add model

1_Pooling/config.json

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

README.md

@@ -1,3 +1,55 @@
 ---
+language: en
 license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+pipeline_tag: sentence-similarity
 ---
+
+Distilbert encoder models trained on European law document tagging dataset (EURLex-4K) using [DEXML](https://github.com/nilesh2797/DEXML) ([Dual Encoder for eXtreme Multi-Label classification, ICLR'24](https://arxiv.org/pdf/2310.10636v2.pdf)) method.
+
+## Inference Usage (Sentence-Transformers)
+With `sentence-transformers` installed you can use this model as following:
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+model = SentenceTransformer('quicktensor/dexml_eurlex-4k')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Usage (HuggingFace Transformers)
+With huggingface transformers you only need to be a bit careful with how you pool the transformer output to get the embedding, you can use this model as following;
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+import torch.nn.functional as F
+
+pooler = lambda x: F.normalize(x[:, 0, :], dim=-1) # Choose CLS token and normalize
+
+sentences = ["This is an example sentence", "Each sentence is converted"]
+tokenizer = AutoTokenizer.from_pretrained('quicktensor/dexml_eurlex-4k')
+model = AutoModel.from_pretrained('quicktensor/dexml_eurlex-4k')
+
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+with torch.no_grad():
+    embeddings = pooler(model(**encoded_input))
+
+print(embeddings)
+```
+
+## Cite
+If you found this model helpful, please cite our work as:
+```bib
+@InProceedings{DEXML,
+  author    = "Gupta, N. and Khatri, D. and Rawat, A-S. and Bhojanapalli, S. and Jain, P. and Dhillon, I.",
+  title     = "Dual-encoders for Extreme Multi-label Classification",
+  booktitle = "International Conference on Learning Representations",
+  month     = "May",
+  year      = "2024"
+}
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+    "__version__": {
+      "sentence_transformers": "2.0.0",
+      "transformers": "4.6.1",
+      "pytorch": "1.8.1"
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2fea4964b4a280e1bc8de2a03e4b6b61788f6bc12933c36efc287efef2b224
+size 265462608

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": 128,
+    "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}