Upload folder using huggingface_hub

braille256_vocab.json

@@ -0,0 +1,263 @@
+{
+  "[PAD]": 0,
+  "[UNK]": 1,
+  "[BOS]": 2,
+  "[EOS]": 3,
+  "[MASK]": 4,
+  "⠀": 5,
+  "⠁": 6,
+  "⠂": 7,
+  "⠃": 8,
+  "⠄": 9,
+  "⠅": 10,
+  "⠆": 11,
+  "⠇": 12,
+  "⠈": 13,
+  "⠉": 14,
+  "⠊": 15,
+  "⠋": 16,
+  "⠌": 17,
+  "⠍": 18,
+  "⠎": 19,
+  "⠏": 20,
+  "⠐": 21,
+  "⠑": 22,
+  "⠒": 23,
+  "⠓": 24,
+  "⠔": 25,
+  "⠕": 26,
+  "⠖": 27,
+  "⠗": 28,
+  "⠘": 29,
+  "⠙": 30,
+  "⠚": 31,
+  "⠛": 32,
+  "⠜": 33,
+  "⠝": 34,
+  "⠞": 35,
+  "⠟": 36,
+  "⠠": 37,
+  "⠡": 38,
+  "⠢": 39,
+  "⠣": 40,
+  "⠤": 41,
+  "⠥": 42,
+  "⠦": 43,
+  "⠧": 44,
+  "⠨": 45,
+  "⠩": 46,
+  "⠪": 47,
+  "⠫": 48,
+  "⠬": 49,
+  "⠭": 50,
+  "⠮": 51,
+  "⠯": 52,
+  "⠰": 53,
+  "⠱": 54,
+  "⠲": 55,
+  "⠳": 56,
+  "⠴": 57,
+  "⠵": 58,
+  "⠶": 59,
+  "⠷": 60,
+  "⠸": 61,
+  "⠹": 62,
+  "⠺": 63,
+  "⠻": 64,
+  "⠼": 65,
+  "⠽": 66,
+  "⠾": 67,
+  "⠿": 68,
+  "⡀": 69,
+  "⡁": 70,
+  "⡂": 71,
+  "⡃": 72,
+  "⡄": 73,
+  "⡅": 74,
+  "⡆": 75,
+  "⡇": 76,
+  "⡈": 77,
+  "⡉": 78,
+  "⡊": 79,
+  "⡋": 80,
+  "⡌": 81,
+  "⡍": 82,
+  "⡎": 83,
+  "⡏": 84,
+  "⡐": 85,
+  "⡑": 86,
+  "⡒": 87,
+  "⡓": 88,
+  "⡔": 89,
+  "⡕": 90,
+  "⡖": 91,
+  "⡗": 92,
+  "⡘": 93,
+  "⡙": 94,
+  "⡚": 95,
+  "⡛": 96,
+  "⡜": 97,
+  "⡝": 98,
+  "⡞": 99,
+  "⡟": 100,
+  "⡠": 101,
+  "⡡": 102,
+  "⡢": 103,
+  "⡣": 104,
+  "⡤": 105,
+  "⡥": 106,
+  "⡦": 107,
+  "⡧": 108,
+  "⡨": 109,
+  "⡩": 110,
+  "⡪": 111,
+  "⡫": 112,
+  "⡬": 113,
+  "⡭": 114,
+  "⡮": 115,
+  "⡯": 116,
+  "⡰": 117,
+  "⡱": 118,
+  "⡲": 119,
+  "⡳": 120,
+  "⡴": 121,
+  "⡵": 122,
+  "⡶": 123,
+  "⡷": 124,
+  "⡸": 125,
+  "⡹": 126,
+  "⡺": 127,
+  "⡻": 128,
+  "⡼": 129,
+  "⡽": 130,
+  "⡾": 131,
+  "⡿": 132,
+  "⢀": 133,
+  "⢁": 134,
+  "⢂": 135,
+  "⢃": 136,
+  "⢄": 137,
+  "⢅": 138,
+  "⢆": 139,
+  "⢇": 140,
+  "⢈": 141,
+  "⢉": 142,
+  "⢊": 143,
+  "⢋": 144,
+  "⢌": 145,
+  "⢍": 146,
+  "⢎": 147,
+  "⢏": 148,
+  "⢐": 149,
+  "⢑": 150,
+  "⢒": 151,
+  "⢓": 152,
+  "⢔": 153,
+  "⢕": 154,
+  "⢖": 155,
+  "⢗": 156,
+  "⢘": 157,
+  "⢙": 158,
+  "⢚": 159,
+  "⢛": 160,
+  "⢜": 161,
+  "⢝": 162,
+  "⢞": 163,
+  "⢟": 164,
+  "⢠": 165,
+  "⢡": 166,
+  "⢢": 167,
+  "⢣": 168,
+  "⢤": 169,
+  "⢥": 170,
+  "⢦": 171,
+  "⢧": 172,
+  "⢨": 173,
+  "⢩": 174,
+  "⢪": 175,
+  "⢫": 176,
+  "⢬": 177,
+  "⢭": 178,
+  "⢮": 179,
+  "⢯": 180,
+  "⢰": 181,
+  "⢱": 182,
+  "⢲": 183,
+  "⢳": 184,
+  "⢴": 185,
+  "⢵": 186,
+  "⢶": 187,
+  "⢷": 188,
+  "⢸": 189,
+  "⢹": 190,
+  "⢺": 191,
+  "⢻": 192,
+  "⢼": 193,
+  "⢽": 194,
+  "⢾": 195,
+  "⢿": 196,
+  "⣀": 197,
+  "⣁": 198,
+  "⣂": 199,
+  "⣃": 200,
+  "⣄": 201,
+  "⣅": 202,
+  "⣆": 203,
+  "⣇": 204,
+  "⣈": 205,
+  "⣉": 206,
+  "⣊": 207,
+  "⣋": 208,
+  "⣌": 209,
+  "⣍": 210,
+  "⣎": 211,
+  "⣏": 212,
+  "⣐": 213,
+  "⣑": 214,
+  "⣒": 215,
+  "⣓": 216,
+  "⣔": 217,
+  "⣕": 218,
+  "⣖": 219,
+  "⣗": 220,
+  "⣘": 221,
+  "⣙": 222,
+  "⣚": 223,
+  "⣛": 224,
+  "⣜": 225,
+  "⣝": 226,
+  "⣞": 227,
+  "⣟": 228,
+  "⣠": 229,
+  "⣡": 230,
+  "⣢": 231,
+  "⣣": 232,
+  "⣤": 233,
+  "⣥": 234,
+  "⣦": 235,
+  "⣧": 236,
+  "⣨": 237,
+  "⣩": 238,
+  "⣪": 239,
+  "⣫": 240,
+  "⣬": 241,
+  "⣭": 242,
+  "⣮": 243,
+  "⣯": 244,
+  "⣰": 245,
+  "⣱": 246,
+  "⣲": 247,
+  "⣳": 248,
+  "⣴": 249,
+  "⣵": 250,
+  "⣶": 251,
+  "⣷": 252,
+  "⣸": 253,
+  "⣹": 254,
+  "⣺": 255,
+  "⣻": 256,
+  "⣼": 257,
+  "⣽": 258,
+  "⣾": 259,
+  "⣿": 260
+}

config.json

@@ -0,0 +1,13 @@
+{
+  "architectures": [
+    "Braille256Model"
+  ],
+  "dtype": "float32",
+  "hidden_size": 512,
+  "intermediate_size": 2048,
+  "model_type": "braille256",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "transformers_version": "4.57.1",
+  "use_dot_pattern_init": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1add3cd68c802584c00480d9d070aa40e5040b506f1d53c659c396584664b56b
+size 102504944

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "Braille256Tokenizer",
+  "unk_token": "[UNK]"
+}

training_config.json

@@ -0,0 +1,18 @@
+{
+  "output_dir": "models/braille256_scaled/braille256_scaled_64M",
+  "learning_rate": 0.0003,
+  "weight_decay": 0.01,
+  "warmup_steps": 1000,
+  "max_steps": 10000,
+  "per_device_train_batch_size": 16,
+  "per_device_eval_batch_size": 16,
+  "gradient_accumulation_steps": 2,
+  "max_seq_length": 512,
+  "logging_steps": 100,
+  "eval_steps": 500,
+  "save_steps": 1000,
+  "track_emergent_patterns": true,
+  "pattern_analysis_steps": 1000,
+  "fp16": true,
+  "dataloader_num_workers": 4
+}