Upload model

config.json

@@ -1,24 +1,40 @@
 {
+  "activation_function": "gelu_new",
+  "add_cross_attention": true,
   "architectures": [
-    "ViTModel"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
-  "image_size": 224,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
-  "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
-  "pooler_act": "tanh",
-  "pooler_output_size": 768,
-  "qkv_bias": true,
+  "is_decoder": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "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": "4.50.2"
+  "transformers_version": "4.50.2",
+  "use_cache": true,
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200cde6f26db8d28dce71aa48ed860c13b4a4e9bd3cc1fb9c35b47de9855b74b
-size 345579424
+oid sha256:451caa709de3103a2cb63db9a3858e9d27890a4cb4498d475d6a7de81646833e
+size 611252424