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 +1,24 @@
 {
-  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
   "architectures": [
-    "BertModel"
+    "MPNetModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "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": "mpnet",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30527
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1c6660937b2350e81526d4879400b3f08ba70914fa27baa2edaa23e3d52d0e
-size 90864192
+oid sha256:93d8ec5cf4993b6118c047c778a0908df55234ccb264f1ef670586212a125db3
+size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1645a15eadc80fd753d7996dbb8a018aebf872391b24e914d62dc9b70ff5e8ca
-size 3935
+oid sha256:8207c4f135bca54b9f77b173c4c5ac47c8984b9078530da97abb579d11375cda
+size 7007

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
+  "max_seq_length": 384,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,27 +1,41 @@
 {
+  "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,

tokenizer_config.json

@@ -1,63 +1,71 @@
 {
   "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,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30526": {
+      "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": 256,
-  "never_split": null,
+  "model_max_length": 384,
   "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "MPNetTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"

vocab.txt

@@ -1,3 +1,7 @@
+<s>
+<pad>
+</s>
+<unk>
 [PAD]
 [unused0]
 [unused1]
@@ -30520,3 +30524,4 @@ necessitated
 ##：
 ##？
 ##～
+<mask>