Add new SentenceTransformer model

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 768,
-    "pooling_mode_cls_token": true,
-    "pooling_mode_mean_tokens": false,
+    "word_embedding_dimension": 384,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:713743
 - loss:MultipleNegativesRankingLoss
-base_model: Alibaba-NLP/gte-modernbert-base
+base_model: sentence-transformers/all-MiniLM-L6-v2
 widget:
 - source_sentence: 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
   sentences:
@@ -59,7 +59,7 @@ metrics:
 - cosine_mrr@10
 - cosine_map@100
 model-index:
-- name: SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
   results:
   - task:
       type: information-retrieval
@@ -69,49 +69,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.38
+      value: 0.26
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.54
+      value: 0.52
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.68
+      value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.8
+      value: 0.62
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.38
+      value: 0.26
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.18
+      value: 0.1733333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.136
+      value: 0.12
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.08
+      value: 0.062
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.38
+      value: 0.26
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.54
+      value: 0.52
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.68
+      value: 0.6
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.8
+      value: 0.62
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5686686381597302
+      value: 0.45904886208148177
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.49702380952380953
+      value: 0.40519047619047627
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.5063338862610184
+      value: 0.4260102142025637
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -121,49 +121,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.4
+      value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.56
+      value: 0.5
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.66
+      value: 0.62
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.4
+      value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.2
+      value: 0.1733333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.12800000000000003
+      value: 0.128
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07
+      value: 0.066
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.36
+      value: 0.3
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.54
+      value: 0.47
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 0.58
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.63
+      value: 0.6
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5105228253020769
+      value: 0.4619884812398348
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.48852380952380947
+      value: 0.4272222222222222
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4728184565167554
+      value: 0.42411471333193373
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -173,63 +173,63 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.39
+      value: 0.29000000000000004
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.55
+      value: 0.51
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.64
+      value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.73
+      value: 0.62
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.39
+      value: 0.29000000000000004
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.19
+      value: 0.1733333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.132
+      value: 0.124
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07500000000000001
+      value: 0.064
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.37
+      value: 0.28
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.54
+      value: 0.495
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.63
+      value: 0.59
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.7150000000000001
+      value: 0.61
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5395957317309036
+      value: 0.4605186716606583
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.4927738095238095
+      value: 0.41620634920634925
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.48957617138888687
+      value: 0.4250624637672487
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision e7f32e3c00f91d699e8c43b53106206bcc72bb22 -->
+- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 768 dimensions
+- **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -245,8 +245,9 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [A
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
-  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, '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': False, 'include_prompt': True})
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
 )
 ```
 
@@ -274,14 +275,14 @@ sentences = [
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 768]
+# [3, 384]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  1.0000, -0.0629],
-#         [ 1.0000,  1.0000, -0.0629],
-#         [-0.0629, -0.0629,  1.0001]])
+# tensor([[ 1.0000,  1.0000, -0.0482],
+#         [ 1.0000,  1.0000, -0.0482],
+#         [-0.0482, -0.0482,  1.0000]])
 ```
 
 <!--
@@ -317,23 +318,23 @@ You can finetune this model on your own dataset.
 * Datasets: `NanoMSMARCO` and `NanoNQ`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | NanoMSMARCO | NanoNQ     |
-|:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.38        | 0.4        |
-| cosine_accuracy@3   | 0.54        | 0.56       |
-| cosine_accuracy@5   | 0.68        | 0.6        |
-| cosine_accuracy@10  | 0.8         | 0.66       |
-| cosine_precision@1  | 0.38        | 0.4        |
-| cosine_precision@3  | 0.18        | 0.2        |
-| cosine_precision@5  | 0.136       | 0.128      |
-| cosine_precision@10 | 0.08        | 0.07       |
-| cosine_recall@1     | 0.38        | 0.36       |
-| cosine_recall@3     | 0.54        | 0.54       |
-| cosine_recall@5     | 0.68        | 0.58       |
-| cosine_recall@10    | 0.8         | 0.63       |
-| **cosine_ndcg@10**  | **0.5687**  | **0.5105** |
-| cosine_mrr@10       | 0.497       | 0.4885     |
-| cosine_map@100      | 0.5063      | 0.4728     |
+| Metric              | NanoMSMARCO | NanoNQ    |
+|:--------------------|:------------|:----------|
+| cosine_accuracy@1   | 0.26        | 0.32      |
+| cosine_accuracy@3   | 0.52        | 0.5       |
+| cosine_accuracy@5   | 0.6         | 0.6       |
+| cosine_accuracy@10  | 0.62        | 0.62      |
+| cosine_precision@1  | 0.26        | 0.32      |
+| cosine_precision@3  | 0.1733      | 0.1733    |
+| cosine_precision@5  | 0.12        | 0.128     |
+| cosine_precision@10 | 0.062       | 0.066     |
+| cosine_recall@1     | 0.26        | 0.3       |
+| cosine_recall@3     | 0.52        | 0.47      |
+| cosine_recall@5     | 0.6         | 0.58      |
+| cosine_recall@10    | 0.62        | 0.6       |
+| **cosine_ndcg@10**  | **0.459**   | **0.462** |
+| cosine_mrr@10       | 0.4052      | 0.4272    |
+| cosine_map@100      | 0.426       | 0.4241    |
 
