Merge pull request #157 from DrCesar/main

fix move model to device before calculating loss

appendix-D/01_main-chapter-code/appendix-D.ipynb

@@ -425,6 +425,7 @@
     "\n",
     "torch.manual_seed(123)\n",
     "model = GPTModel(GPT_CONFIG_124M)\n",
+    "model.to(device)\n",
     "\n",
     "loss = calc_loss_batch(input_batch, target_batch, model, device)\n",
     "loss.backward()"