Update iupac-gpt/README.md

iupac-gpt/README.md

@@ -1,7 +1,7 @@
 # Generative Pre-Training from Molecules
 
 Autoregressive transformer language model for drug discovery. (Pre)trained on a large
-SMILES corpus. Evaluated on molecular property prediction and low-data de novo design
+IUPAC corpus. Evaluated on molecular property prediction and low-data de novo design
 tasks.
 
 
@@ -11,22 +11,22 @@ Set up [conda](https://conda.io/en/latest/index.html) and create a new environme
 `environment.yml` (if needed, make corresponding edits for GPU-compatibility).
 ```shell
 conda env create -f environment.yml
-conda activate smiles-gpt
+conda activate iupacgpt
 git clone https://github.com/sanjaradylov/smiles-gpt.git
-cd smiles-gpt
+cd iupacgpt
 ```
 
 
 ## Benchmark
 
 ### Checkpoint
-[checkpoints/benchmark-5m](https://github.com/sanjaradylov/smiles-gpt/tree/master/checkpoints/benchmark-5m)
+[checkpoints/iupac](https://huggingface.co/superspider2023/iupacGPT/edit/main/iupac-gpt/checkpoints/iupac)
 stores serialized model, tokenizer, and configuration. Do not modify them. Use
 `from_pretrained` method to load HuggingFace objects, e.g.,
 ```python
 from transformers import GPT2Config, GPT2LMHeadModel, PreTrainedTokenizerFast
 
-checkpoint = "checkpoints/benchmark-5m"
+checkpoint = "checkpoints/iupac"
 
 config = GPT2Config.from_pretrained(checkpoint)
 model = GPT2LMHeadModel.from_pretrained(checkpoint)