Model for character level

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/scratch/c_evolm/trained_models/prokbert-mini-k1s1/checkpoint-13200",
+  "architectures": [
+    "MegatronBertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "relative_key_query",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 20
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73539bc7d995b7a331e8c54fffbf7401d860d01de587734c3328faad95e0227a
+size 99939786

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "ProkBERTTokenizer"
+}

vocab.txt

@@ -0,0 +1 @@
+[PAD]\n[UNK]\n[CLS]\n[SEP]\n[MASK]\nA\nC\nG\nT\nN\n