Figure 5
From: CPMI-ChatGLM: parameter-efficient fine-tuning ChatGLM with Chinese patent medicine instructions
The schematic diagram of P-Tuning v2. The orange blocks (i.e., \({h}_{0}\),…,\({h}_{i}\)) represent trainable prompt embeddings, and the blue part represents the embedding layer, which is stored or computed by a frozen pre-trained language model. The dashed arrow that returns to the input indicates the optional reparameterization optimization mode.
