Upload model

config.json

@@ -1,26 +1,46 @@
 {
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "RobertaForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attn_pdrop": 0.1,
   "bos_token_id": 0,
-  "classifier_dropout": null,
+  "embd_pdrop": 0.1,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "roberta",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "4.30.2",
-  "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 64001
 }

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "pad_token_id": 1,
   "transformers_version": "4.30.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f130bf2ccf15d81e1029d0482d2cc9699d16b498cabd0ee2557f6c4aafd23bef
-size 85581369
+oid sha256:7fade51bceb1e4bb240f51323aa53cc309e83d0bcf865fe69c390853c38778c7
+size 369896341