Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,65 @@
 {
-  "bos_token": "<|end|>",
-  "eos_token": "<|end|>",
-  "pad_token": "<|end|>",
-  "unk_token": "<|end|>"
+  "additional_special_tokens": [
+    "<|reg_extra|>",
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|endofprompt|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pause|>",
+    "<|reg0|>",
+    "<|reg1|>",
+    "<|reg2|>",
+    "<|reg3|>",
+    "<|reg4|>",
+    "<|reg5|>",
+    "<|reg6|>",
+    "<|reg7|>",
+    "<|extra0|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86bb7b272d5e2649c6013ed8cbf564802f0c36cede60687af4192dc3f8d1acfb
-size 4239708
+oid sha256:290f60278265b590e6e79137d425f9aa8c19d934e08b6ac7a6229e55a1bdaa27
+size 4239524

tokenizer_config.json

@@ -264,27 +264,53 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "100289": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<|end|>",
+  "additional_special_tokens": [
+    "<|reg_extra|>",
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|endofprompt|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pause|>",
+    "<|reg0|>",
+    "<|reg1|>",
+    "<|reg2|>",
+    "<|reg3|>",
+    "<|reg4|>",
+    "<|reg5|>",
+    "<|reg6|>",
+    "<|reg7|>",
+    "<|extra0|>"
+  ],
+  "bos_token": "<|endoftext|>",
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end|>",
+  "eos_token": "<|endoftext|>",
   "max_length": 2048,
-  "model_max_length": 512,
-  "pad_token": "<|end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
   "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": "<|end|>"
+  "unk_token": "<|endoftext|>"
 }