Add new CrossEncoder model

.gitattributes

@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,63 +1,63 @@
----
-license: apache-2.0
-language:
-- en
-- ar
-- zh
-- nl
-- fr
-- de
-- hi
-- in
-- it
-- ja
-- pt
-- ru
-- es
-- vi
-- multilingual
-datasets:
-- unicamp-dl/mmarco
-base_model:
-- nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large
-pipeline_tag: text-ranking
-library_name: sentence-transformers
-tags:
-- transformers
----
-# Cross-Encoder for multilingual MS Marco
-
-This model was trained on the [MMARCO](https://hf.co/unicamp-dl/mmarco) dataset. It is a machine translated version of MS MARCO using Google Translate. It was translated to 14 languages. In our experiments, we observed that it performs also well for other languages.
-
-As a base model, we used the [multilingual MiniLMv2](https://huggingface.co/nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large) model.
-
-The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/ms_marco)
-
-## Usage with SentenceTransformers
-
-The usage becomes easy when you have [SentenceTransformers](https://www.sbert.net/) installed. Then, you can use the pre-trained models like this:
-```python
-from sentence_transformers import CrossEncoder
-model = CrossEncoder('model_name')
-scores = model.predict([('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')])
-```
-
-
-
-
-## Usage with Transformers
-
-```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
-
-model = AutoModelForSequenceClassification.from_pretrained('model_name')
-tokenizer = AutoTokenizer.from_pretrained('model_name')
-
-features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'],  padding=True, truncation=True, return_tensors="pt")
-
-model.eval()
-with torch.no_grad():
-    scores = model(**features).logits
-    print(scores)
+---
+license: apache-2.0
+language:
+- en
+- ar
+- zh
+- nl
+- fr
+- de
+- hi
+- in
+- it
+- ja
+- pt
+- ru
+- es
+- vi
+- multilingual
+datasets:
+- unicamp-dl/mmarco
+base_model:
+- nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+tags:
+- transformers
+---
+# Cross-Encoder for multilingual MS Marco
+
+This model was trained on the [MMARCO](https://hf.co/unicamp-dl/mmarco) dataset. It is a machine translated version of MS MARCO using Google Translate. It was translated to 14 languages. In our experiments, we observed that it performs also well for other languages.
+
+As a base model, we used the [multilingual MiniLMv2](https://huggingface.co/nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large) model.
+
+The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/ms_marco)
+
+## Usage with SentenceTransformers
+
+The usage becomes easy when you have [SentenceTransformers](https://www.sbert.net/) installed. Then, you can use the pre-trained models like this:
+```python
+from sentence_transformers import CrossEncoder
+model = CrossEncoder('model_name')
+scores = model.predict([('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')])
+```
+
+
+
+
+## Usage with Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained('model_name')
+tokenizer = AutoTokenizer.from_pretrained('model_name')
+
+features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'],  padding=True, truncation=True, return_tensors="pt")
+
+model.eval()
+with torch.no_grad():
+    scores = model(**features).logits
+    print(scores)
 ```

config.json

@@ -1,34 +1,36 @@
-{
-  "_name_or_path": "nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large",
-  "architectures": [
-    "XLMRobertaForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
-  "id2label": {
-    "0": "LABEL_0"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002,
-  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity"
-}
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.linear.Identity",
+    "version": "4.1.0.dev0"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9a03ed1e966f7c5288dd4230e3d6a9bf5e3a170a06f1f4241c5bca12c6487c
+size 470883696

special_tokens_map.json

@@ -1 +1,51 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
+{
+  "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -1 +1,55 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large", "tokenizer_class": "XLMRobertaTokenizer"}
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}