Upload config

config.json

@@ -0,0 +1,45 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "outputs/pccot-gpt2-h800-3-24-seed0-upload",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PCoTGPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "loss_alpha": 1.0,
+  "loss_beta": 1.0,
+  "loss_gamma": 1.0,
+  "model_type": "pccot-gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "num_iterations": 3,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_layerwise_std": true,
+  "use_projection": false,
+  "vocab_size": 50261
+}