Add SetFit model

.gitattributes

@@ -32,3 +32,5 @@ 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

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 1024,
+  "word_embedding_dimension": 384,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

config.json

@@ -1,29 +1,26 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/IslemTouati_french_model/",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/",
   "architectures": [
-    "CamembertModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "camembert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 1,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
-  "type_vocab_size": 1,
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 32005
+  "vocab_size": 250037
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.2.2",
-    "transformers": "4.29.2",
-    "pytorch": "2.0.0+cu118"
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
   }
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1dfe44138d2dadce3d4e1bae88902490d1783c5c75e87f1489b962462055b8
-size 33655
+oid sha256:6fac7146a37c2d6fa0844c611b032052811aff4746f30f693b456e39c643893d
+size 13175

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db1e118c954962b0a8629a282323366501c7503c4d1296060aa5fd42e5d51e6
-size 1346782317
+oid sha256:0f9f5bd96021515b9b9757a66506876946f1ba1209ee26a75f682269f553fc58
+size 470683437

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 514,
+  "max_seq_length": 128,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,15 +1,11 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED"
-  ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer_config.json

@@ -1,11 +1,8 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
+  "do_lower_case": true,
   "eos_token": "</s>",
   "mask_token": {
     "__type": "AddedToken",
@@ -15,10 +12,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "CamembertTokenizer",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "<unk>"
 }

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
+size 14763234