DistilBertModel模型的简单解释
前言 DistilBertModel((embeddings): Embeddings((word\_embeddings): Embedding(30522, 768, padding\_idx0)(position\_embeddings): Embedding(512, 768)(LayerNorm): LayerNorm((768,), eps1e-12, elementwise\_affineTrue)(dropout): Dropout(p\0.1, inplaceFalse))(trans…
2025-12-16