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": "sentence-transformers/all-MiniLM-L6-v2",
+  "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": "4.39.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.39.0",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

config_setfit.json

@@ -0,0 +1,108 @@
+{
+  "normalize_embeddings": false,
+  "labels": [
+    "Acknowledging limitation(s) whilst stating a finding or contribution",
+    "Advising cautious interpretation of the findings",
+    "Commenting on the findings",
+    "Commenting on the strengths of the current study",
+    "Comparing the result: contradicting previous findings",
+    "Comparing the result: supporting previous findings",
+    "Contrasting sources with \u2018however\u2019 for emphasis",
+    "Describing previously used methods",
+    "Describing questionnaire design",
+    "Describing the characteristics of the participants",
+    "Describing the limitations of the current study",
+    "Describing the process: adverbs of manner",
+    "Describing the process: expressing purpose with for",
+    "Describing the process: infinitive of purpose",
+    "Describing the process: sequence words",
+    "Describing the process: statistical procedures",
+    "Describing the process: typical verbs in the passive form",
+    "Describing the process: using + instrument",
+    "Describing the research design and the methods used",
+    "Describing what other writers do in their published work",
+    "Detailing specific limitations",
+    "Establishing the importance of the topic for the discipline",
+    "Establishing the importance of the topic for the discipline: time frame given",
+    "Establishing the importance of the topic for the world or society",
+    "Establishing the importance of the topic for the world or society: time frame given",
+    "Establising the importance of the topic as a problem to be addressed",
+    "Explaining keywords (also refer to Defining Terms)",
+    "Explaining the provenance of articles for review",
+    "Explaining the provenance of the participants",
+    "Explaining the significance of the current study",
+    "Explaining the significance of the findings or contribution of the study",
+    "General comments on the relevant literature",
+    "General reference to previous research or scholarship: highlighting negative outcomes",
+    "Giving reasons for personal interest in the research (sometimes found in the humanities, and the applied human sciences)",
+    "Giving reasons why a particular method was adopted",
+    "Giving reasons why a particular method was rejected",
+    "Highlighting inadequacies or weaknesses of previous studies (also refer to Being Critical)",
+    "Highlighting interesting or surprising results",
+    "Highlighting significant data in a table or chart",
+    "Identifying a controversy within the field of study",
+    "Identifying a knowledge gap in the field of study",
+    "Implications and/or recommendations for practice or policy",
+    "Indicating an expected outcome",
+    "Indicating an unexpected outcome",
+    "Indicating criteria for selection or inclusion in the study",
+    "Indicating methodological problems or limitations",
+    "Indicating missing, weak, or contradictory evidence",
+    "Indicating the methodology for the current research",
+    "Indicating the use of an established method",
+    "Introducing the limitations of the current study",
+    "Making recommendations for further research work",
+    "Noting implications of the findings",
+    "Noting the lack of or paucity of previous research",
+    "Offering an explanation for the findings",
+    "Outlining the structure of a short paper",
+    "Outlining the structure of a thesis or dissertation",
+    "Pointing out interesting or important findings",
+    "Previewing a chapter",
+    "Previous research: A historic perspective",
+    "Previous research: Approaches taken",
+    "Previous research: What has been established or proposed",
+    "Previous research: area investigated as the sentence object",
+    "Previous research: area investigated as the sentence subject",
+    "Previous research: highlighting negative outcomes",
+    "Providing background information: reference to the literature",
+    "Providing background information: reference to the purpose of the study",
+    "Reference to previous research: important studies",
+    "Referring back to the purpose of the paper or study",
+    "Referring back to the research aims or procedures",
+    "Referring to a single investigation in the past: investigation prominent",
+    "Referring to a single investigation in the past: researcher prominent",
+    "Referring to another writer\u2019s idea(s) or position",
+    "Referring to data in a table or chart",
+    "Referring to important texts in the area of interest",
+    "Referring to previous work to establish what is already known",
+    "Referring to secondary sources",
+    "Referring to the literature to justify a method or approach ",
+    "Reporting positive and negative reactions",
+    "Restating a result or one of several results",
+    "Setting out the research questions or hypotheses",
+    "Some ways of introducing quotations",
+    "Stating a negative result",
+    "Stating a positive result",
+    "Stating purpose of the current research with reference to gaps or issues in the literature",
+    "Stating the aims of the current research (note frequent use of past tense)",
+    "Stating the focus, aim, or argument of a short paper",
+    "Stating the purpose of the thesis, dissertation, or research article (note use of present tense)",
+    "Stating what is currently known about the topic",
+    "Suggesting general hypotheses",
+    "Suggesting implications for what is already known",
+    "Suggestions for future work",
+    "Summarising the literature review",
+    "Summarising the main research findings",
+    "Summarising the results section",
+    "Summarising the studies reviewed",
+    "Surveys and interviews: Introducing excerpts from interview data",
+    "Surveys and interviews: Reporting participants\u2019 views",
+    "Surveys and interviews: Reporting proportions",
+    "Surveys and interviews: Reporting response rates",
+    "Surveys and interviews: Reporting themes",
+    "Synthesising sources: contrasting evidence or ideas",
+    "Synthesising sources: supporting evidence or ideas",
+    "Transition: moving to the next result"
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8511aae8825d3a996b23c7396fa18e39f8400be98c865e8a0715f18b54dbd22b
+size 90864192

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd905ee574c42dae304d3561c962c107f695fbf80e3139f6aa8eeaa8d505852
+size 367519

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": 256,
+  "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]"
+}