Upload 7 files

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "Priyasi/Pretrain_TransVi_3",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "zhihan1996/DNA_bert_3--configuration_bert.BertConfig",
+    "AutoModel": "zhihan1996/DNA_bert_3--dnabert_layer.BertModel",
+    "AutoModelForMaskedLM": "zhihan1996/DNA_bert_3--dnabert_layer.BertForMaskedLM",
+    "AutoModelForPreTraining": "zhihan1996/DNA_bert_3--dnabert_layer.BertForPreTraining",
+    "AutoModelForSequenceClassification": "zhihan1996/DNA_bert_3--dnabert_layer.DNABertForSequenceClassification"
+  },
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_rnn_layer": 1,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "rnn": "lstm",
+  "rnn_dropout": 0.0,
+  "rnn_hidden": 768,
+  "split": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 69
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ddb3f1455d6946acd75a1232075008f090af8cf10a0e2333f91edceac32224
+size 344419200

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,233 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "BertNormalizer",
+    "clean_text": true,
+    "handle_chinese_chars": true,
+    "strip_accents": null,
+    "lowercase": false
+  },
+  "pre_tokenizer": {
+    "type": "BertPreTokenizer"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[CLS]": {
+        "id": "[CLS]",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "[CLS]"
+        ]
+      },
+      "[SEP]": {
+        "id": "[SEP]",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "[SEP]"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "WordPiece",
+    "prefix": "##",
+    "cleanup": true
+  },
+  "model": {
+    "type": "WordPiece",
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": "##",
+    "max_input_chars_per_word": 100,
+    "vocab": {
+      "[PAD]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[SEP]": 3,
+      "[MASK]": 4,
+      "AAA": 5,
+      "AAT": 6,
+      "AAC": 7,
+      "AAG": 8,
+      "ATA": 9,
+      "ATT": 10,
+      "ATC": 11,
+      "ATG": 12,
+      "ACA": 13,
+      "ACT": 14,
+      "ACC": 15,
+      "ACG": 16,
+      "AGA": 17,
+      "AGT": 18,
+      "AGC": 19,
+      "AGG": 20,
+      "TAA": 21,
+      "TAT": 22,
+      "TAC": 23,
+      "TAG": 24,
+      "TTA": 25,
+      "TTT": 26,
+      "TTC": 27,
+      "TTG": 28,
+      "TCA": 29,
+      "TCT": 30,
+      "TCC": 31,
+      "TCG": 32,
+      "TGA": 33,
+      "TGT": 34,
+      "TGC": 35,
+      "TGG": 36,
+      "CAA": 37,
+      "CAT": 38,
+      "CAC": 39,
+      "CAG": 40,
+      "CTA": 41,
+      "CTT": 42,
+      "CTC": 43,
+      "CTG": 44,
+      "CCA": 45,
+      "CCT": 46,
+      "CCC": 47,
+      "CCG": 48,
+      "CGA": 49,
+      "CGT": 50,
+      "CGC": 51,
+      "CGG": 52,
+      "GAA": 53,
+      "GAT": 54,
+      "GAC": 55,
+      "GAG": 56,
+      "GTA": 57,
+      "GTT": 58,
+      "GTC": 59,
+      "GTG": 60,
+      "GCA": 61,
+      "GCT": 62,
+      "GCC": 63,
+      "GCG": 64,
+      "GGA": 65,
+      "GGT": 66,
+      "GGC": 67,
+      "GGG": 68
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0a0a21b9667d5c7a0dc7c3ae9d42fb41e34bd15dd78ca65814cbe141296820
+size 5240

vocab.txt

@@ -0,0 +1,69 @@
+[PAD]
+[UNK]
+[CLS]
+[SEP]
+[MASK]
+AAA
+AAT
+AAC
+AAG
+ATA
+ATT
+ATC
+ATG
+ACA
+ACT
+ACC
+ACG
+AGA
+AGT
+AGC
+AGG
+TAA
+TAT
+TAC
+TAG
+TTA
+TTT
+TTC
+TTG
+TCA
+TCT
+TCC
+TCG
+TGA
+TGT
+TGC
+TGG
+CAA
+CAT
+CAC
+CAG
+CTA
+CTT
+CTC
+CTG
+CCA
+CCT
+CCC
+CCG
+CGA
+CGT
+CGC
+CGG
+GAA
+GAT
+GAC
+GAG
+GTA
+GTT
+GTC
+GTG
+GCA
+GCT
+GCC
+GCG
+GGA
+GGT
+GGC
+GGG