from transformers import AutoModel, AutoTokenizer

model_path = 'heqin-zhu/structRFM'
# model_path = os.getenv('structRFM_checkpoint')

model = AutoModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

# single sequence
seq = 'GUCCCAACUCUUGCGGGGAGGGAU'
inputs = tokenizer(seq, return_tensors="pt")
outputs = model(**inputs)
print('>>> single seq, length:', len(seq))
for k, v in outputs.items():
    print(k, v.shape)
print(outputs.last_hidden_state.shape)

# batch mode
seqs = ["GUCCCAA", 'AGUGUUG', 'AUGUAGUTCUN']
inputs = tokenizer(
             seqs,
             add_special_tokens=True,
             max_length=514,
             padding='max_length',
             truncation=True,
             return_tensors='pt'
        )
outputs = model(**inputs) # note that the output sequential features are padded to max-length
print('>>> batch seqs, batch:', len(seqs))
for k, v in outputs.items():
    print(k, v.shape)

'''
>>> single seq, length: 24
last_hidden_state torch.Size([1, 24, 768])
pooler_output torch.Size([1, 768])
torch.Size([1, 24, 768])
>>> batch seqs, batch: 3
last_hidden_state torch.Size([3, 514, 768])
pooler_output torch.Size([3, 768])
'''