Upload model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "gpt2-xl",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,11 +12,12 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1600,
+  "n_head": 25,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 48,
   "n_positions": 1024,
+  "output_past": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4f040b950ad8dfb4ad4fe7e51b129bd2ca327bc0f362def68bb79fd32f0e80
+oid sha256:e2fcf93c2e2cd96af4e4c52ded3b669196ebad0320a9dbadfc527cd3a7f10fe0
 size 4970916328

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f14a54efb177d8a18dd540acf71ad52644b85a4eaa6f43653f5b9e7f3d5faaa
+oid sha256:e29e2b5941fec51089d251ac890ec9461c61a1b017e2e7b49539bd714addbad9
 size 1147659632