Upload 12 files

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "zhihan1996/DNA_bert_4",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "zhihan1996/DNA_bert_4--configuration_bert.BertConfig",
+    "AutoModel": "zhihan1996/DNA_bert_4--dnabert_layer.BertModel",
+    "AutoModelForMaskedLM": "zhihan1996/DNA_bert_4--dnabert_layer.BertForMaskedLM",
+    "AutoModelForPreTraining": "zhihan1996/DNA_bert_4--dnabert_layer.BertForPreTraining",
+    "AutoModelForSequenceClassification": "zhihan1996/DNA_bert_4--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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "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": 261
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dea914655bef782126768f3843a3a19a45834954fc03359d1ec0df835ee739b
+size 344997924

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28db9e3aafd38285923c0941f86450b7cc1dc2aac200165de9a948cebfda2451
+size 690117498

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acaa77db6e8ae5999994ba61c045c5ea857c6dc195da50c9eba3524f469dc924
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99727da09a35fc29a8189bd9d2264ba8c5b891942344616cc23fd5b7a6f76432
+size 1000

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,425 @@
+{
+  "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,
+      "AAAA": 5,
+      "AAAT": 6,
+      "AAAC": 7,
+      "AAAG": 8,
+      "AATA": 9,
+      "AATT": 10,
+      "AATC": 11,
+      "AATG": 12,
+      "AACA": 13,
+      "AACT": 14,
+      "AACC": 15,
+      "AACG": 16,
+      "AAGA": 17,
+      "AAGT": 18,
+      "AAGC": 19,
+      "AAGG": 20,
+      "ATAA": 21,
+      "ATAT": 22,
+      "ATAC": 23,
+      "ATAG": 24,
+      "ATTA": 25,
+      "ATTT": 26,
+      "ATTC": 27,
+      "ATTG": 28,
+      "ATCA": 29,
+      "ATCT": 30,
+      "ATCC": 31,
+      "ATCG": 32,
+      "ATGA": 33,
+      "ATGT": 34,
+      "ATGC": 35,
+      "ATGG": 36,
+      "ACAA": 37,
+      "ACAT": 38,
+      "ACAC": 39,
+      "ACAG": 40,
+      "ACTA": 41,
+      "ACTT": 42,
+      "ACTC": 43,
+      "ACTG": 44,
+      "ACCA": 45,
+      "ACCT": 46,
+      "ACCC": 47,
+      "ACCG": 48,
+      "ACGA": 49,
+      "ACGT": 50,
+      "ACGC": 51,
+      "ACGG": 52,
+      "AGAA": 53,
+      "AGAT": 54,
+      "AGAC": 55,
+      "AGAG": 56,
+      "AGTA": 57,
+      "AGTT": 58,
+      "AGTC": 59,
+      "AGTG": 60,
+      "AGCA": 61,
+      "AGCT": 62,
+      "AGCC": 63,
+      "AGCG": 64,
+      "AGGA": 65,
+      "AGGT": 66,
+      "AGGC": 67,
+      "AGGG": 68,
+      "TAAA": 69,
+      "TAAT": 70,
+      "TAAC": 71,
+      "TAAG": 72,
+      "TATA": 73,
+      "TATT": 74,
+      "TATC": 75,
+      "TATG": 76,
+      "TACA": 77,
+      "TACT": 78,
+      "TACC": 79,
+      "TACG": 80,
+      "TAGA": 81,
+      "TAGT": 82,
+      "TAGC": 83,
+      "TAGG": 84,
+      "TTAA": 85,
+      "TTAT": 86,
+      "TTAC": 87,
+      "TTAG": 88,
+      "TTTA": 89,
+      "TTTT": 90,
+      "TTTC": 91,
+      "TTTG": 92,
+      "TTCA": 93,
+      "TTCT": 94,
+      "TTCC": 95,
+      "TTCG": 96,
+      "TTGA": 97,
+      "TTGT": 98,
+      "TTGC": 99,
+      "TTGG": 100,
+      "TCAA": 101,
+      "TCAT": 102,
+      "TCAC": 103,
+      "TCAG": 104,
+      "TCTA": 105,
