add model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-large",
+  "_name_or_path": "gpt2-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,11 +12,13 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1280,
-  "n_head": 20,
+  "n_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
-  "n_layer": 36,
+  "n_layer": 24,
   "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
   "reorder_and_upcast_attn": true,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": true,
@@ -35,5 +37,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.19.0",
   "use_cache": true,
-  "vocab_size": 32768
+  "vocab_size": 200000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2222e919d27bfdfb2ada96f5d50c7643a48f8041567050b3980fb8e9989616f5
-size 3044480713
+oid sha256:95b904851b71c3ee2fb7642054a64529f53f7c23dfde8d3007adb8ffca3d48bb
+size 2057909465