Upload model

config.json

@@ -1,22 +1,27 @@
 {
   "_name_or_path": "mGPT-base",
-  "afn": "gelu",
+  "activation_function": "gelu_new",
+  "afn": "gelu_new",
   "architectures": [
-    "OpenAIGPTModel"
+    "GPT2Model"
   ],
   "attn_pdrop": 0.1,
+  "bos_token_id": 101,
   "embd_pdrop": 0.1,
+  "eos_token_id": 102,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-12,
-  "model_type": "openai-gpt",
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
   "n_ctx": 512,
   "n_embd": 768,
   "n_head": 12,
+  "n_inner": null,
   "n_layer": 12,
   "n_positions": 512,
-  "n_special": 0,
-  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -29,5 +34,6 @@
     }
   },
   "transformers_version": "4.23.1",
+  "use_cache": true,
   "vocab_size": 119547
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9944360654b0eb5bbbc9aae52305d5c47772db77665fd0f4b8c313bbbb609da6
-size 709213544
+oid sha256:ca447bd099e618a62c80e015be857d8f4e6dcfa0513280e84d65d05b5fe2ee55
+size 709221480