT.</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `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`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `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`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `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`: True
+- `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_fused
+- `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
+- `hub_revision`: None
+- `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
+- `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
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch   | Step     | Training Loss | dim_1024_cosine_ndcg@10 | 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 |
+|:-------:|:--------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.0401  | 10       | 1.5256        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.0802  | 20       | 0.8247        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.1202  | 30       | 0.4102        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.1603  | 40       | 0.27          | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.2004  | 50       | 0.2182        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.2405  | 60       | 0.1998        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.2806  | 70       | 0.2017        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.3206  | 80       | 0.1672        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.3607  | 90       | 0.2029        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.4008  | 100      | 0.1609        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.4409  | 110      | 0.1565        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.4810  | 120      | 0.1476        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.5210  | 130      | 0.1278        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.5611  | 140      | 0.1669        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.6012  | 150      | 0.1642        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.6413  | 160      | 0.1307        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.6814  | 170      | 0.1487        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.7214  | 180      | 0.1329        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.7615  | 190      | 0.13          | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.8016  | 200      | 0.1393        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.8417  | 210      | 0.1344        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.8818  | 220      | 0.1184        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.9218  | 230      | 0.1147        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.9619  | 240      | 0.1283        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.0     | 250      | 0.1228        | 0.8693                  | 0.8683                 | 0.8634                 | 0.8535                 | 0.8430                 | 0.8082                |
+| 1.0401  | 260      | 0.0613        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.0802  | 270      | 0.0559        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.1202  | 280      | 0.0704        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.1603  | 290      | 0.0578        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.2004  | 300      | 0.0588        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.2405  | 310      | 0.079         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.2806  | 320      | 0.0602        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.3206  | 330      | 0.0553        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.3607  | 340      | 0.0663        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.4008  | 350      | 0.0513        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.4409  | 360      | 0.0615        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.4810  | 370      | 0.0462        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.5210  | 380      | 0.0674        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.5611  | 390      | 0.0558        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.6012  | 400      | 0.0562        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.6413  | 410      | 0.0688        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.6814  | 420      | 0.0905        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.7214  | 430      | 0.0463        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.7615  | 440      | 0.0581        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.8016  | 450      | 0.0586        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.8417  | 460      | 0.0712        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.8818  | 470      | 0.041         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.9218  | 480      | 0.0578        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.9619  | 490      | 0.063         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.0     | 500      | 0.0505        | 0.8771                  | 0.8780                 | 0.8764                 | 0.8690                 | 0.8587                 | 0.8353                |
+| 2.0401  | 510      | 0.032         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.0802  | 520      | 0.0239        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.1202  | 530      | 0.029         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.1603  | 540      | 0.0236        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.2004  | 550      | 0.0381        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.2405  | 560      | 0.028         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.2806  | 570      | 0.0366        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.3206  | 580      | 0.0372        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.3607  | 590      | 0.0306        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.4008  | 600      | 0.0294        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.4409  | 610      | 0.0269        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.4810  | 620      | 0.0411        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.5210  | 630      | 0.0251        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.5611  | 640      | 0.0299        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.6012  | 650      | 0.0275        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.6413  | 660      | 0.0267        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.6814  | 670      | 0.0304        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.7214  | 680      | 0.0246        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.7615  | 690      | 0.025         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.8016  | 700      | 0.037         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.8417  | 710      | 0.0393        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.8818  | 720      | 0.0405        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.9218  | 730      | 0.0279        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.9619  | 740      | 0.0243        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.0     | 750      | 0.0284        | 0.8870                  | 0.8858                 | 0.8827                 | 0.8745                 | 0.8648                 | 0.8499                |
+| 3.0401  | 760      | 0.0166        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.0802  | 770      | 0.024         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.1202  | 780      | 0.0302        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.1603  | 790      | 0.0263        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.2004  | 800      | 0.0172        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.2405  | 810      | 0.023         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.2806  | 820      | 0.0313        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.3206  | 830      | 0.0253        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.3607  | 840      | 0.0189        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.4008  | 850      | 0.0177        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.4409  | 860      | 0.0187        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.4810  | 870      | 0.0142        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.5210  | 880      | 0.0281        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.5611  | 890      | 0.0253        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.6012  | 900      | 0.0184        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.6413  | 910      | 0.0217        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.6814  | 920      | 0.027         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.7214  | 930      | 0.0192        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.7615  | 940      | 0.0183        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.8016  | 950      | 0.0242        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.8417  | 960      | 0.0223        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.8818  | 970      | 0.0161        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.9218  | 980      | 0.0219        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.9619  | 990      | 0.0236        | -                       | -                      | -                      | -                      | -                      | -                     |
+| **4.0** | **1000** | **0.0278**    | **0.886**               | **0.8859**             | **0.8844**             | **0.8753**             | **0.8663**             | **0.8522**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.3
+- Transformers: 4.55.4
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.12.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
+
+## 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### 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.*
+-->

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.3",
+    "transformers": "4.55.4",
+    "pytorch": "2.10.0+cu128"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21673e793547c4325d656b03b49a66335bb38d124fcbf38d11bb38a9f6c6daf
+size 2383139480

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": 32768,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f45684bb3bd50e1eb753e6bc438efc14329c293af236ecd331667b46657a3cc
+size 11423973

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}