Upload 5 files

config.json

@@ -0,0 +1,34 @@
+{
+  "alphabet": "gene_prot",
+  "architectures": [
+    "LucaGPLMModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.0,
+  "embed_scale": 1.0,
+  "ffn_dim": 10240,
+  "flash_attention_causal": false,
+  "flash_attention_dropout": 0.0,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 2560,
+  "ignore_index": -100,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 3074,
+  "model_type": "lucagplm",
+  "no_position_embeddings": true,
+  "no_token_type_embeddings": false,
+  "num_attention_heads": 20,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooling_type": "avg",
+  "pooling_units": null,
+  "token_dropout": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_embed_layer_norm": false,
+  "use_flash_attention": false,
+  "use_last_layer_norm": true,
+  "vocab_size": 39
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683554b24c8c6370d58572b386313c13606ab4e242399b87d0d2ec1bb4061110
+size 3776937392

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 +1,52 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "LucaGPLMTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  "[PAD]": 0,
+  "[UNK]": 1,
+  "[CLS]": 2,
+  "[SEP]": 3,
+  "[MASK]": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "L": 10,
+  "A": 11,
+  "G": 12,
+  "V": 13,
+  "S": 14,
+  "E": 15,
+  "R": 16,
+  "T": 17,
+  "I": 18,
+  "D": 19,
+  "P": 20,
+  "K": 21,
+  "Q": 22,
+  "N": 23,
+  "F": 24,
+  "Y": 25,
+  "M": 26,
+  "H": 27,
+  "W": 28,
+  "C": 29,
+  "X": 30,
+  "B": 31,
+  "U": 32,
+  "Z": 33,
+  "O": 34,
+  "J": 35,
+  ".": 36,
+  "-": 37,
+  "*": 38
+}