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,

README.md

@@ -7,7 +7,7 @@ tags:
 pipeline_tag: text-classification
 ---
 
-# /var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpvyuta4a1/abolton99/test
+# /var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpj7_chx3l/abolton99/test
 
 This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -28,7 +28,7 @@ You can then run inference as follows:
 from setfit import SetFitModel
 
 # Download from Hub and run inference
-model = SetFitModel.from_pretrained("/var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpvyuta4a1/abolton99/test")
+model = SetFitModel.from_pretrained("/var/folders/gr/47hycvx13rd_q25kzttvfx6h0000gn/T/tmpj7_chx3l/abolton99/test")
 # Run inference
 preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
 ```

config.json

@@ -1,26 +1,24 @@
 {
-  "_name_or_path": "/Users/angusbolton/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/",
+  "_name_or_path": "/Users/angusbolton/.cache/torch/sentence_transformers/abolton99_test/",
   "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": "4.35.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30527
 }

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.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a90ca87c80771f3cbe7aa4fcfa5acd7299bc3f54bec3a9736a91473ce55080
-size 90864192
+oid sha256:42d2dfbac68a035b369313412d2630e74f94bf036fb1d8dd04a9cfb535592531
+size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1ac6602d8bb102aa2e137261b171bf1f6ff62f4c005d36faf6d8a0f3599a4e
-size 3919
+oid sha256:2074cf73030138980c88bccb535e90d1cc6599e720442f0cab219074e3d471c3
+size 6991

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"
   }
 ]

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
+  "max_seq_length": 512,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,63 +1,65 @@
 {
   "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]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "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]",
+  "cls_token": "<s>",
   "do_basic_tokenize": true,
   "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "max_length": 128,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
   "never_split": null,
   "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>