 #### Nano BEIR
 
@@ -351,21 +352,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.39       |
-| cosine_accuracy@3   | 0.55       |
-| cosine_accuracy@5   | 0.64       |
-| cosine_accuracy@10  | 0.73       |
-| cosine_precision@1  | 0.39       |
-| cosine_precision@3  | 0.19       |
-| cosine_precision@5  | 0.132      |
-| cosine_precision@10 | 0.075      |
-| cosine_recall@1     | 0.37       |
-| cosine_recall@3     | 0.54       |
-| cosine_recall@5     | 0.63       |
-| cosine_recall@10    | 0.715      |
-| **cosine_ndcg@10**  | **0.5396** |
-| cosine_mrr@10       | 0.4928     |
-| cosine_map@100      | 0.4896     |
+| cosine_accuracy@1   | 0.29       |
+| cosine_accuracy@3   | 0.51       |
+| cosine_accuracy@5   | 0.6        |
+| cosine_accuracy@10  | 0.62       |
+| cosine_precision@1  | 0.29       |
+| cosine_precision@3  | 0.1733     |
+| cosine_precision@5  | 0.124      |
+| cosine_precision@10 | 0.064      |
+| cosine_recall@1     | 0.28       |
+| cosine_recall@3     | 0.495      |
+| cosine_recall@5     | 0.59       |
+| cosine_recall@10    | 0.61       |
+| **cosine_ndcg@10**  | **0.4605** |
+| cosine_mrr@10       | 0.4162     |
+| cosine_map@100      | 0.4251     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -391,7 +392,7 @@ You can finetune this model on your own dataset.
   |         | anchor                                                                            | positive                                                                          | negative                                                                          |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.96 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.93 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.72 tokens</li><li>max: 59 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 16.07 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.03 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 58 tokens</li></ul> |
 * Samples:
   | anchor                                                                         | positive                                                                              | negative                                                                                                          |
   |:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|
@@ -417,7 +418,7 @@ You can finetune this model on your own dataset.
   |         | anchor                                                                            | positive                                                                          | negative                                                                          |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 7 tokens</li><li>mean: 15.47 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.48 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.76 tokens</li><li>max: 67 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.52 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.51 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.79 tokens</li><li>max: 69 tokens</li></ul> |
 * Samples:
   | anchor                                                                                                                                                       | positive                                                                                                                                                     | negative                                                                                                                                                            |
   |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -582,27 +583,27 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss | Validation Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
 |:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
-| 0      | 0    | -             | 2.2389          | 0.6530                     | 0.6552                | 0.6541                       |
-| 0.0448 | 250  | 1.0022        | 0.4154          | 0.6615                     | 0.5429                | 0.6022                       |
-| 0.0897 | 500  | 0.3871        | 0.3658          | 0.6042                     | 0.4458                | 0.5250                       |
-| 0.1345 | 750  | 0.3575        | 0.3479          | 0.5819                     | 0.5160                | 0.5489                       |
-| 0.1793 | 1000 | 0.3454        | 0.3355          | 0.5976                     | 0.5595                | 0.5785                       |
-| 0.2242 | 1250 | 0.337         | 0.3284          | 0.5901                     | 0.4544                | 0.5223                       |
-| 0.2690 | 1500 | 0.3291        | 0.3235          | 0.6138                     | 0.5729                | 0.5933                       |
-| 0.3138 | 1750 | 0.323         | 0.3182          | 0.6210                     | 0.5608                | 0.5909                       |
-| 0.3587 | 2000 | 0.3206        | 0.3141          | 0.6139                     | 0.5474                | 0.5807                       |
-| 0.4035 | 2250 | 0.3151        | 0.3120          | 0.6275                     | 0.5665                | 0.5970                       |
-| 0.4484 | 2500 | 0.3132        | 0.3093          | 0.6059                     | 0.5349                | 0.5704                       |
-| 0.4932 | 2750 | 0.3087        | 0.3072          | 0.6011                     | 0.5305                | 0.5658                       |
-| 0.5380 | 3000 | 0.3065        | 0.3051          | 0.5816                     | 0.5057                | 0.5436                       |
-| 0.5829 | 3250 | 0.3044        | 0.3033          | 0.5959                     | 0.5203                | 0.5581                       |
-| 0.6277 | 3500 | 0.3053        | 0.3018          | 0.5817                     | 0.5185                | 0.5501                       |
-| 0.6725 | 3750 | 0.3028        | 0.3006          | 0.5744                     | 0.5052                | 0.5398                       |
-| 0.7174 | 4000 | 0.3018        | 0.2996          | 0.5783                     | 0.5190                | 0.5487                       |
-| 0.7622 | 4250 | 0.3011        | 0.2994          | 0.5679                     | 0.4959                | 0.5319                       |
-| 0.8070 | 4500 | 0.3009        | 0.2979          | 0.5689                     | 0.5068                | 0.5378                       |
-| 0.8519 | 4750 | 0.2985        | 0.2975          | 0.5687                     | 0.5135                | 0.5411                       |
-| 0.8967 | 5000 | 0.2995        | 0.2971          | 0.5687                     | 0.5105                | 0.5396                       |
+| 0      | 0    | -             | 0.7908          | 0.5540                     | 0.5931                | 0.5735                       |
+| 0.0448 | 250  | 0.7632        | 0.4756          | 0.5373                     | 0.5302                | 0.5337                       |
+| 0.0897 | 500  | 0.5825        | 0.4308          | 0.5277                     | 0.4949                | 0.5113                       |
+| 0.1345 | 750  | 0.5438        | 0.4161          | 0.5180                     | 0.5039                | 0.5110                       |
+| 0.1793 | 1000 | 0.5277        | 0.4070          | 0.5008                     | 0.4875                | 0.4942                       |
+| 0.2242 | 1250 | 0.516         | 0.4012          | 0.4983                     | 0.4779                | 0.4881                       |
+| 0.2690 | 1500 | 0.5049        | 0.3962          | 0.4923                     | 0.4777                | 0.4850                       |
+| 0.3138 | 1750 | 0.4966        | 0.3931          | 0.4789                     | 0.4769                | 0.4779                       |
+| 0.3587 | 2000 | 0.493         | 0.3894          | 0.4792                     | 0.4616                | 0.4704                       |
+| 0.4035 | 2250 | 0.4852        | 0.3866          | 0.4828                     | 0.4749                | 0.4788                       |
+| 0.4484 | 2500 | 0.4815        | 0.3841          | 0.4589                     | 0.4559                | 0.4574                       |
+| 0.4932 | 2750 | 0.4761        | 0.3820          | 0.4647                     | 0.4539                | 0.4593                       |
+| 0.5380 | 3000 | 0.4747        | 0.3796          | 0.4588                     | 0.4493                | 0.4540                       |
+| 0.5829 | 3250 | 0.4722        | 0.3786          | 0.4588                     | 0.4458                | 0.4523                       |
+| 0.6277 | 3500 | 0.4725        | 0.3774          | 0.4587                     | 0.4537                | 0.4562                       |
+| 0.6725 | 3750 | 0.4692        | 0.3766          | 0.4561                     | 0.4621                | 0.4591                       |
+| 0.7174 | 4000 | 0.4664        | 0.3763          | 0.4584                     | 0.4395                | 0.4489                       |
+| 0.7622 | 4250 | 0.4659        | 0.3747          | 0.4645                     | 0.4586                | 0.4616                       |
+| 0.8070 | 4500 | 0.464         | 0.3742          | 0.4619                     | 0.4479                | 0.4549                       |
+| 0.8519 | 4750 | 0.4662        | 0.3739          | 0.4590                     | 0.4498                | 0.4544                       |
+| 0.8967 | 5000 | 0.4662        | 0.3739          | 0.4590                     | 0.4620                | 0.4605                       |
 
 
 ### Framework Versions

config_sentence_transformers.json

@@ -4,11 +4,11 @@
     "transformers": "4.57.3",
     "pytorch": "2.9.1+cu128"
   },
+  "model_type": "SentenceTransformer",
   "prompts": {
     "query": "",
     "document": ""
   },
   "default_prompt_name": null,
-  "similarity_fn_name": "cosine",
-  "model_type": "SentenceTransformer"
+  "similarity_fn_name": "cosine"
 }

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]