Upload 12 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -1,13 +1 @@
-{
-  "model_type": "gpt2",
-  "architectures": ["GPT2LMHeadModel"],
-  "tokenizer_class": "GPT2Tokenizer",
-  "vocab_size": 1000,
-  "hidden_size": 16,
-  "embedding_size": 16,
-  "num_attention_heads": 4,
-  "num_hidden_layers": 2,
-  "max_position_embeddings": 10,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-12
-}
+{"vocab_size": 30522, "embedding_dim": 512, "hidden_dim": 1024, "num_layers": 6, "model_type": "sparkoo"}

special_tokens_map.json

@@ -1,7 +1,30 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,39 +1,17 @@
 {
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
+    "50257": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,15 +19,12 @@
       "special": true
     }
   },
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
   "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }