You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
class LlamaForCausalLM(LlamaPreTrainedModel):
....................
if labels is not None:
# Shift so that tokens < n predict n
**shift_logits = logits[..., :-1, :].contiguous()
shift_labels = labels[..., 1:].contiguous()**
在 main.py中数据准备时:
在 modeling_llama.py 中loss计算时:
为什么在模型数据sample输入时进行了预测和真实值之间的位移对齐,在模型中loss计算时还进行了一次位移对齐?
The text was updated successfully, but these errors were encountered: