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": 51
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452fe745e87696095ab7b0b2bda9d3a8fdf41527e9ea659af9d1d7e269232182
+size 341182080

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 +1,166 @@
+{
+  "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": "Replace",
+        "pattern": {
+          "String": " WORD_BOUNDARY"
+        },
+        "content": ""
+      },
+      {
+        "type": "Strip",
+        "strip_left": true,
+        "strip_right": true
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "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,
+      "WORD_BOUNDARY": 2,
+      "UTT_BOUNDARY": 3,
+      "j": 4,
+      "ɛ": 5,
+      "h": 6,
+      "k": 7,
+      "ɑ": 8,
+      "m": 9,
+      "p": 10,
+      "aʊ": 11,
+      "n": 12,
+      "d": 13,
+      "z": 14,
+      "θ": 15,
+      "ɪ": 16,
+      "ŋ": 17,
+      "l": 18,
+      "aɪ": 19,
+      "s": 20,
+      "ɜː": 21,
+      "t": 22,
+      "w": 23,
+      "v": 24,
+      "ð": 25,
+      "æ": 26,
+      "ɔ": 27,
+      "ɹ": 28,
+      "ʌ": 29,
+      "f": 30,
+      "ə": 31,
+      "b": 32,
+      "iː": 33,
+      "eɪ": 34,
+      "oʊ": 35,
+      "d̠ʒ": 36,
+      "i": 37,
+      "uː": 38,
+      "iə": 39,
+      "ʊ": 40,
+      "ɡ": 41,
+      "t̠ʃ": 42,
+      "ɔɪ": 43,
+      "ʃ": 44,
+      "ʒ": 45,
+      "r": 46,
+      "x": 47,
+      "ɬ": 48,
+      "ɑ̃": 49,
+      "nʲ": 50
+    },
+    "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 sha256:07b857f0c7f5ff42d26627cc5c529e93d9d5e7281f236267235c06475167c2c6
+size 5368

vocab.json

@@ -0,0 +1 @@
+{"UNK":0,"PAD":1,"WORD_BOUNDARY":2,"UTT_BOUNDARY":3,"j":4,"ɛ":5,"h":6,"k":7,"ɑ":8,"m":9,"p":10,"aʊ":11,"n":12,"d":13,"z":14,"θ":15,"ɪ":16,"ŋ":17,"l":18,"aɪ":19,"s":20,"ɜː":21,"t":22,"w":23,"v":24,"ð":25,"æ":26,"ɔ":27,"ɹ":28,"ʌ":29,"f":30,"ə":31,"b":32,"iː":33,"eɪ":34,"oʊ":35,"d̠ʒ":36,"i":37,"uː":38,"iə":39,"ʊ":40,"ɡ":41,"t̠ʃ":42,"ɔɪ":43,"ʃ":44,"ʒ":45,"r":46,"x":47,"ɬ":48,"ɑ̃":49,"nʲ":50}