Add Plant DNABERT model

README.md

@@ -1,3 +1,76 @@
----
-license: cc-by-nc-sa-4.0
----
+---
+license: cc-by-nc-sa-4.0
+widget:
+- text: ACCTGA<mask>TTCTGAGTC
+tags:
+- DNA
+- biology
+- genomics
+datasets:
+- zhangtaolab/plant_reference_genomes
+---
+# Plant foundation DNA large language models
+
+The plant DNA large language models (LLMs) contain a series of foundation models based on different model architectures, which are pre-trained on various plant reference genomes.  
+All the models have a comparable model size between 90 MB and 150 MB, BPE tokenizer is used for tokenization and 8000 tokens are included in the vocabulary.  
+
+
+Part of this collection is the **nucleotide-transformer-v2-100m-multi-species**, a 100m parameters transformer pre-trained  on a collection of 850 genomes from a wide range of species, including model and non-model organisms.
+
+**Developed by:** zhangtaolab
+
+### Model Sources
+
+- **Repository:** [Plant DNA LLMs](https://github.com/zhangtaolab/plant_DNA_LLMs)
+- **Manuscript:** [Versatile applications of foundation DNA language models in plant genomes]() 
+
+### Architecture
+
+The model is trained based on the Google BERT base model with modified tokenizer specific for DNA sequence.
+
+### How to use
+
+Install the runtime library first:
+```bash
+pip install transformers
+```
+
+Here is a simple code for inference:
+```python
+from transformers import AutoModelForMaskedLM, AutoTokenizer
+import torch
+
+model_name = 'plant-dnabert'
+# load model and tokenizer
+model = AutoModelForMaskedLM.from_pretrained(f'zhangtaolab/{model_name}', trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(f'zhangtaolab/{model_name}', trust_remote_code=True)
+
+# example sequence and tokenization
+sequences = ['ATATACGGCCGNC','GGGTATCGCTTCCGAC']
+tokens = tokenizer(sequences,padding="longest")['input_ids']
+print(f"Tokenzied sequence: {tokenizer.batch_decode(tokens)}")
+
+# inference
+device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+model.to(device)
+inputs = tokenizer(sequences, truncation=True, padding='max_length', max_length=512, 
+                   return_tensors="pt")
+inputs = {k: v.to(device) for k, v in inputs.items()}
+outs = model(
+    **inputs,
+    output_hidden_states=True
+)
+
+# get the final layer embeddings and prediction logits
+embeddings = outs['hidden_states'][-1].detach().numpy()
+logits = outs['logits'].detach().numpy()
+```
+
+
+### Training data
+We use MaskedLM method to pre-train the model, the tokenized sequence have a maximum length of 512.  
+Detailed training procedure can be found in our manuscript.
+
+
+#### Hardware
+Model was pre-trained on a NVIDIA RTX4090 GPU (24 GB).

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 8000,
+  "[MASK]": 8004,
+  "[PAD]": 8003,
+  "[SEP]": 8001,
+  "[UNK]": 8002
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 8005
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4c3d0c1421a9f2234c5593cb8c4c40c60009edd853a4fff1acae4c90c67af9
+size 368818524

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "8000": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8001": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8002": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8003": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8004": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}