Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,130 @@
+---
+tags:
+- text-classification
+- transformers
+language:
+- en
+metrics:
+- accuracy
+- precision
+- recall
+library_name: transformers
+pipeline_tag: text-classification
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 14756 with parameters:
+```
+{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 0,
+    "evaluator": "NoneType",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": 14756,
+    "warmup_steps": 1476,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BartModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,119 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Mamoona/Huggingface_model/HIMsetfitMultiLabelModel2epochs/",
+  "_num_labels": 36,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": "atmosphere",
+    "1": "beer list",
+    "2": "bottomless brunch",
+    "3": "breakfast",
+    "4": "brunch",
+    "5": "business",
+    "6": "byob",
+    "7": "casual",
+    "8": "date night",
+    "9": "delivery",
+    "10": "fine dining",
+    "11": "gluten free",
+    "12": "good value",
+    "13": "great cocktails",
+    "14": "great service",
+    "15": "happy hour",
+    "16": "healthy",
+    "17": "instagrammable",
+    "18": "kid friendly",
+    "19": "large groups",
+    "20": "late night",
+    "21": "live music",
+    "22": "lunch",
+    "23": "night out",
+    "24": "outdoor seating",
+    "25": "quick",
+    "26": "romantic",
+    "27": "rooftop",
+    "28": "small plates",
+    "29": "special event",
+    "30": "sports/tvs",
+    "31": "takeout",
+    "32": "tasting menu",
+    "33": "vegetarian",
+    "34": "walk-in",
+    "35": "wine list"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "atmosphere": 0,
+    "beer list": 1,
+    "bottomless brunch": 2,
+    "breakfast": 3,
+    "brunch": 4,
+    "business": 5,
+    "byob": 6,
+    "casual": 7,
+    "date night": 8,
+    "delivery": 9,
+    "fine dining": 10,
+    "gluten free": 11,
+    "good value": 12,
+    "great cocktails": 13,
+    "great service": 14,
+    "happy hour": 15,
+    "healthy": 16,
+    "instagrammable": 17,
+    "kid friendly": 18,
+    "large groups": 19,
+    "late night": 20,
+    "live music": 21,
+    "lunch": 22,
+    "night out": 23,
+    "outdoor seating": 24,
+    "quick": 25,
+    "romantic": 26,
+    "rooftop": 27,
+    "small plates": 28,
+    "special event": 29,
+    "sports/tvs": 30,
+    "takeout": 31,
+    "tasting menu": 32,
+    "vegetarian": 33,
+    "walk-in": 34,
+    "wine list": 35
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "multi_target_strategy": "multi-output",
+  "normalize_before": false,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "problem_type": "multi_label_classification",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.26.0",
+    "pytorch": "1.13.1+cu116"
+  }
+}

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a30431b5d6c36262536b263a16f2d4e3d6bbe7bf442ba377efc2c988c20b93
+size 309489

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 sha256:0a686fb75bb5b1c11fd33c8602b89bf4b16b877c3dc55a429df630b3018bd4f5
+size 1625329737

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 1024,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "name_or_path": "/content/drive/MyDrive/Mamoona/Huggingface_model/HIMsetfitMultiLabelModel2epochs/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}