Model and configs

README.md

@@ -0,0 +1,32 @@
+The repository is adapted based on: https://huggingface.co/chenxran/bart-smiles/tree/main
+
+
+```python
+from transformers import AutoTokenizer, AutoModel, SequenceFeatureExtractor
+import torch
+from transformers import AutoTokenizer, AutoModel
+
+smiles = "CCC(=O)"
+
+tokenizer = AutoTokenizer.from_pretrained("./BARTSmiles/", add_prefix_space=True)
+inputs = tokenizer(smiles, return_tensors="pt", return_token_type_ids=False, add_special_tokens=True)
+
+model = AutoModel.from_pretrained('./BARTSmiles')
+model.eval()
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+extractor = pipeline("feature-extraction", model=model, tokenizer=tokenizer)
+result = extractor(smiles, return_tensors=True, tokenize_kwargs={'return_token_type_ids':False})
+
+```
+
+## Citation
+
+@article{chilingaryan2022bartsmiles,
+  title={Bartsmiles: Generative masked language models for molecular representations},
+  author={Chilingaryan, Gayane and Tamoyan, Hovhannes and Tevosyan, Ani and Babayan, Nelly and Khondkaryan, Lusine and Hambardzumyan, Karen and Navoyan, Zaven and Khachatrian, Hrant and Aghajanyan, Armen},
+  journal={arXiv preprint arXiv:2211.16349},
+  year={2022}
+}

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "pretrained_model/bart-smiles",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 128,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 1026
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97732fdbcc3c52b53c0929a76bea0311cfd8b4d18b744956243e036aac5ac652
+size 135

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}