Update README.md

README.md

@@ -1,3 +1,33 @@
 ---
 license: mit
 ---
+This model is provided to compare with official ESM-2 35M model. It only receives residue sequence but shares the same vocabulary with normal SaProt,
+which means all structure tokens are marked as ``#``.
+
+### Huggingface model
+The following code shows how to load the model.
+```
+from transformers import EsmTokenizer, EsmForMaskedLM
+
+model_path = "/your/path/to/SaProt_35M_AF2_seqOnly"
+tokenizer = EsmTokenizer.from_pretrained(model_path)
+model = EsmForMaskedLM.from_pretrained(model_path)
+
+#################### Example ####################
+device = "cuda"
+model.to(device)
+
+seq = "M#E#V#Q#L#V#Q#Y#K#"
+tokens = tokenizer.tokenize(seq)
+print(tokens)
+
+inputs = tokenizer(seq, return_tensors="pt")
+inputs = {k: v.to(device) for k, v in inputs.items()}
+
+outputs = model(**inputs)
+print(outputs.logits.shape)
+
+"""
+['M#', 'E#', 'V#', 'Q#', 'L#', 'V#', 'Q#', 'Y#', 'K#']
+torch.Size([1, 11, 446])
+"""