Add SetFit model

.gitattributes

@@ -33,3 +33,5 @@ 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": 768,
+  "word_embedding_dimension": 384,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

added_tokens.json

@@ -1,8 +1,7 @@
 {
   "</s>": 2,
-  "<mask>": 30526,
+  "<mask>": 250001,
   "<pad>": 1,
   "<s>": 0,
-  "<unk>": 3,
-  "[UNK]": 104
+  "<unk>": 3
 }

config.json

@@ -1,24 +1,26 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-mpnet-base-v2/",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/",
   "architectures": [
-    "MPNetModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
+  "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": 1,
-  "relative_attention_num_buckets": 32,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
-  "vocab_size": 30527
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
 }

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:dbe1b7dcdc2482ce048e4d02af7f45e7f133f9aa6030f05f3782a89999438006
-size 16267
+oid sha256:97ebfc7e938324767d411e952f5675c981bc3456104b3f6fb7542dc344f4ff41
+size 16315

modules.json

@@ -10,11 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89512a7c06eb96f01e31cf2738e5f211fa6f105f40d5c8c830f70c6e6a865a87
-size 438012073
+oid sha256:f200c48728cbd35ceabc83323f8de2826324d1dc32365a056a271d8e7f27291d
+size 470681769

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 384,
+  "max_seq_length": 128,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -5,5 +5,5 @@
   "mask_token": "<mask>",
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -27,20 +27,12 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "104": {
-      "content": "[UNK]",
-      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "30526": {
+    "250001": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
@@ -66,8 +58,8 @@
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "MPNetTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260