Add SetFit model

1_Pooling/config.json

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

config.json

@@ -1,26 +1,29 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/dangvantuan_sentence-camembert-large",
   "architectures": [
-    "BertModel"
+    "CamembertModel"
   ],
   "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": 384,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "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,
+  "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,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250037
+  "vocab_size": 32005
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "2.0.0+cu118"
   }
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcfff30f5180369d54cd8f4c8a8df47eeb15f36b8828aab526a9f39ebda2dda8
-size 13175
+oid sha256:1701c157edd9142887618177c4eadff39a8130f8b8557a27bafeb2c8818de119
+size 33655

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbc82b78933613e3ebcec889190807f528973c19b23e78daefaba85083642bc
-size 470686253
+oid sha256:de9abdc1c6a7b4c9b0d938557abfdd52bebd4e5b49d660ea41b6c120c71846ec
+size 1346782317

sentence_bert_config.json

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
+size 808767

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
-size 17082913
+oid sha256:da4a19b41f008689418c2e004192b6eeca0292138a0ef0c775d7dfaf70584a0c
+size 2418775

tokenizer_config.json

@@ -1,8 +1,11 @@
 {
+  "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",
@@ -12,11 +15,10 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }