Add SetFit model

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9cb48efa0eb9798c4b961434f13f179144d9f0397138460c27b5d5d92e0e61
+size 1575072

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: akhooli/Arabic-SBERT-100K
+base_model: sentence-transformers/distiluse-base-multilingual-cased-v1
 library_name: setfit
 metrics:
 - accuracy
@@ -35,7 +35,7 @@ widget:
     فالفندق
 inference: true
 model-index:
-- name: SetFit with akhooli/Arabic-SBERT-100K
+- name: SetFit with sentence-transformers/distiluse-base-multilingual-cased-v1
   results:
   - task:
       type: text-classification
@@ -46,13 +46,13 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.5005050505050505
+      value: 0.45696969696969697
       name: Accuracy
 ---
 
-# SetFit with akhooli/Arabic-SBERT-100K
+# SetFit with sentence-transformers/distiluse-base-multilingual-cased-v1
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [akhooli/Arabic-SBERT-100K](https://huggingface.co/akhooli/Arabic-SBERT-100K) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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/distiluse-base-multilingual-cased-v1](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v1) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -63,9 +63,9 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [akhooli/Arabic-SBERT-100K](https://huggingface.co/akhooli/Arabic-SBERT-100K)
+- **Sentence Transformer body:** [sentence-transformers/distiluse-base-multilingual-cased-v1](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v1)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
-- **Maximum Sequence Length:** 512 tokens
+- **Maximum Sequence Length:** 128 tokens
 - **Number of Classes:** 3 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -89,7 +89,7 @@ The model has been trained using an efficient few-shot learning technique that i
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.5005   |
+| **all** | 0.4570   |
 
 ## Uses
 
@@ -170,11 +170,11 @@ preds = model("مكان راحه البال . المكان نظيف جدا وم
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.1667 | 1    | 0.2506        | -               |
-| 1.0    | 6    | -             | 0.2707          |
-| 2.0    | 12   | -             | 0.2555          |
-| 3.0    | 18   | -             | 0.2677          |
-| 4.0    | 24   | -             | 0.2754          |
+| 0.1667 | 1    | 0.3001        | -               |
+| 1.0    | 6    | -             | 0.2727          |
+| 2.0    | 12   | -             | 0.2697          |
+| 3.0    | 18   | -             | 0.2861          |
+| 4.0    | 24   | -             | 0.2927          |
 
 ### Framework Versions
 - Python: 3.10.14

config.json

@@ -1,25 +1,24 @@
 {
-  "_name_or_path": "akhooli/Arabic-SBERT-100K",
+  "_name_or_path": "sentence-transformers/distiluse-base-multilingual-cased-v1",
+  "activation": "gelu",
   "architectures": [
-    "BertModel"
+    "DistilBertModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.45.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 64000
+  "vocab_size": 119547
 }

config_setfit.json

@@ -1,8 +1,8 @@
 {
-  "normalize_embeddings": false,
   "labels": [
     "Mixed",
     "Negative",
     "Positive"
-  ]
+  ],
+  "normalize_embeddings": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a56c33d50e4ea6defd40d5c06e9feb367b7d6e473eb03e975cf65f772deab63
-size 540795752
+oid sha256:d84bc88a6b764709dd4fa7c3e29b7e36f3de9d5cec70e876f2bbb6de150c320c
+size 538947416

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4e48c683cb7411d3312fb65609c7d3b5ee2bfba3b96357f2e84b85a38abad1
-size 19375
+oid sha256:efddb0394f5ff4e41d62c78c799c5d0d3e8c2ce18e25a2029ccd99028a8890cb
+size 13231

modules.json

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

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 128,
   "do_lower_case": false
 }

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,62 +32,27 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "5": {
-      "content": "[رابط]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": true,
-      "special": true
-    },
-    "6": {
-      "content": "[بريد]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": true,
-      "special": true
-    },
-    "7": {
-      "content": "[مستخدم]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": true,
-      "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "max_len": 512,
-  "max_length": 512,
-  "model_max_length": 512,
-  "never_split": [
-    "[بريد]",
-    "[مستخدم]",
-    "[رابط]"
-  ],
-  "pad_to_multiple_of": null,
+  "model_max_length": 128,
+  "never_split": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }