Upload model

config.json

@@ -1,20 +1,21 @@
 {
+  "_name_or_path": "output_model_dir",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPTLanguageModel"
+    "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "dropout": 0.2,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_embd": 256,
-  "n_head": 4,
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 4,
+  "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -25,8 +26,14 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.30.0",
   "use_cache": true,
-  "vocab_size": 52000
+  "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8f3e347e86e79f79f542a344c27ed1e1386636f230f7863618a8070811c38
-size 186513429
+oid sha256:17cfa2cb57706c5a5690d7f596bfc8fd3c405fcfd59610c5c2194c24592444c6
+size 497805149