Upload folder using huggingface_hub

config.json

@@ -0,0 +1,23 @@
+{
+    "n_layer": 6,
+    "n_head": 4,
+    "n_embd": 256,
+    "max_position_embeddings": 512,
+    "vocab_size": 94,
+    "model_type": "gpt2",
+    "architectures": [
+        "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "embd_pdrop": 0.1,
+    "resid_pdrop": 0.1,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "n_positions": 512,
+    "scale_attn_weights": true,
+    "use_cache": true,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "pad_token_id": 0,
+    "unk_token_id": 3
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d74df2a09fe381c9e7bbb9c14fd2defe8ceb3f622a31e98bc1a93ae7ac740d
+size 25876288

tokenizer.json

@@ -0,0 +1,395 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Lowercase"
+      },
+      {
+        "type": "NFKC"
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<unk>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<pad>": 0,
+      "<bos>": 1,
+      "<eos>": 2,
+      "<unk>": 3,
+      "(": 4,
+      ")": 5,
+      ",": 6,
+      ".": 7,
+      "a": 8,
+      "b": 9,
+      "c": 10,
+      "d": 11,
+      "e": 12,
+      "f": 13,
+      "g": 14,
+      "h": 15,
+      "i": 16,
+      "j": 17,
+      "k": 18,
+      "l": 19,
+      "m": 20,
+      "n": 21,
+      "o": 22,
+      "p": 23,
+      "r": 24,
+      "s": 25,
+      "t": 26,
+      "u": 27,
+      "v": 28,
+      "y": 29,
+      "z": 30,
+      "ç": 31,
+      "ö": 32,
+      "ü": 33,
+      "ğ": 34,
+      "ı": 35,
+      "ş": 36,
+      "el": 37,
+      "in": 38,
+      "il": 39,
+      "er": 40,
+      "ir": 41,
+      "en": 42,
+      "la": 43,
+      "me": 44,
+      "bir": 45,
+      "da": 46,
+      "dil": 47,
+      "ok": 48,
+      "tü": 49,
+      "eli": 50,
+      "eni": 51,
+      "bu": 52,
+      "eğ": 53,
+      "gü": 54,
+      "ha": 55,
+      "kç": 56,
+      "le": 57,
+      "ma": 58,
+      "or": 59,
+      "yor": 60,
+      "ır": 61,
+      "eği": 62,
+      "ar": 63,
+      "ay": 64,
+      "ala": 65,
+      "du": 66,
+      "dır": 67,
+      "ek": 68,
+      "gin": 69,
+      "iç": 70,
+      "ldu": 71,
+      "mo": 72,
+      "ne": 73,
+      "oldu": 74,
+      "rkç": 75,
+      "tir": 76,
+      "tok": 77,
+      "ve": 78,
+      "ya": 79,
+      "zel": 80,
+      "zer": 81,
+      "çok": 82,
+      "ştir": 83,
+      "türkç": 84,
+      "enizer": 85,
+      "lem": 86,
+      "mak": 87,
+      "eğit": 88,
+      "alan": 89,
+      "için": 90,
+      "mod": 91,
+      "tokenizer": 92,
+      "türkçe": 93
+    },
+    "merges": [
+      [
+        "e",
+        "l"
+      ],
+      [
+        "i",
+        "n"
+      ],
+      [
+        "i",
+        "l"
+      ],
+      [
+        "e",
+        "r"
+      ],
+      [
+        "i",
+        "r"
+      ],
+      [
+        "e",
+        "n"
+      ],
+      [
+        "l",
+        "a"
+      ],
+      [
+        "m",
+        "e"
+      ],
+      [
+        "b",
+        "ir"
+      ],
+      [
+        "d",
+        "a"
+      ],
+      [
+        "d",
+        "il"
+      ],
+      [
+        "o",
+        "k"
+      ],
+      [
+        "t",
+        "ü"
+      ],
+      [
+        "el",
+        "i"
+      ],
+      [
+        "en",
+        "i"
+      ],
+      [
+        "b",
+        "u"
+      ],
+      [
+        "e",
+        "ğ"
+      ],
+      [
+        "g",
+        "ü"
+      ],
+      [
+        "h",
+        "a"
+      ],
+      [
+        "k",
+        "ç"
+      ],
+      [
+        "l",
+        "e"
+      ],
+      [
+        "m",
+        "a"
+      ],
+      [
+        "o",
+        "r"
+      ],
+      [
+        "y",
+        "or"
+      ],
+      [
+        "ı",
+        "r"
+      ],
+      [
+        "eğ",
+        "i"
+      ],
+      [
+        "a",
+        "r"
+      ],
+      [
+        "a",
+        "y"
+      ],
+      [
+        "a",
+        "la"
+      ],
+      [
+        "d",
+        "u"
+      ],
+      [
+        "d",
+        "ır"
+      ],
+      [
+        "e",
+        "k"
+      ],
+      [
+        "g",
+        "in"
+      ],
+      [
+        "i",
+        "ç"
+      ],
+      [
+        "l",
+        "du"
+      ],
+      [
+        "m",
+        "o"
+      ],
+      [
+        "n",
+        "e"
+      ],
+      [
+        "o",
+        "ldu"
+      ],
+      [
+        "r",
+        "kç"
+      ],
+      [
+        "t",
+        "ir"
+      ],
+      [
+        "t",
+        "ok"
+      ],
+      [
+        "v",
+        "e"
+      ],
+      [
+        "y",
+        "a"
+      ],
+      [
+        "z",
+        "el"
+      ],
+      [
+        "z",
+        "er"
+      ],
+      [
+        "ç",
+        "ok"
+      ],
+      [
+        "ş",
+        "tir"
+      ],
+      [
+        "tü",
+        "rkç"
+      ],
+      [
+        "eni",
+        "zer"
+      ],
+      [
+        "le",
+        "m"
+      ],
+      [
+        "ma",
+        "k"
+      ],
+      [
+        "eği",
+        "t"
+      ],
+      [
+        "ala",
+        "n"
+      ],
+      [
+        "iç",
+        "in"
+      ],
+      [
+        "mo",
+        "d"
+      ],
+      [
+        "tok",
+        "enizer"
+      ],
+      [
+        "türkç",
+        "e"
+      ]
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+    "model_max_length": 512,
+    "add_prefix_space": false,
+    "bos_token": "<bos>",
+    "eos_token": "<eos>",
+    "unk_token": "<unk>",
+    "pad_token": "<pad>",
+    "errors": "replace",
+    "tokenizer_class": "PreTrainedTokenizerFast",
+    "name_or_path": "SykoLLM-0.1B-HF",
+    "do_lower_case": true,
+    "special_tokens_map_file": null
+}

