Upload 5 files

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Logan/Codon_LLM/Weights/CodonBERT-BFD",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 40000,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 30,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 69
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992e98298217ad531b101a176a91909713d1be761ad1db9f39ff3c1137a51dbd
+size 840147869

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.txt

@@ -0,0 +1,69 @@
+[PAD]
+[UNK]
+[CLS]
+[SEP]
+[MASK]
+a
+A
+@
+b
+B
+#
+$
+%
+r
+R
+n
+N
+d
+D
+c
+C
+e
+E
+q
+Q
+^
+G
+&
+g
+h
+H
+i
+I
+j
++
+M
+m
+l
+J
+L
+k
+K
+(
+f
+F
+p
+P
+o
+O
+=
+s
+z
+Z
+w
+S
+X
+T
+t
+x
+W
+y
+Y
+u
+v
+U
+V
+]
+}
+)