Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,18 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* 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
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz 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
-*.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
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+datasets:
+- sentence-transformers/msmarco
+language:
+- en
+base_model:
+- microsoft/MiniLM-L12-H384-uncased
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+tags:
+- transformers
+---
+# Cross-Encoder for MS Marco
+
+This model was trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task.
+
+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/cross_encoder/training/ms_marco)
+
+
+## Usage with SentenceTransformers
+
+The usage is 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('cross-encoder/ms-marco-MiniLM-L12-v2')
+scores = model.predict([
+    ("How many people live in Berlin?", "Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers."),
+    ("How many people live in Berlin?", "Berlin is well known for its museums."),
+])
+print(scores)
+# [ 9.218911  -4.0780287]
+```
+
+
+## Usage with Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/ms-marco-MiniLM-L12-v2')
+tokenizer = AutoTokenizer.from_pretrained('cross-encoder/ms-marco-MiniLM-L12-v2')
+
+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)
+```
+
+
+
+## Performance
+In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [TREC Deep Learning 2019](https://microsoft.github.io/TREC-2019-Deep-Learning/) and the [MS Marco Passage Reranking](https://github.com/microsoft/MSMARCO-Passage-Ranking/) dataset. 
+
+
+| Model-Name        | NDCG@10 (TREC DL 19) | MRR@10 (MS Marco Dev)  | Docs / Sec |
+| ------------- |:-------------| -----| --- | 
+| **Version 2 models** | | | 
+| cross-encoder/ms-marco-TinyBERT-L2-v2 | 69.84 | 32.56 | 9000
+| cross-encoder/ms-marco-MiniLM-L2-v2 | 71.01 | 34.85 | 4100
+| cross-encoder/ms-marco-MiniLM-L4-v2 | 73.04 | 37.70 | 2500
+| cross-encoder/ms-marco-MiniLM-L6-v2 | 74.30 | 39.01 | 1800
+| cross-encoder/ms-marco-MiniLM-L12-v2 | 74.31 | 39.02 | 960
+| **Version 1 models** | | | 
+| cross-encoder/ms-marco-TinyBERT-L2  | 67.43 | 30.15  | 9000
+| cross-encoder/ms-marco-TinyBERT-L4  | 68.09 | 34.50  | 2900
+| cross-encoder/ms-marco-TinyBERT-L6 |  69.57 | 36.13  | 680
+| cross-encoder/ms-marco-electra-base | 71.99 | 36.41 | 340
+| **Other models** | | | 
+| nboost/pt-tinybert-msmarco | 63.63 | 28.80 | 2900 
+| nboost/pt-bert-base-uncased-msmarco | 70.94 | 34.75 | 340 
+| nboost/pt-bert-large-msmarco | 73.36 | 36.48 | 100 
+| Capreolus/electra-base-msmarco | 71.23 | 36.89 | 340 
+| amberoad/bert-multilingual-passage-reranking-msmarco | 68.40 | 35.54 | 330 
+| sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco | 72.82 | 37.88 | 720
+ 
+ Note: Runtime was computed on a V100 GPU.

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522,
+  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity"
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5544d476410b7ec448de6f86668aba7224fbfd6b83315f675fcf67c9e928d8c
+size 133448756

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed84b90cdf3518f76ec9bb93a16f97887eea7c4e7ee5dfb03cc297e394fbbc3
+size 133469020

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac389ab6abe08dcbddf2c41a69b6a18853e0dca440adbc2abc1adfcee46483f
+size 133743863

onnx/model_O1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a5524ece92ecb778653270b53cade1326967ad00be9f2058c83985e9f9206a
+size 133647288

onnx/model_O2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39748ee92c8b2f5260cc87d0e4e96f1792def4682651f5e3d59cdaa321053f48
+size 133479607

onnx/model_O3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bced017a0a022a6500f6b89c888968a479ee0d28eebc47055f96a129472f989
+size 133479462

onnx/model_O4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2d497a5f40e3fdae1e758ce1225e00b74a7e41efe35da1b8fc0475220b4c16
+size 66889072

onnx/model_qint8_arm64.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148a402605f68037609b081d3f4e85154f49cd89f9e93990cfbe8120ae34410c
+size 34311898

onnx/model_qint8_avx512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148a402605f68037609b081d3f4e85154f49cd89f9e93990cfbe8120ae34410c
+size 34311898

onnx/model_qint8_avx512_vnni.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148a402605f68037609b081d3f4e85154f49cd89f9e93990cfbe8120ae34410c
+size 34311898

onnx/model_quint8_avx2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9906ae940e137b83d512c8d0f5c6ce9980bf487b168d40b9522b4747c4c89b
+size 34311898

openvino/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8538376778c5d1464299273717fc0cc731654f875277031e007f18118a8ae680
+size 133445792

openvino/openvino_model_qint8_quantized.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c1d9df505fbeeb8bc136a916c1d6a41e73b0e1200531ddaaffd76e3e08c4c4
+size 33972068

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207bb14d184b7728b7c2a68c685678aab636ae301a46f99fe05e5ffdae89e4d8
+size 133530889

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 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}