Upload model

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 3,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 256,
+  "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": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 115
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b283429a987d18374784eab74ec5e0e1dc3c65e350fdc09b9cfcf5b6e88b7309
+size 341378688

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "UTT_BOUNDARY",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "UTT_BOUNDARY",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "PAD",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "UNK",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,244 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "UNK",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "PAD",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "UTT_BOUNDARY",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "NFD"
+      },
+      {
+        "type": "Lowercase"
+      },
+      {
+        "type": "Strip",
+        "strip_left": true,
+        "strip_right": true
+      },
+      {
+        "type": "StripAccents"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": " "
+        },
+        "content": ""
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "String": ""
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "UTT_BOUNDARY",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "UTT_BOUNDARY",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "UTT_BOUNDARY",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "UTT_BOUNDARY": {
+        "id": "UTT_BOUNDARY",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "UTT_BOUNDARY"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "UNK": 0,
+      "PAD": 1,
+      "W": 2,
+      "UTT_BOUNDARY": 3,
+      "y": 4,
+      "e": 5,
+      "a": 6,
+      "h": 7,
+      ".": 8,
+      "c": 9,
+      "o": 10,
+      "m": 11,
+      "p": 12,
+      "u": 13,
+      "n": 14,
+      "d": 15,
+      "'": 16,
+      "s": 17,
+      "t": 18,
+      "i": 19,
+      "g": 20,
+      "l": 21,
+      "k": 22,
+      "x": 23,
+      ",": 24,
+      "r": 25,
+      "w": 26,
+      "v": 27,
+      "f": 28,
+      "b": 29,
+      "j": 30,
+      "?": 31,
+      "-": 32,
+      "q": 33,
+      ";": 34,
+      "2": 35,
+      "‘": 36,
+      "’": 37,
+      "!": 38,
+      "/": 39,
+      "1": 40,
+      ":": 41,
+      "z": 42,
+      "3": 43,
+      "6": 44,
+      "9": 45,
+      "&": 46,
+      "4": 47,
+      "5": 48,
+      "0": 49,
+      "=": 50,
+      "8": 51,
+      "7": 52,
+      "£": 53,
+      "(": 54,
+      ")": 55,
+      "—": 56,
+      "*": 57,
+      "]": 58,
+      "[": 59,
+      "\"": 60,
+      "_": 61,
+      "%": 62,
+      "“": 63,
+      "”": 64,
+      "+": 65,
+      "$": 66,
+      "^": 67,
+      "#": 68,
+      "æ": 69,
+      "ʌ": 70,
+      "ɩ": 71,
+      "ə": 72,
+      "↫": 73,
+      "|": 74,
+      "°": 75,
+      "ø": 76,
+      "~": 77,
+      "⁄": 78,
+      "`": 79,
+      "�": 80,
+      "′": 81,
+      "@": 82,
+      "}": 83,
+      "{": 84,
+      "―": 85,
+      "–": 86,
+      "·": 87,
+      "♪": 88,
+      "¡": 89,
+      "÷": 90,
+      "\\": 91,
+      "¶": 92,
+      "ð": 93,
+      "¿": 94,
+      "­": 95,
+      "♫": 96,
+      "​": 97,
+      "œ": 98,
+      "ł": 99,
+      "¦": 100,
+      "×": 101,
+      "™": 102,
+      "ß": 103,
+      "ˈ": 104,
+      "ı": 105,
+      "đ": 106,
+      "−": 107,
+      "ː": 108,
+      "•": 109,
+      "⟨": 110,
+      "⟩": 111,
+      "ŋ": 112,
+      "ʼ": 113,
+      "\t": 114
+    },
+    "unk_token": "UNK"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "UNK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "PAD",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "UTT_BOUNDARY",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "UTT_BOUNDARY",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "UTT_BOUNDARY",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "PAD",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "UNK"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fa734da6cb25f5559da3afe4f24c337b478930763d251de0bc666d081e17fb
+size 5368

vocab.json

@@ -0,0 +1 @@
+{"UNK":0,"PAD":1,"W":2,"UTT_BOUNDARY":3,"y":4,"e":5,"a":6,"h":7,".":8,"c":9,"o":10,"m":11,"p":12,"u":13,"n":14,"d":15,"'":16,"s":17,"t":18,"i":19,"g":20,"l":21,"k":22,"x":23,",":24,"r":25,"w":26,"v":27,"f":28,"b":29,"j":30,"?":31,"-":32,"q":33,";":34,"2":35,"‘":36,"’":37,"!":38,"/":39,"1":40,":":41,"z":42,"3":43,"6":44,"9":45,"&":46,"4":47,"5":48,"0":49,"=":50,"8":51,"7":52,"£":53,"(":54,")":55,"—":56,"*":57,"]":58,"[":59,"\"":60,"_":61,"%":62,"“":63,"”":64,"+":65,"$":66,"^":67,"#":68,"æ":69,"ʌ":70,"ɩ":71,"ə":72,"↫":73,"|":74,"°":75,"ø":76,"~":77,"⁄":78,"`":79,"�":80,"′":81,"@":82,"}":83,"{":84,"―":85,"–":86,"·":87,"♪":88,"¡":89,"÷":90,"\\":91,"¶":92,"ð":93,"¿":94,"­":95,"♫":96,"​":97,"œ":98,"ł":99,"¦":100,"×":101,"™":102,"ß":103,"ˈ":104,"ı":105,"đ":106,"−":107,"ː":108,"•":109,"⟨":110,"⟩":111,"ŋ":112,"ʼ":113,"\t":114}