>>> from transformers import AutoTokenizer, LlamaForCausalLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("zjunlp/MolGen-7b")
>>> model = LlamaForCausalLM.from_pretrained(
                              "zjunlp/MolGen-7b",
                              load_in_8bit=True,
                              torch_dtype=torch.float16,
                              device_map="auto",
                              )
>>> device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
>>> sf_input = tokenizer(tokenizer.bos_token, return_tensors="pt").to(device)

>>> molecules = model.generate(input_ids=sf_input["input_ids"],
                              attention_mask=sf_input["attention_mask"],
                              do_sample=True,
                              max_new_tokens=10,
                              top_p=0.75,
                              top_k=30,
                              return_dict_in_generate=False,
                              num_return_sequences=5,
                              )
>>> sf_output = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True).replace(" ","") for g in molecules]
['[C][C][=C][C][=C][Branch2][Ring1][=Branch2][C][=Branch1]',
'[C][N][C][C][C][Branch2][Ring2][Ring2][N][C]',
'[C][O][C][=C][C][=C][C][Branch2][Ring1][Branch1]',
'[C][N][C][C][C@H1][Branch2][Ring1][Branch2][N][Branch1]',
'[C][=C][C][Branch2][Ring1][#C][C][=Branch1][C][=O]']

Molecular completion example:

python

>>> from transformers import AutoTokenizer, LlamaForCausalLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("zjunlp/MolGen-7b")
>>> model = LlamaForCausalLM.from_pretrained(
                              "zjunlp/MolGen-7b",
                              load_in_8bit=True,
                              torch_dtype=torch.float16,
                              device_map="auto",
                              )
>>> device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
>>> sf_input = tokenizer("[C][N][O]", return_tensors="pt").to(device)

>>> molecules = model.generate(input_ids=sf_input["input_ids"],
                              attention_mask=sf_input["attention_mask"],
                              do_sample=True,
                              max_new_tokens=10,
                              top_p=0.75,
                              top_k=30,
                              return_dict_in_generate=False,
                              num_return_sequences=5,
                              )
>>> sf_output = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True).replace(" ","") for g in molecules]
['[C][N][O][C][=Branch1][C][=O][/C][Ring1][=Branch1][=C][/C][=C]',
'[C][N][O][/C][=Branch1][#Branch1][=C][/N][Branch1][C][C][C][C]',
'[C][N][O][/C][=C][/C][=C][C][=Branch1][C][=O][C][=C]',
'[C][N][O][C][=Branch1][C][=O][N][Branch1][C][C][C][=Branch1]',
'[C][N][O][Ring1][Branch1][C][C][C][C][C][C][C][C]']

📚 Citation

If you use our repository, please cite:

bibtex

@inproceedings{fang2023domain,
  author       = {Yin Fang and
                  Ningyu Zhang and
                  Zhuo Chen and
                  Xiaohui Fan and
                  Huajun Chen},
  title        = {Domain-Agnostic Molecular Generation with Chemical Feedback},
  booktitle    = {{ICLR}},
  publisher    = {OpenReview.net},
  year         = {2024},
  url          = {https://openreview.net/pdf?id=9rPyHyjfwP}
}