Upload model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "microsoft/DialoGPT-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,10 +12,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 24,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -27,13 +27,12 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
+    "conversational": {
+      "max_length": 1000
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.30.1",
+  "transformers_version": "4.30.2",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.30.1"
+  "transformers_version": "4.30.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b24777bd9fbe447f3f241523d32a29b9ef49d1a1d0eff81100e242a7ab64f7
-size 497807197
+oid sha256:b702b7eca07c02fb48b81c0942f1a864e7bd1b3155bbceae4557d3c3c156c3d2
+size 1419383773