Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "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,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,112 @@
+---
+pipeline_tag: sentence-similarity
+license: apache-2.0
+language:
+- cs
+- da
+- de
+- en
+- es
+- fi
+- fr
+- he
+- hr
+- hu
+- id
+- it
+- nl
+- 'no'
+- pl
+- pt
+- ro
+- ru
+- sv
+- tr
+- vi
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+datasets:
+- clips/mfaq
+widget:
+  - text: "<Q>How many models can I host on HuggingFace?"
+    example_title: source_sentence
+---
+
+# MFAQ
+
+We present a multilingual FAQ retrieval model trained on the [MFAQ dataset](https://huggingface.co/datasets/clips/mfaq), it ranks candidate answers according to a given question.
+
+## Installation
+
+```
+pip install sentence-transformers transformers
+```
+
+## Usage
+You can use MFAQ with sentence-transformers or directly with a HuggingFace model. 
+In both cases, questions need to be prepended with `<Q>`, and answers with `<A>`.
+
+#### Sentence Transformers
+```python
+from sentence_transformers import SentenceTransformer
+
+question = "<Q>How many models can I host on HuggingFace?"
+answer_1 = "<A>All plans come with unlimited private models and datasets."
+answer_2 = "<A>AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem."
+answer_3 = "<A>Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job."
+
+model = SentenceTransformer('clips/mfaq')
+embeddings = model.encode([question, answer_1, answer_3, answer_3])
+print(embeddings)
+```
+
+#### HuggingFace Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+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)
+
+question = "<Q>How many models can I host on HuggingFace?"
+answer_1 = "<A>All plans come with unlimited private models and datasets."
+answer_2 = "<A>AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem."
+answer_3 = "<A>Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job."
+
+tokenizer = AutoTokenizer.from_pretrained('clips/mfaq')
+model = AutoModel.from_pretrained('clips/mfaq')
+
+# Tokenize sentences
+encoded_input = tokenizer([question, answer_1, answer_3, answer_3], padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, max pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+```
+
+## Training
+You can find the training script for the model [here](https://github.com/clips/mfaq).
+
+## People
+This model was developed by [Maxime De Bruyn](https://www.linkedin.com/in/maximedebruyn/), Ehsan Lotfi, Jeska Buhmann and Walter Daelemans.
+
+## Citation information
+```
+@misc{debruyn2021mfaq,
+      title={MFAQ: a Multilingual FAQ Dataset}, 
+      author={Maxime De Bruyn and Ehsan Lotfi and Jeska Buhmann and Walter Daelemans},
+      year={2021},
+      eprint={2109.12870},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<A>": 250003,
+  "<Q>": 250002,
+  "<link>": 250004
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "clips-mfaq-test/",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.25,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250005
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.10.2",
+    "pytorch": "1.9.0"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18b358dbd0bbf823fb81ba9f0df77ed11f19ae1bb6ba900489189c4ea9b6780
+size 1112206312

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,56 @@
+{
+  "additional_special_tokens": [
+    "<Q>",
+    "<A>",
+    "<link>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c202c2904979914d10811ca26aaf9672c41820a3d25cb432040fe1405be30ffb
+size 17083552

tokenizer_config.json

@@ -0,0 +1,90 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<Q>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "<A>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250004": {
+      "content": "<link>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<Q>",
+    "<A>",
+    "<link>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}