config files

config.json

@@ -0,0 +1 @@
+{"_name_or_path": "zhihan1996/DNABERT-2-117M", "alibi_starting_size": 512, "architectures": ["BertForMaskedLM"], "attention_probs_dropout_prob": 0.0, "auto_map": {"AutoConfig": "configuration_bert.BertConfig", "AutoModel": "bert_layers.BertModel", "AutoModelForMaskedLM": "bert_layers.BertForMaskedLM", "AutoModelForSequenceClassification": "bert_layers.BertForSequenceClassification"}, "classifier_dropout": null, "gradient_checkpointing": false, "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, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.28.0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 4096}

configuration_bert.py

@@ -0,0 +1,26 @@
+# Copyright 2022 MosaicML Examples authors
+# SPDX-License-Identifier: Apache-2.0
+
+from transformers import BertConfig as TransformersBertConfig
+
+
+class BertConfig(TransformersBertConfig):
+
+    def __init__(
+        self,
+        alibi_starting_size: int = 512,
+        attention_probs_dropout_prob: float = 0.0,
+        **kwargs,
+    ):
+        """Configuration class for MosaicBert.
+
+        Args:
+            alibi_starting_size (int): Use `alibi_starting_size` to determine how large of an alibi tensor to
+                create when initializing the model. You should be able to ignore this parameter in most cases.
+                Defaults to 512.
+            attention_probs_dropout_prob (float): By default, turn off attention dropout in Mosaic BERT
+                (otherwise, Flash Attention will be off by default). Defaults to 0.0.
+        """
+        super().__init__(
+            attention_probs_dropout_prob=attention_probs_dropout_prob, **kwargs)
+        self.alibi_starting_size = alibi_starting_size

gitattributes.txt

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text