+      "TCTT": 106,
+      "TCTC": 107,
+      "TCTG": 108,
+      "TCCA": 109,
+      "TCCT": 110,
+      "TCCC": 111,
+      "TCCG": 112,
+      "TCGA": 113,
+      "TCGT": 114,
+      "TCGC": 115,
+      "TCGG": 116,
+      "TGAA": 117,
+      "TGAT": 118,
+      "TGAC": 119,
+      "TGAG": 120,
+      "TGTA": 121,
+      "TGTT": 122,
+      "TGTC": 123,
+      "TGTG": 124,
+      "TGCA": 125,
+      "TGCT": 126,
+      "TGCC": 127,
+      "TGCG": 128,
+      "TGGA": 129,
+      "TGGT": 130,
+      "TGGC": 131,
+      "TGGG": 132,
+      "CAAA": 133,
+      "CAAT": 134,
+      "CAAC": 135,
+      "CAAG": 136,
+      "CATA": 137,
+      "CATT": 138,
+      "CATC": 139,
+      "CATG": 140,
+      "CACA": 141,
+      "CACT": 142,
+      "CACC": 143,
+      "CACG": 144,
+      "CAGA": 145,
+      "CAGT": 146,
+      "CAGC": 147,
+      "CAGG": 148,
+      "CTAA": 149,
+      "CTAT": 150,
+      "CTAC": 151,
+      "CTAG": 152,
+      "CTTA": 153,
+      "CTTT": 154,
+      "CTTC": 155,
+      "CTTG": 156,
+      "CTCA": 157,
+      "CTCT": 158,
+      "CTCC": 159,
+      "CTCG": 160,
+      "CTGA": 161,
+      "CTGT": 162,
+      "CTGC": 163,
+      "CTGG": 164,
+      "CCAA": 165,
+      "CCAT": 166,
+      "CCAC": 167,
+      "CCAG": 168,
+      "CCTA": 169,
+      "CCTT": 170,
+      "CCTC": 171,
+      "CCTG": 172,
+      "CCCA": 173,
+      "CCCT": 174,
+      "CCCC": 175,
+      "CCCG": 176,
+      "CCGA": 177,
+      "CCGT": 178,
+      "CCGC": 179,
+      "CCGG": 180,
+      "CGAA": 181,
+      "CGAT": 182,
+      "CGAC": 183,
+      "CGAG": 184,
+      "CGTA": 185,
+      "CGTT": 186,
+      "CGTC": 187,
+      "CGTG": 188,
+      "CGCA": 189,
+      "CGCT": 190,
+      "CGCC": 191,
+      "CGCG": 192,
+      "CGGA": 193,
+      "CGGT": 194,
+      "CGGC": 195,
+      "CGGG": 196,
+      "GAAA": 197,
+      "GAAT": 198,
+      "GAAC": 199,
+      "GAAG": 200,
+      "GATA": 201,
+      "GATT": 202,
+      "GATC": 203,
+      "GATG": 204,
+      "GACA": 205,
+      "GACT": 206,
+      "GACC": 207,
+      "GACG": 208,
+      "GAGA": 209,
+      "GAGT": 210,
+      "GAGC": 211,
+      "GAGG": 212,
+      "GTAA": 213,
+      "GTAT": 214,
+      "GTAC": 215,
+      "GTAG": 216,
+      "GTTA": 217,
+      "GTTT": 218,
+      "GTTC": 219,
+      "GTTG": 220,
+      "GTCA": 221,
+      "GTCT": 222,
+      "GTCC": 223,
+      "GTCG": 224,
+      "GTGA": 225,
+      "GTGT": 226,
+      "GTGC": 227,
+      "GTGG": 228,
+      "GCAA": 229,
+      "GCAT": 230,
+      "GCAC": 231,
+      "GCAG": 232,
+      "GCTA": 233,
+      "GCTT": 234,
+      "GCTC": 235,
+      "GCTG": 236,
+      "GCCA": 237,
+      "GCCT": 238,
+      "GCCC": 239,
+      "GCCG": 240,
+      "GCGA": 241,
+      "GCGT": 242,
+      "GCGC": 243,
+      "GCGG": 244,
+      "GGAA": 245,
+      "GGAT": 246,
+      "GGAC": 247,
+      "GGAG": 248,
+      "GGTA": 249,
+      "GGTT": 250,
+      "GGTC": 251,
+      "GGTG": 252,
+      "GGCA": 253,
+      "GGCT": 254,
+      "GGCC": 255,
+      "GGCG": 256,
+      "GGGA": 257,
+      "GGGT": 258,
+      "GGGC": 259,
+      "GGGG": 260
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18edc369f4fa30839114c54c71b3a981d6073a09f88ee5e45659f2f8847fbc5b
+size 5240