vocab.json

@@ -0,0 +1,96 @@
+{
+    "ldu": 71,
+    "b": 9,
+    "i\u00e7": 70,
+    "t\u00fcrk\u00e7": 84,
+    "g\u00fc": 54,
+    "ne": 73,
+    "el": 37,
+    "tok": 77,
+    "ek": 68,
+    "ala": 65,
+    "mod": 91,
+    "enizer": 85,
+    "in": 38,
+    "ya": 79,
+    "<bos>": 1,
+    "n": 21,
+    "l": 19,
+    "\u00e7": 31,
+    "tir": 76,
+    "ha": 55,
+    "ar": 63,
+    "le": 57,
+    "<eos>": 2,
+    "d": 11,
+    "ma": 58,
+    "bu": 52,
+    "p": 23,
+    "r": 24,
+    "e": 12,
+    ",": 6,
+    "eli": 50,
+    "(": 4,
+    "\u00e7ok": 82,
+    "y": 29,
+    "<unk>": 3,
+    "la": 43,
+    "k\u00e7": 56,
+    ")": 5,
+    "lem": 86,
+    "j": 17,
+    "tokenizer": 92,
+    "t\u00fcrk\u00e7e": 93,
+    "e\u011f": 53,
+    "s": 25,
+    "gin": 69,
+    "ir": 41,
+    "g": 14,
+    "k": 18,
+    "\u00fc": 33,
+    "d\u0131r": 67,
+    "me": 44,
+    "eni": 51,
+    ".": 7,
+    "z": 30,
+    "e\u011fit": 88,
+    "h": 15,
+    "du": 66,
+    "yor": 60,
+    "u": 27,
+    "mak": 87,
+    "mo": 72,
+    "er": 40,
+    "i\u00e7in": 90,
+    "a": 8,
+    "da": 46,
+    "\u015f": 36,
+    "t": 26,
+    "ve": 78,
+    "t\u00fc": 49,
+    "\u0131": 35,
+    "dil": 47,
+    "c": 10,
+    "ok": 48,
+    "\u015ftir": 83,
+    "rk\u00e7": 75,
+    "bir": 45,
+    "alan": 89,
+    "il": 39,
+    "\u0131r": 61,
+    "\u00f6": 32,
+    "m": 20,
+    "oldu": 74,
+    "\u011f": 34,
+    "zel": 80,
+    "v": 28,
+    "zer": 81,
+    "i": 16,
+    "e\u011fi": 62,
+    "f": 13,
+    "<pad>": 0,
+    "ay": 64,
+    "en": 42,
+    "or": 59,
+    "o": 22
+}