Upload model

config.json

@@ -1,24 +1,32 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "relu",
+  "_name_or_path": "distilbert/distilgpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "GPT2LMHeadModel"
   ],
-  "attention_dropout": 0.4,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "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,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "vocab_size": 30522
+  "use_cache": true,
+  "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff400350725866c809f3f5b2c77149278be0bf66ae656cb94d9da041b0331e7
-size 265470032
+oid sha256:e78e61065a45800b9d68840c30e624f78e0da4efca292e66c9d810adad6b5897
+size 497774208