Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,49 @@
+---
+license: apache-2.0
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+pipeline_tag: text-classification
+---
+
+# njprogrammer/goemotion-BERT
+
+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:
+
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
+
+## Usage
+
+To use this model for inference, first install the SetFit library:
+
+```bash
+python -m pip install setfit
+```
+
+You can then run inference as follows:
+
+```python
+from setfit import SetFitModel
+
+# Download from Hub and run inference
+model = SetFitModel.from_pretrained("njprogrammer/goemotion-BERT")
+# Run inference
+preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
+```
+
+## BibTeX entry and citation info
+
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+doi = {10.48550/ARXIV.2209.11055},
+url = {https://arxiv.org/abs/2209.11055},
+author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+title = {Efficient Few-Shot Learning Without Prompts},
+publisher = {arXiv},
+year = {2022},
+copyright = {Creative Commons Attribution 4.0 International}
+}
+```

config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "C:\\Users\\njpark/.cache\\torch\\sentence_transformers\\monologg_bert-base-cased-goemotions-original",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "goemotions",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "admiration",
+    "1": "amusement",
+    "2": "anger",
+    "3": "annoyance",
+    "4": "approval",
+    "5": "caring",
+    "6": "confusion",
+    "7": "curiosity",
+    "8": "desire",
+    "9": "disappointment",
+    "10": "disapproval",
+    "11": "disgust",
+    "12": "embarrassment",
+    "13": "excitement",
+    "14": "fear",
+    "15": "gratitude",
+    "16": "grief",
+    "17": "joy",
+    "18": "love",
+    "19": "nervousness",
+    "20": "optimism",
+    "21": "pride",
+    "22": "realization",
+    "23": "relief",
+    "24": "remorse",
+    "25": "sadness",
+    "26": "surprise",
+    "27": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "admiration": 0,
+    "amusement": 1,
+    "anger": 2,
+    "annoyance": 3,
+    "approval": 4,
+    "caring": 5,
+    "confusion": 6,
+    "curiosity": 7,
+    "desire": 8,
+    "disappointment": 9,
+    "disapproval": 10,
+    "disgust": 11,
+    "embarrassment": 12,
+    "excitement": 13,
+    "fear": 14,
+    "gratitude": 15,
+    "grief": 16,
+    "joy": 17,
+    "love": 18,
+    "nervousness": 19,
+    "neutral": 27,
+    "optimism": 20,
+    "pride": 21,
+    "realization": 22,
+    "relief": 23,
+    "remorse": 24,
+    "sadness": 25,
+    "surprise": 26
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.30.2",
+    "pytorch": "1.8.1+cu111"
+  }
+}

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33fd01870205b60c87d2af80a1c75f041268c4fa7045f5b9ff266fd4a26eec9b
+size 87446

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0027df0550466df7abb3961d32a1c11191a7cdb257f4acbe1c323ba548793d8
+size 433315311

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "[NAME]",
+    "[RELIGION]"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "[NAME]",
+    "[RELIGION]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}