Add SetFit model

.gitattributes

@@ -33,3 +33,5 @@ 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
+unigram.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -5,7 +5,7 @@ tags:
 - sentence-transformers
 - text-classification
 - generated_from_setfit_trainer
-base_model: sentence-transformers/paraphrase-MiniLM-L6-v2
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
 metrics:
 - accuracy
 widget:
@@ -96,9 +96,9 @@ pipeline_tag: text-classification
 inference: false
 ---
 
-# SetFit with sentence-transformers/paraphrase-MiniLM-L6-v2
+# SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -109,7 +109,7 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [sentence-transformers/paraphrase-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-v2)
+- **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
 - **Classification head:** a OneVsRestClassifier instance
 - **Maximum Sequence Length:** 128 tokens
 <!-- - **Number of Classes:** Unknown -->
@@ -177,7 +177,7 @@ preds = model("Mitarbeit am wissenschaftlichen Arbeitsplatz (LV0125)")
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
-- num_epochs: (1, 1)
+- num_epochs: (2, 2)
 - max_steps: -1
 - sampling_strategy: oversampling
 - num_iterations: 20
@@ -197,25 +197,43 @@ preds = model("Mitarbeit am wissenschaftlichen Arbeitsplatz (LV0125)")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0011 | 1    | 0.2952        | -               |
-| 0.0552 | 50   | 0.2217        | -               |
-| 0.1105 | 100  | 0.1748        | -               |
-| 0.1657 | 150  | 0.15          | -               |
-| 0.2210 | 200  | 0.1397        | -               |
-| 0.2762 | 250  | 0.1241        | -               |
-| 0.3315 | 300  | 0.1208        | -               |
-| 0.3867 | 350  | 0.1128        | -               |
-| 0.4420 | 400  | 0.1044        | -               |
-| 0.4972 | 450  | 0.1121        | -               |
-| 0.5525 | 500  | 0.106         | -               |
-| 0.6077 | 550  | 0.1069        | -               |
-| 0.6630 | 600  | 0.098         | -               |
-| 0.7182 | 650  | 0.0921        | -               |
-| 0.7735 | 700  | 0.0986        | -               |
-| 0.8287 | 750  | 0.0838        | -               |
-| 0.8840 | 800  | 0.091         | -               |
-| 0.9392 | 850  | 0.0934        | -               |
-| 0.9945 | 900  | 0.0954        | -               |
+| 0.0011 | 1    | 0.2964        | -               |
+| 0.0552 | 50   | 0.2042        | -               |
+| 0.1105 | 100  | 0.1643        | -               |
+| 0.1657 | 150  | 0.1376        | -               |
+| 0.2210 | 200  | 0.1232        | -               |
+| 0.2762 | 250  | 0.1125        | -               |
+| 0.3315 | 300  | 0.1079        | -               |
+| 0.3867 | 350  | 0.0951        | -               |
+| 0.4420 | 400  | 0.0847        | -               |
+| 0.4972 | 450  | 0.0917        | -               |
+| 0.5525 | 500  | 0.085         | -               |
+| 0.6077 | 550  | 0.0758        | -               |
+| 0.6630 | 600  | 0.0743        | -               |
+| 0.7182 | 650  | 0.0671        | -               |
+| 0.7735 | 700  | 0.0743        | -               |
+| 0.8287 | 750  | 0.0571        | -               |
+| 0.8840 | 800  | 0.0625        | -               |
+| 0.9392 | 850  | 0.0607        | -               |
+| 0.9945 | 900  | 0.0686        | -               |
+| 1.0497 | 950  | 0.0541        | -               |
+| 1.1050 | 1000 | 0.0553        | -               |
+| 1.1602 | 1050 | 0.0565        | -               |
+| 1.2155 | 1100 | 0.0558        | -               |
+| 1.2707 | 1150 | 0.0578        | -               |
+| 1.3260 | 1200 | 0.0525        | -               |
+| 1.3812 | 1250 | 0.0541        | -               |
+| 1.4365 | 1300 | 0.049         | -               |
+| 1.4917 | 1350 | 0.0485        | -               |
+| 1.5470 | 1400 | 0.0475        | -               |
+| 1.6022 | 1450 | 0.0479        | -               |
+| 1.6575 | 1500 | 0.0514        | -               |
+| 1.7127 | 1550 | 0.0509        | -               |
+| 1.7680 | 1600 | 0.0517        | -               |
+| 1.8232 | 1650 | 0.0455        | -               |
+| 1.8785 | 1700 | 0.0493        | -               |
+| 1.9337 | 1750 | 0.0501        | -               |
+| 1.9890 | 1800 | 0.0492        | -               |
 
 ### Framework Versions
 - Python: 3.12.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sentence-transformers/paraphrase-MiniLM-L6-v2",
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
   "architectures": [
     "BertModel"
   ],
@@ -15,12 +15,12 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.43.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 250037
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94453a28695f826bd7955817136533b0d3cd57f03a9f4b5907b986b8d419d207
-size 90864192
+oid sha256:42e2383eb5474eed20c60c6a3fad5e648145652feb7e0764fbec3bdb0749421a
+size 470637416

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a432ee29f7090fa5a16b651ad4b4773ae8eecf202bb18dc4b5f0bfa5051115
+oid sha256:480e709d8a111a96f8c6ae0719ba08c423e620951ab490a55a242b2022be5623
 size 21396

special_tokens_map.json

@@ -1,34 +1,48 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,57 +1,64 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
+  "cls_token": "<s>",
   "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 128,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
 }

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260