Add SetFit model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 384,
+  "word_embedding_dimension": 768,
   "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/sentence-transformers_paraphrase-xlm-r-multilingual-v1/",
   "architectures": [
-    "BertModel"
+    "XLMRobertaModel"
   ],
   "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": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250037
+  "vocab_size": 250002
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a10c8bbb82c44c8a949b48139828b5fd6f9b6436996efac5fa8a9db0c0f3ac
-size 3919
+oid sha256:a409da806c687f95523839df607a32b902fd87398d045a369825f0a24e3104fa
+size 6991

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872f16a84a550207929706a5b0d75b15522e4f915140f5465fb36bbe71b4c85b
-size 470681769
+oid sha256:0b68eb592cbf9de7ce5c3aa004d19a70b05cb832ff29b55ae7034c6851b90989
+size 1112241321

special_tokens_map.json

@@ -2,13 +2,7 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
-size 17082913
+oid sha256:40e4a12784b3e7ee5c5c373c28a22f02497b30a4ea39d9548ee0f3c6a31e9ca9
+size 17082983

tokenizer_config.json

@@ -2,8 +2,8 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": true,
   "eos_token": "</s>",
+  "full_tokenizer_file": null,
   "mask_token": {
     "__type": "AddedToken",
     "content": "<mask>",
@@ -15,8 +15,7 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }