Add new SentenceTransformer model

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 384,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "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,

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:111470
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L12-v2
+base_model: Alibaba-NLP/gte-modernbert-base
 widget:
 - source_sentence: why are some rocks radioactive
   sentences:
@@ -106,7 +106,7 @@ metrics:
 - cosine_mrr@10
 - cosine_map@100
 model-index:
-- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+- name: SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
   results:
   - task:
       type: information-retrieval
@@ -116,49 +116,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.36
+      value: 0.46
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.58
+      value: 0.66
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.68
+      value: 0.7
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.76
+      value: 0.82
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.36
+      value: 0.46
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.19333333333333333
+      value: 0.22
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.136
+      value: 0.14
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07600000000000001
+      value: 0.08199999999999999
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.36
+      value: 0.46
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.58
+      value: 0.66
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.68
+      value: 0.7
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.76
+      value: 0.82
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5522122196843595
+      value: 0.6411634133079402
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.48633333333333334
+      value: 0.5842460317460317
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4958040190560276
+      value: 0.5911749882485325
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -168,49 +168,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.44
+      value: 0.34
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.56
+      value: 0.58
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.6
+      value: 0.66
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.66
+      value: 0.78
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.44
+      value: 0.34
       name: Cosine Precision@1
     - type: cosine_precision@3
       value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.128
+      value: 0.136
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07
+      value: 0.08399999999999999
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.41
+      value: 0.32
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.53
+      value: 0.54
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.58
+      value: 0.62
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.64
+      value: 0.74
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5277371826996979
+      value: 0.5340775600556903
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.505079365079365
+      value: 0.4830238095238096
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.5002333969355556
+      value: 0.4703754816157255
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -223,60 +223,60 @@ model-index:
       value: 0.4
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.5700000000000001
+      value: 0.62
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.64
+      value: 0.6799999999999999
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.71
+      value: 0.8
       name: Cosine Accuracy@10
     - type: cosine_precision@1
       value: 0.4
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.19333333333333333
+      value: 0.20666666666666667
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.132
+      value: 0.138
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07300000000000001
+      value: 0.08299999999999999
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.385
+      value: 0.39
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.5549999999999999
+      value: 0.6000000000000001
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.63
+      value: 0.6599999999999999
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.7
+      value: 0.78
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5399747011920287
+      value: 0.5876204866818153
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.49570634920634915
+      value: 0.5336349206349207
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4980187079957916
+      value: 0.5307752349321291
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+# SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-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.
+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.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision 936af83a2ecce5fe87a09109ff5cbcefe073173a -->
+- **Base model:** [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision e7f32e3c00f91d699e8c43b53106206bcc72bb22 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -292,9 +292,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 
 ```
 SentenceTransformer(
-  (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()
+  (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})
 )
 ```
 
@@ -322,14 +321,14 @@ sentences = [
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 384]
+# [3, 768]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[0.9999, 0.9999, 0.9775],
-#         [0.9999, 0.9999, 0.9775],
-#         [0.9775, 0.9775, 1.0000]])
+# tensor([[1.0000, 1.0000, 0.2374],
+#         [1.0000, 1.0000, 0.2374],
+#         [0.2374, 0.2374, 1.0000]])
 ```
 
 <!--
@@ -367,21 +366,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.36        | 0.44       |
-| cosine_accuracy@3   | 0.58        | 0.56       |
-| cosine_accuracy@5   | 0.68        | 0.6        |
-| cosine_accuracy@10  | 0.76        | 0.66       |
-| cosine_precision@1  | 0.36        | 0.44       |
-| cosine_precision@3  | 0.1933      | 0.1933     |
-| cosine_precision@5  | 0.136       | 0.128      |
-| cosine_precision@10 | 0.076       | 0.07       |
-| cosine_recall@1     | 0.36        | 0.41       |
-| cosine_recall@3     | 0.58        | 0.53       |
-| cosine_recall@5     | 0.68        | 0.58       |
-| cosine_recall@10    | 0.76        | 0.64       |
-| **cosine_ndcg@10**  | **0.5522**  | **0.5277** |
-| cosine_mrr@10       | 0.4863      | 0.5051     |
-| cosine_map@100      | 0.4958      | 0.5002     |
+| cosine_accuracy@1   | 0.46        | 0.34       |
+| cosine_accuracy@3   | 0.66        | 0.58       |
+| cosine_accuracy@5   | 0.7         | 0.66       |
+| cosine_accuracy@10  | 0.82        | 0.78       |
+| cosine_precision@1  | 0.46        | 0.34       |
+| cosine_precision@3  | 0.22        | 0.1933     |
+| cosine_precision@5  | 0.14        | 0.136      |
+| cosine_precision@10 | 0.082       | 0.084      |
+| cosine_recall@1     | 0.46        | 0.32       |
+| cosine_recall@3     | 0.66        | 0.54       |
+| cosine_recall@5     | 0.7         | 0.62       |
+| cosine_recall@10    | 0.82        | 0.74       |
+| **cosine_ndcg@10**  | **0.6412**  | **0.5341** |
+| cosine_mrr@10       | 0.5842      | 0.483      |
+| cosine_map@100      | 0.5912      | 0.4704     |
 
 #### Nano BEIR
 
@@ -397,23 +396,23 @@ You can finetune this model on your own dataset.
   }
   ```
 
