Add SetFit model

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
   "word_embedding_dimension": 768,
-  "pooling_mode_cls_token": true,
-  "pooling_mode_mean_tokens": false,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,
   "pooling_mode_mean_sqrt_len_tokens": false
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/datascience/.cache/torch/sentence_transformers/sentence-transformers_multi-qa-mpnet-base-dot-v1/",
+  "_name_or_path": "/home/datascience/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-mpnet-base-v2/",
   "architectures": [
     "MPNetModel"
   ],

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.0.0",
-    "transformers": "4.6.1",
-    "pytorch": "1.8.1"
+    "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 sha256:13fe61d92cef49c5324dad0ad1f759a563d2421fb2399b1649eef6ef581e4d41
+oid sha256:84998b8483e4df7ab09aed7496b032cc922f079bc47fc6d29d2a7c3047a05e5b
 size 6991

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c1c24e22cd448f15a58d5bbe5747010860668028f20cdfdda3c4006e01371e
+oid sha256:45496c68bd7c7cfc85678bdaeeb9c6676f6420b2629875e9db0ddea0b8101fac
 size 438016493

tokenizer.json

@@ -42,15 +42,6 @@
       "normalized": false,
       "special": true
     },
-    {
-      "id": 3,
-      "content": "<unk>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": true
-    },
     {
       "id": 104,
       "content": "[UNK]",
@@ -81,17 +72,85 @@
     "type": "BertPreTokenizer"
   },
   "post_processor": {
-    "type": "RobertaProcessing",
-    "sep": [
-      "</s>",
-      2
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      }
     ],
-    "cls": [
-      "<s>",
-      0
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 1
+        }
+      }
     ],
-    "trim_offsets": true,
-    "add_prefix_space": false
+    "special_tokens": {
+      "</s>": {
+        "id": "</s>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "</s>"
+        ]
+      },
+      "<s>": {
+        "id": "<s>",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "<s>"
+        ]
+      }
+    }
   },
   "decoder": {
     "type": "WordPiece",

tokenizer_config.json

@@ -1,15 +1,66 @@
 {
-  "bos_token": "<s>",
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_basic_tokenize": true,
   "do_lower_case": true,
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "never_split": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "MPNetTokenizer",
-  "unk_token": "[UNK]"
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }