Add new LinkTransformer model.

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/88/21/882195bf57f6178b187ee24446a6091f8842bfeb8984266d2e7f867e2f87ce77 filter=lfs diff=lfs merge=lfs -text

LT_training_config.json

@@ -24,6 +24,6 @@
   "loss_params": {},
   "eval_type": "classification",
   "training_dataset": "dataframe",
-  "base_model_path": "oshizo/sbert-jsnli-luke-japanese-base-lite",
+  "base_model_path": "DMetaSoul/sbert-chinese-qmc-domain-v1",
   "best_model_path": "models/check"
 }

README.md

@@ -19,7 +19,7 @@ It maps sentences & paragraphs to a 768 dimensional dense vector space and can b
 Take a look at the documentation of [sentence-transformers](https://www.sbert.net/index.html) if you want to use this model for more than what we support in our applications. 
 
 
-This model has been fine-tuned on the model : oshizo/sbert-jsnli-luke-japanese-base-lite. It is pretrained for the language : - zh.
+This model has been fine-tuned on the model : DMetaSoul/sbert-chinese-qmc-domain-v1. It is pretrained for the language : - zh.
 
 
 test
@@ -126,7 +126,7 @@ Parameters of the fit()-Method:
 
 
 LinkTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: LukeModel 
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
   (1): Pooling({'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})
 )
 ```

config.json

@@ -1,32 +1,31 @@
 {
   "_name_or_path": "models/check",
   "architectures": [
-    "LukeModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bert_model_name": "models/luke-japanese/hf_xlm_roberta",
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "cls_entity_prediction": false,
-  "entity_emb_size": 256,
-  "entity_vocab_size": 4,
-  "eos_token_id": 2,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "luke",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.1",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "use_entity_aware_attention": true,
-  "vocab_size": 32772
+  "vocab_size": 21128
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.2.2",
-    "transformers": "4.25.1",
-    "pytorch": "1.13.0+cu116"
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.16.0",
+    "pytorch": "1.10.2"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882195bf57f6178b187ee24446a6091f8842bfeb8984266d2e7f867e2f87ce77
-size 532299592
+oid sha256:568e6ab4e674b1bda99bc119f94f0e37a8e60473e1fe971aa2bccca9d8afeb3e
+size 409092920

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 128,
+  "max_seq_length": 256,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,72 +1,34 @@
 {
-  "additional_special_tokens": [
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>",
-    {
-      "content": "<ent>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<ent2>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "cls_token": {
-    "content": "<s>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": {
-    "content": "</s>",
+  "mask_token": {
+    "content": "[MASK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,108 +1,62 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32769": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32770": {
-      "content": "<ent>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32771": {
-      "content": "<ent2>",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>",
-    "<ent>",
-    "<ent2>"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "entity_mask2_token": "[MASK2]",
-  "entity_mask_token": "[MASK]",
-  "entity_pad_token": "[PAD]",
-  "entity_token_1": {
-    "__type": "AddedToken",
-    "content": "<ent>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false,
-    "special": false
-  },
-  "entity_token_2": {
-    "__type": "AddedToken",
-    "content": "<ent2>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false,
-    "special": false
-  },
-  "entity_unk_token": "[UNK]",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "max_entity_length": 32,
-  "max_mention_length": 30,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 256,
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "task": null,
-  "tokenizer_class": "MLukeTokenizer",
-  "unk_token": "<unk>"
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
 }