初始化项目，由ModelHub XC社区提供模型

Model: l3cube-pune/marathi-sentence-bert-nli
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,138 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+license: cc-by-4.0
+language: mr
+widget:
+- source_sentence: "शेतकऱ्यांचे डोळे आकाशाकडे लागले आहेत"
+  sentences:
+    - "आता शेतकऱ्यांचे डोळे आभाळाकडे लागले आहेत"
+    - "अन्नधान्य उत्पादनासाठी शेतकरी कष्ट करतात"
+    - "शहरात कचऱ्याचे ढीग दिसतात"
+  example_title: "Example 1"
+
+- source_sentence: "घटनेची माहिती मिळताच पोलिसांचा ताफा तेथे पोहोचला"
+  sentences:
+    - "पोलिसांना घटनेची माहिती मिळताच त्यांचे पथक घटनास्थळी पोहोचले"
+    - "तेव्हा पोलिसांनी त्यांच्या तक्रारीची दखल घेतली नाही"
+    - "दिवसाचा उत्तरार्ध कुटुंबासोबत मौजमजेत घालवाल"
+  example_title: "Example 2"
+
+- source_sentence: "पहिल्या पाच किलोमीटर अंतरासाठी पाच रुपये दर आकारण्यात येत आहे"
+  sentences:
+    - "पाच रुपयांत पाच किमी प्रवास करा"
+    - "दोन ठिकाणांमधले मोठे अंतर प्रवास करणे कंटाळवाणे आहे"
+    - "नुकत्याच झालेल्या पावसामुळे हिरवळ दिसत आहे"
+  example_title: "Example 3"
+---
+
+# MahaSBERT
+
+A MahaBERT model (l3cube-pune/marathi-bert-v2) trained on the NLI dataset. <br>
+This is released as a part of project MahaNLP: https://github.com/l3cube-pune/MarathiNLP <br>
+A multilingual version of this model supporting major Indic languages and cross-lingual capabilities is shared here <a href='https://huggingface.co/l3cube-pune/indic-sentence-bert-nli'> indic-sentence-bert-nli </a> <br>
+
+A better sentence similarity model(fine-tuned version of this model) is shared here: https://huggingface.co/l3cube-pune/marathi-sentence-similarity-sbert <br>
+
+More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2211.11187) 
+
+```
+@article{joshi2022l3cubemahasbert,
+  title={L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi},
+  author={Joshi, Ananya and Kajale, Aditi and Gadre, Janhavi and Deode, Samruddhi and Joshi, Raviraj},
+  journal={arXiv preprint arXiv:2211.11187},
+  year={2022}
+}
+```
+
+<a href='https://arxiv.org/abs/2211.11187'> monolingual Indic SBERT paper </a> <br>
+<a href='https://arxiv.org/abs/2304.11434'> multilingual Indic SBERT paper </a>
+
+Other Monolingual Indic sentence BERT models are listed below: <br>
+<a href='https://huggingface.co/l3cube-pune/marathi-sentence-bert-nli'> Marathi SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/hindi-sentence-bert-nli'> Hindi SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/kannada-sentence-bert-nli'> Kannada SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/telugu-sentence-bert-nli'> Telugu SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/malayalam-sentence-bert-nli'> Malayalam SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/tamil-sentence-bert-nli'> Tamil SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/gujarati-sentence-bert-nli'> Gujarati SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/odia-sentence-bert-nli'> Oriya SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/bengali-sentence-bert-nli'> Bengali SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/punjabi-sentence-bert-nli'> Punjabi SBERT</a> <br>
+<a href='https://huggingface.co/l3cube-pune/indic-sentence-bert-nli'> Indic SBERT (multilingual)</a> <br>
+
+Other Monolingual similarity models are listed below: <br>
+<a href='https://huggingface.co/l3cube-pune/marathi-sentence-similarity-sbert'> Marathi Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/hindi-sentence-similarity-sbert'> Hindi Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/kannada-sentence-similarity-sbert'> Kannada Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/telugu-sentence-similarity-sbert'> Telugu Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/malayalam-sentence-similarity-sbert'> Malayalam Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/tamil-sentence-similarity-sbert'> Tamil Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/gujarati-sentence-similarity-sbert'> Gujarati Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/odia-sentence-similarity-sbert'> Oriya Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/bengali-sentence-similarity-sbert'> Bengali Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/punjabi-sentence-similarity-sbert'> Punjabi Similarity </a> <br>
+<a href='https://huggingface.co/l3cube-pune/indic-sentence-similarity-sbert'> Indic Similarity (multilingual)</a> <br>
+
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 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
+
+
+def cls_pooling(model_output, attention_mask):
+    return model_output[0][:,0]
+
+
+# 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, cls pooling.
+sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "l3cube-pune/marathi-sentence-bert-nli/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 197285
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.22.2",
+    "pytorch": "1.12.1+cu113"
+  }
+}

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 sha256:9a7f4ec8d2268a448037f255a09f66830bae83a4330fc00c941e5aa84bfcc191
+size 950291505

sentence_bert_config.json

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

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 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "l3cube-pune/marathi-sentence-bert-nli/",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/ebs_ds_share/raviraj.j/temp/models/muril-base-cased/special_tokens_map.json",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}