Upload model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "gpt2-large",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,13 +12,11 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 36,
   "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a74b5e8f90b48ec10d03fb9c2828f2fd1243a2668d850aea6f316d03687ea1f
-size 1419322880
+oid sha256:05a0e17fca6bee11fb0f7eb56e4fe3c70a14b67c065387b1c43ce026bdb6fed9
+size 3096165928