Refreshed metadata and configs and tokenizer files

added_tokens.json

@@ -1 +1,5 @@
-{"<|unknown|>": 50259, "<|startoftext|>": 50258, "<|endoftext|>": 50257}
+{
+  "<|endoftext|>": 50257,
+  "<|startoftext|>": 50258,
+  "<|unknown|>": 50259
+}

config.json

@@ -59,8 +59,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.9.0.dev0",
-  "use_cache": true,
+  "transformers_version": "4.21.0.dev0",
   "vocab_size": 50257,
   "window_size": 256
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ ×
 × Ļ
 × ķ

special_tokens_map.json

@@ -2,4 +2,4 @@
   "bos_token": "<s>",
   "eos_token": "</s>",
   "unk_token": "<unk>"
-}
+}

tokenizer_config.json

@@ -1 +1,36 @@
-{"do_lower_case": false, "max_len": 1024, "bos_token": "<|startoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "special_tokens_map_file": "special_tokens_map.json", "full_tokenizer_file": null}
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "max_len": 1024,
+  "name_or_path": "./hebrew-gpt_neo-xl",
+  "pad_token": null,
+  "special_tokens_map_file": "special_tokens_map.json",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}