-| Metric              | Value    |
-|:--------------------|:---------|
-| cosine_accuracy@1   | 0.4      |
-| cosine_accuracy@3   | 0.57     |
-| cosine_accuracy@5   | 0.64     |
-| cosine_accuracy@10  | 0.71     |
-| cosine_precision@1  | 0.4      |
-| cosine_precision@3  | 0.1933   |
-| cosine_precision@5  | 0.132    |
-| cosine_precision@10 | 0.073    |
-| cosine_recall@1     | 0.385    |
-| cosine_recall@3     | 0.555    |
-| cosine_recall@5     | 0.63     |
-| cosine_recall@10    | 0.7      |
-| **cosine_ndcg@10**  | **0.54** |
-| cosine_mrr@10       | 0.4957   |
-| cosine_map@100      | 0.498    |
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.4        |
+| cosine_accuracy@3   | 0.62       |
+| cosine_accuracy@5   | 0.68       |
+| cosine_accuracy@10  | 0.8        |
+| cosine_precision@1  | 0.4        |
+| cosine_precision@3  | 0.2067     |
+| cosine_precision@5  | 0.138      |
+| cosine_precision@10 | 0.083      |
+| cosine_recall@1     | 0.39       |
+| cosine_recall@3     | 0.6        |
+| cosine_recall@5     | 0.66       |
+| cosine_recall@10    | 0.78       |
+| **cosine_ndcg@10**  | **0.5876** |
+| cosine_mrr@10       | 0.5336     |
+| cosine_map@100      | 0.5308     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -439,7 +438,7 @@ You can finetune this model on your own dataset.
   |         | anchor                                                                            | positive                                                                           | negative                                                                           |
   |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                             | string                                                                             |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 10.95 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 67.57 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 66.64 tokens</li><li>max: 128 tokens</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 11.17 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 68.53 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 67.56 tokens</li><li>max: 128 tokens</li></ul> |
 * Samples:
   | anchor                                                                | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
   |:----------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -465,7 +464,7 @@ You can finetune this model on your own dataset.
   |         | anchor                                                                            | positive                                                                           | negative                                                                           |
   |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                             | string                                                                             |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 11.11 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 67.99 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 66.08 tokens</li><li>max: 128 tokens</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 11.35 tokens</li><li>max: 64 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 68.67 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 67.03 tokens</li><li>max: 128 tokens</li></ul> |
 * Samples:
   | anchor                                                                                                    | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
   |:----------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -630,19 +629,19 @@ 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    | -             | 1.1142          | 0.5887                     | 0.5786                | 0.5836                       |
-| 0.2874 | 250  | 1.1156        | 0.8606          | 0.5535                     | 0.5483                | 0.5509                       |
-| 0.5747 | 500  | 0.972         | 0.8202          | 0.5383                     | 0.5521                | 0.5452                       |
-| 0.8621 | 750  | 0.9475        | 0.8071          | 0.5445                     | 0.5372                | 0.5409                       |
-| 1.1494 | 1000 | 0.924         | 0.8011          | 0.5444                     | 0.5591                | 0.5517                       |
-| 1.4368 | 1250 | 0.9108        | 0.7953          | 0.5390                     | 0.5372                | 0.5381                       |
-| 1.7241 | 1500 | 0.9024        | 0.7896          | 0.5473                     | 0.5381                | 0.5427                       |
-| 2.0115 | 1750 | 0.8971        | 0.7864          | 0.5539                     | 0.5201                | 0.5370                       |
-| 2.2989 | 2000 | 0.8815        | 0.7842          | 0.5580                     | 0.5329                | 0.5455                       |
-| 2.5862 | 2250 | 0.8791        | 0.7824          | 0.5569                     | 0.5286                | 0.5427                       |
-| 2.8736 | 2500 | 0.8667        | 0.7821          | 0.5565                     | 0.5188                | 0.5376                       |
-| 3.1609 | 2750 | 0.8709        | 0.7807          | 0.5536                     | 0.5213                | 0.5374                       |
-| 3.4483 | 3000 | 0.8642        | 0.7802          | 0.5522                     | 0.5277                | 0.5400                       |
+| 0      | 0    | -             | 2.5772          | 0.6530                     | 0.6552                | 0.6541                       |
+| 0.2874 | 250  | 1.4443        | 0.8286          | 0.6168                     | 0.5857                | 0.6012                       |
+| 0.5747 | 500  | 0.7965        | 0.7746          | 0.6253                     | 0.5651                | 0.5952                       |
+| 0.8621 | 750  | 0.7676        | 0.7581          | 0.6431                     | 0.5307                | 0.5869                       |
+| 1.1494 | 1000 | 0.7381        | 0.7493          | 0.6446                     | 0.5651                | 0.6048                       |
+| 1.4368 | 1250 | 0.7166        | 0.7433          | 0.6286                     | 0.5574                | 0.5930                       |
+| 1.7241 | 1500 | 0.7115        | 0.7380          | 0.6370                     | 0.5645                | 0.6008                       |
+| 2.0115 | 1750 | 0.7033        | 0.7349          | 0.6316                     | 0.5408                | 0.5862                       |
+| 2.2989 | 2000 | 0.678         | 0.7360          | 0.6380                     | 0.5270                | 0.5825                       |
+| 2.5862 | 2250 | 0.674         | 0.7345          | 0.6236                     | 0.5488                | 0.5862                       |
+| 2.8736 | 2500 | 0.6669        | 0.7330          | 0.6403                     | 0.5472                | 0.5937                       |
+| 3.1609 | 2750 | 0.6641        | 0.7331          | 0.6221                     | 0.5367                | 0.5794                       |
+| 3.4483 | 3000 | 0.6556        | 0.7334          | 0.6412                     | 0.5341                | 0.5876                       |
 
 
 ### 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"
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer"
 }

modules.json

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