vocab.txt

@@ -0,0 +1,261 @@
+[PAD]
+[UNK]
+[CLS]
+[SEP]
+[MASK]
+AAAA
+AAAT
+AAAC
+AAAG
+AATA
+AATT
+AATC
+AATG
+AACA
+AACT
+AACC
+AACG
+AAGA
+AAGT
+AAGC
+AAGG
+ATAA
+ATAT
+ATAC
+ATAG
+ATTA
+ATTT
+ATTC
+ATTG
+ATCA
+ATCT
+ATCC
+ATCG
+ATGA
+ATGT
+ATGC
+ATGG
+ACAA
+ACAT
+ACAC
+ACAG
+ACTA
+ACTT
+ACTC
+ACTG
+ACCA
+ACCT
+ACCC
+ACCG
+ACGA
+ACGT
+ACGC
+ACGG
+AGAA
+AGAT
+AGAC
+AGAG
+AGTA
+AGTT
+AGTC
+AGTG
+AGCA
+AGCT
+AGCC
+AGCG
+AGGA
+AGGT
+AGGC
+AGGG
+TAAA
+TAAT
+TAAC
+TAAG
+TATA
+TATT
+TATC
+TATG
+TACA
+TACT
+TACC
+TACG
+TAGA
+TAGT
+TAGC
+TAGG
+TTAA
+TTAT
+TTAC
+TTAG
+TTTA
+TTTT
+TTTC
+TTTG
+TTCA
+TTCT
+TTCC
+TTCG
+TTGA
+TTGT
+TTGC
+TTGG
+TCAA
+TCAT
+TCAC
+TCAG
+TCTA
+TCTT
+TCTC
+TCTG
+TCCA
+TCCT
+TCCC
+TCCG
+TCGA
+TCGT
+TCGC
+TCGG
+TGAA
+TGAT
+TGAC
+TGAG
+TGTA
+TGTT
+TGTC
+TGTG
+TGCA
+TGCT
+TGCC
+TGCG
+TGGA
+TGGT
+TGGC
+TGGG
+CAAA
+CAAT
+CAAC
+CAAG
+CATA
+CATT
+CATC
+CATG
+CACA
+CACT
+CACC
+CACG
+CAGA
+CAGT
+CAGC
+CAGG
+CTAA
+CTAT
+CTAC
+CTAG
+CTTA
+CTTT
+CTTC
+CTTG
+CTCA
+CTCT
+CTCC
+CTCG
+CTGA
+CTGT
+CTGC
+CTGG
+CCAA
+CCAT
+CCAC
+CCAG
+CCTA
+CCTT
+CCTC
+CCTG
+CCCA
+CCCT
+CCCC
+CCCG
+CCGA
+CCGT
+CCGC
+CCGG
+CGAA
+CGAT
+CGAC
+CGAG
+CGTA
+CGTT
+CGTC
+CGTG
+CGCA
+CGCT
+CGCC
+CGCG
+CGGA
+CGGT
+CGGC
+CGGG
+GAAA
+GAAT
+GAAC
+GAAG
+GATA
+GATT
+GATC
+GATG
+GACA
+GACT
+GACC
+GACG
+GAGA
+GAGT
+GAGC
+GAGG
+GTAA
+GTAT
+GTAC
+GTAG
+GTTA
+GTTT
+GTTC
+GTTG
+GTCA
+GTCT
+GTCC
+GTCG
+GTGA
+GTGT
+GTGC
+GTGG
+GCAA
+GCAT
+GCAC
+GCAG
+GCTA
+GCTT
+GCTC
+GCTG
+GCCA
+GCCT
+GCCC
+GCCG
+GCGA
+GCGT
+GCGC
+GCGG
+GGAA
+GGAT
+GGAC
+GGAG
+GGTA
+GGTT
+GGTC
+GGTG
+GGCA
+GGCT
+GGCC
+GGCG
+GGGA
+GGGT
+GGGC
+GGGG