Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "checkpoints/step_19800",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

config_setfit.json

@@ -0,0 +1,105 @@
+{
+  "labels": [
+    "governing laws",
+    "counterparts",
+    "notices",
+    "entire agreements",
+    "severability",
+    "waivers",
+    "amendments",
+    "expenses",
+    "survival",
+    "representations",
+    "assigns",
+    "taxes",
+    "litigations",
+    "insurances",
+    "confidentiality",
+    "waiver of jury trials",
+    "terminations",
+    "further assurances",
+    "general",
+    "terms",
+    "assignments",
+    "authority",
+    "use of proceeds",
+    "payments",
+    "compliance with laws",
+    "no conflicts",
+    "indemnifications",
+    "organizations",
+    "base salary",
+    "binding effects",
+    "headings",
+    "costs",
+    "definitions",
+    "modifications",
+    "remedies",
+    "releases",
+    "disclosures",
+    "participations",
+    "vesting",
+    "no waivers",
+    "withholdings",
+    "miscellaneous",
+    "jurisdictions",
+    "closings",
+    "integration",
+    "fees",
+    "effective dates",
+    "enforcements",
+    "financial statements",
+    "capitalization",
+    "benefits",
+    "interpretations",
+    "subsidiaries",
+    "solvency",
+    "cooperation",
+    "approvals",
+    "construction",
+    "intellectual property",
+    "brokers",
+    "enforceability",
+    "authorizations",
+    "consents",
+    "tax withholdings",
+    "arbitration",
+    "transactions with affiliates",
+    "applicable laws",
+    "defined terms",
+    "change in control",
+    "no defaults",
+    "adjustments",
+    "non-disparagement",
+    "employment",
+    "positions",
+    "erisa",
+    "warranties",
+    "disability",
+    "interests",
+    "duties",
+    "specific performance",
+    "anti-corruption laws",
+    "vacations",
+    "generally",
+    "publicity",
+    "choice of laws",
+    "liens",
+    "death",
+    "purposes",
+    "information",
+    "compensation",
+    "consent to jurisdiction",
+    "successors",
+    "limitation of liability",
+    "books",
+    "exercise price",
+    "register",
+    "powers",
+    "good standings",
+    "transferability",
+    "permits",
+    "existence"
+  ],
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5153d1810889b57bcd6f17b48eb3c80bdf230116f9ba70875f98013024e5d5f
+size 90864192

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3e1d218e79f115b725eb69f41f8e571f338eff8f955335fe0b4b924f76b6a0
+size 320039

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "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

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}