update model

README.md

@@ -3,7 +3,7 @@ language: en
 thumbnail: https://huggingface.co/front/thumbnails/google.png
 license: apache-2.0
 base_model:
-- cross-encoder/ms-marco-TinyBERT-L-2-v2
+- cross-encoder/ms-marco-MiniLM-L-4-v2
 pipeline_tag: text-classification
 library_name: transformers
 metrics:
@@ -16,7 +16,7 @@ datasets:
 
 ## Cross-Encoder for MS Marco with TinyBert
 
-This is a fine-tuned version of the model checkpointed at [cross-encoder/ms-marco-TinyBert-L-2-v2](https://huggingface.co/cross-encoder/ms-marco-TinyBERT-L-2-v2).
+This is a fine-tuned version of the model checkpointed at [cross-encoder/ms-marco-MiniLM-L-4-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-4-v2).
 
 It was fine-tuned on html tags and labels generated using [Fathom](https://mozilla.github.io/fathom/commands/label.html).
 
@@ -31,18 +31,18 @@ classifier = pipeline(
 )
 
 print(
-	classifier('<input class="cc-number" placeholder="Enter credit card number..." />')
+	classifier('Card information input Card number cc-number <SEP> <SEP> input First name <SEP> <SEP>')
 )
 
 ```
 
 ## Model Training Info
 ```python
-HyperParameters: {
-    'learning_rate': 0.000082,
-    'num_train_epochs': 71,
-    'weight_decay': 0.1,
-    'per_device_train_batch_size': 32,
+HyperParameters = {
+    'learning_rate': 2.3878733582558547e-05,
+    'num_train_epochs': 21,
+    'weight_decay': 0.0005288040458920454,
+    'per_device_train_batch_size': 32
 }
 ```
 

config.json

@@ -1,6 +1,6 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "/content/cross-encoder/ms-marco-TinyBERT-L-2-v2",
+  "_name_or_path": "/content/cross-encoder/ms-marco-MiniLM-L-4-v2",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -9,47 +9,69 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 384,
   "id2label": {
-    "0": "cc-csc",
-    "1": "cc-exp",
-    "2": "cc-exp-month",
-    "3": "cc-exp-year",
-    "4": "cc-name",
-    "5": "cc-number",
-    "6": "cc-type",
-    "7": "email",
-    "8": "given-name",
-    "9": "last-name",
-    "10": "other",
-    "11": "postal-code"
+    "0": "address-level1",
+    "1": "address-level2",
+    "2": "address-line1",
+    "3": "address-line2",
+    "4": "cc-csc",
+    "5": "cc-exp",
+    "6": "cc-exp-month",
+    "7": "cc-exp-year",
+    "8": "cc-name",
+    "9": "cc-number",
+    "10": "cc-type",
+    "11": "country-name",
+    "12": "current-password",
+    "13": "email",
+    "14": "family-name",
+    "15": "given-name",
+    "16": "name",
+    "17": "new-password",
+    "18": "organization",
+    "19": "other",
+    "20": "postal-code",
+    "21": "street-address",
+    "22": "tel"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 512,
+  "intermediate_size": 1536,
   "label2id": {
-    "cc-csc": 0,
-    "cc-exp": 1,
-    "cc-exp-month": 2,
-    "cc-exp-year": 3,
-    "cc-name": 4,
-    "cc-number": 5,
-    "cc-type": 6,
-    "email": 7,
-    "given-name": 8,
-    "last-name": 9,
-    "other": 10,
-    "postal-code": 11
+    "address-level1": 0,
+    "address-level2": 1,
+    "address-line1": 2,
+    "address-line2": 3,
+    "cc-csc": 4,
+    "cc-exp": 5,
+    "cc-exp-month": 6,
+    "cc-exp-year": 7,
+    "cc-name": 8,
+    "cc-number": 9,
+    "cc-type": 10,
+    "country-name": 11,
+    "current-password": 12,
+    "email": 13,
+    "family-name": 14,
+    "given-name": 15,
+    "name": 16,
+    "new-password": 17,
+    "organization": 18,
+    "other": 19,
+    "postal-code": 20,
+    "street-address": 21,
+    "tel": 22
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.46.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d095f0e0dd6ba39462fec2067c71b4e27fe1808abf0db79114f98a8ac3acb5b2
-size 17554472
+oid sha256:340a1f388c0a35abde4edc524be81f4cdd9acdbb8b3e7430fae31068abda9c3e
+size 76700884

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da31488b459a7851731ec263425d7af53b51bb497487fc76922677d8aea111f7
-size 17612158
+oid sha256:4e1443fbd2a9ac7862468ce3b6433442e657ab3d44e3b0ea3b06e14bc113ae66
+size 76801703

onnx/model_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef8c27f9dbaf27ba39d979442a822c1ff4051bfcf9ba32d535618a784c4cf13
-size 16262309
+oid sha256:62fe679f535a90b246c2531e2e349fd4c3f3fe13e8dca02e8d9b488e0432b191
+size 52475154

onnx/model_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70dc3df0f2c9420f8092090a51f73a83a5e535e65025533e02c1feb6a1e3d054
-size 8837300
+oid sha256:0b8b969f498202e7d9923addb97d1d9725d3ad4d6f6184f6bd23927b41d4cb12
+size 38455479

onnx/model_int8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3aaada3f9b2699f57dc534d35a9e5882de6cd2ab0ae25c5b915cb335befcb0
-size 4479682
+oid sha256:bbe8711f9b3897dbb10439e7c72def73dca020acd48e4feb3bcf5a1362c7d9fa
+size 19451059

onnx/model_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2441385e5c3dc7e9a2639e58c335011152a757e8a4cf098ca2fb368cbdc92f
-size 16286797
+oid sha256:a57408bc6b196c2251fbd7cd7aae3fcdbe9152d1477c38df111b9743c301b838
+size 52917370

onnx/model_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2281c5e2b61e2bc7d7c0cf4cb2a392de10d2c2e81e25c94ef82a77efeee1ebf
-size 8273795
+oid sha256:0933fd729d3dceea9166ec135818d71b06933599b7942e7efb4cb0980368f832
+size 28284538

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3aaada3f9b2699f57dc534d35a9e5882de6cd2ab0ae25c5b915cb335befcb0
-size 4479682
+oid sha256:bbe8711f9b3897dbb10439e7c72def73dca020acd48e4feb3bcf5a1362c7d9fa
+size 19451059

onnx/model_uint8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175b941a81aac05aaae2cdb0aed7755f6c7d0efacb13ca682f2d0e49e021a900
-size 4479682
+oid sha256:669c6a29cb8f05c079eb28e831c10c0f7c2c99f9f5d9ac45b4f1a7e0f2cf5495
+size 19451056

quantize_config.json

@@ -8,11 +8,10 @@
         "q4f16",
         "bnb4"
     ],
-    "per_channel": false,
+    "per_channel": true,
     "reduce_range": true,
     "block_size": null,
     "is_symmetric": true,
     "accuracy_level": null,
-    "quant_type": 1,
-    "op_block_list": null
+    "quant_type": 1
 }

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_length": 512,
   "model_max_length": 512,