Add SetFit model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 1024,
+  "word_embedding_dimension": 768,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

config.json

@@ -1,51 +1,24 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/facebook_bart-large-mnli",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_final_layer_norm": false,
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-mpnet-base-v2/",
   "architectures": [
-    "BartModel"
+    "MPNetModel"
   ],
-  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "contradiction",
-    "1": "neutral",
-    "2": "entailment"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "contradiction": 0,
-    "entailment": 2,
-    "neutral": 1
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "normalize_before": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": false,
   "pad_token_id": 1,
-  "scale_embedding": false,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30527
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.2.2",
-    "transformers": "4.35.0",
-    "pytorch": "2.1.0+cu118"
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7149c85c69fda5d7627ab364985fbf690de294bae1443757b2aab2ab40602b7
-size 1625222792
+oid sha256:d712cc6aa9a637365fd60245367085cc6e285375a4e724c485da89dbd325554b
+size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21322e35074912a1170547308992816bfae6c66dd7ded35f5298c7d60daa364b
-size 50071
+oid sha256:a9b6b8870e4bcc7390edc41d76bd30b514829aec524da823dc1a023bd5c2a95d
+size 37783

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 1024,
+  "max_seq_length": 512,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,15 +1,51 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +11,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,23 +19,23 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "30526": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -45,13 +44,16 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "eos_token": "</s>",
-  "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 1024,
+  "model_max_length": 512,
+  "never_split": null,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
 }