Upload model

config.json

@@ -1,25 +1,39 @@
 {
-  "_name_or_path": "bert-small/checkpoint-160000",
+  "_name_or_path": "./gpt2-base/checkpoint-130000",
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertForMaskedLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 4,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 100000
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
-  "pad_token_id": 0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece31f1a9fa6fd332a511e19fb05fef4072e7484972a9568f13c8d0acb1db83c
-size 257758256
+oid sha256:8afb81cd09a3cffc42d396023aa2aa3ec5badb108c047446276d8c449272fd99
+size 650584704