Update for cnlpt v0.6.0

added_tokens.json

@@ -1 +1,10 @@
-{"<neg>": 30529, "<a1>": 30524, "<cr>": 30528, "</a2>": 30527, "</a1>": 30525, "<a2>": 30526, "</e>": 30523, "<e>": 30522}
+{
+  "</a1>": 30525,
+  "</a2>": 30527,
+  "</e>": 30523,
+  "<a1>": 30524,
+  "<a2>": 30526,
+  "<cr>": 30528,
+  "<e>": 30522,
+  "<neg>": 30529
+}

config.json

@@ -2,8 +2,9 @@
   "architectures": [
     "CnlpModelForClassification"
   ],
+  "cnlpt_version": "0.6.0",
   "encoder_config": {
-    "_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
+    "_name_or_path": "microsoft/xtremedistil-l6-h384-uncased",
     "add_cross_attention": false,
     "architectures": [
       "BertModel"
@@ -20,19 +21,20 @@
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "gradient_checkpointing": false,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
-    "hidden_size": 256,
+    "hidden_size": 384,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 1024,
+    "intermediate_size": 1536,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -46,7 +48,7 @@
     "min_length": 0,
     "model_type": "bert",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 6,
@@ -66,6 +68,7 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -73,35 +76,41 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.15.0",
+    "transformers_version": "4.22.2",
     "type_vocab_size": 2,
+    "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
     "vocab_size": 30530
   },
-  "encoder_name": "microsoft/xtremedistil-l6-h256-uncased",
+  "encoder_name": "microsoft/xtremedistil-l6-h384-uncased",
   "finetuning_task": [
     "dtr"
   ],
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
-  "layer": -1,
+  "hidden_size": 384,
+  "hier_head_config": null,
+  "label_dictionary": {
+    "dtr": [
+      "AFTER",
+      "BEFORE",
+      "BEFORE/OVERLAP",
+      "OVERLAP"
+    ]
+  },
+  "layer": 6,
   "model_type": "cnlpt",
-  "num_labels_list": [
-    4
-  ],
   "num_rel_attention_heads": 12,
-  "num_tokens": -1,
   "rel_attention_head_dims": 64,
-  "relations": [
-    false
-  ],
-  "tagger": [
-    false
-  ],
+  "relations": {
+    "dtr": false
+  },
+  "tagger": {
+    "dtr": false
+  },
   "tokens": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.15.0",
+  "transformers_version": "4.22.2",
   "use_prior_tasks": false,
   "vocab_size": 30530
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a6105f29b4f019286de46c7c2e19d0e93ad6093d5202e4b6f1a19548aaa8f4
-size 51307399
+oid sha256:656c9caad2072035ec356257e965b42ffadec00bf5fc060e65d12ea8495baf17
+size 91503485

special_tokens_map.json

@@ -1 +1,17 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"]}
+{
+  "additional_special_tokens": [
+    "<e>",
+    "</e>",
+    "<a1>",
+    "</a1>",
+    "<a2>",
+    "</a2>",
+    "<cr>",
+    "<neg>"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,26 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": true, "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"], "special_tokens_map_file": null, "name_or_path": "microsoft/xtremedistil-l6-h256-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
+{
+  "add_prefix_space": true,
+  "additional_special_tokens": [
+    "<e>",
+    "</e>",
+    "<a1>",
+    "</a1>",
+    "<a2>",
+    "</a2>",
+    "<cr>",
+    "<neg>"
+  ],
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "microsoft/xtremedistil-l6-h384-uncased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}