Embedding

LLM Embedding ChatGLM ChatGLM获取Embedding向量 inputs = tokenizer([text], return_tensors="pt").to(device) resp = model.transformer(**inputs, output_hidden_states=True) y = resp.last_hidden_state y_mean = torch.mean(y, dim=0, keepdim=True) y_mean = y_mean.cpu().detach().numpy() print(y_mean.shape) > [1, 4096]