Update README.md

README.md

@@ -1,3 +1,76 @@
 ---
 license: apache-2.0
 ---
+
+## Model description
+This repo contains a large molecular generative model built with molecular language SELFIES.
+
+## Intended uses
+You can use the model to generate molecules from scratch (i.e., inputting the bos_token), or input a partial structure for the model to complete.
+
+## How to use
+We have provided two types of examples. You can modify the input, generation parameters, etc., according to your needs.
+
+- Denovo molecule generation 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(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]']
+```