'what's the difference between lm_labels and decoder_input_ids in t5 model?
I didn't find anything about lm_labels on T5 docs. How to explain the below code:
model = F5ForConfiditionalGeneration.from_pretrained('t5-base')
outputs = model(inputs_ids=input_ids, attention_mask=mask, decoder_input_ids=y_ids,lm_labels=lm_labels)
How to distinguish the difference between decoder_input_ids and lm_labels?
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|