MCPcopy Create free account
hub / github.com/ckd0817/LLM-Interview-Code / FFN

Class FFN

ffn/FFN.py:13–58  ·  view source on GitHub ↗

标准前馈神经网络模块 由两个线性层组成,中间使用 ReLU 激活函数。 intermediate_dim 通常是 model_dim 的 4 倍。 Args: model_dim: 输入/输出维度 intermediate_dim: 中间层维度(通常是 model_dim 的 4 倍)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected