Add tokenizer
Browse files- added_tokens.json +35 -0
- chat_template.jinja +100 -0
- merges.txt +0 -0
- special_tokens_map.json +86 -0
- tokenizer.json +0 -0
- tokenizer_config.json +501 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<EMAIL>": 110521,
|
| 3 |
+
"<KEY>": 110522,
|
| 4 |
+
"<NAME>": 110520,
|
| 5 |
+
"<PASSWORD>": 110523,
|
| 6 |
+
"<code_to_intermediate>": 110502,
|
| 7 |
+
"<empty_output>": 110501,
|
| 8 |
+
"<file_sep>": 110492,
|
| 9 |
+
"<intermediate_to_code>": 110503,
|
| 10 |
+
"<issue_closed>": 110495,
|
| 11 |
+
"<issue_comment>": 110494,
|
| 12 |
+
"<issue_start>": 110493,
|
| 13 |
+
"<jupyter_code>": 110498,
|
| 14 |
+
"<jupyter_output>": 110499,
|
| 15 |
+
"<jupyter_script>": 110500,
|
| 16 |
+
"<jupyter_start>": 110496,
|
| 17 |
+
"<jupyter_text>": 110497,
|
| 18 |
+
"<pr>": 110504,
|
| 19 |
+
"<pr_base>": 110507,
|
| 20 |
+
"<pr_base_code>": 110509,
|
| 21 |
+
"<pr_comment>": 110512,
|
| 22 |
+
"<pr_diff>": 110510,
|
| 23 |
+
"<pr_diff_hunk>": 110511,
|
| 24 |
+
"<pr_diff_hunk_comment_line>": 110519,
|
| 25 |
+
"<pr_event_id>": 110513,
|
| 26 |
+
"<pr_file>": 110508,
|
| 27 |
+
"<pr_in_reply_to_comment_id>": 110518,
|
| 28 |
+
"<pr_in_reply_to_review_id>": 110517,
|
| 29 |
+
"<pr_is_merged>": 110506,
|
| 30 |
+
"<pr_review>": 110514,
|
| 31 |
+
"<pr_review_comment>": 110516,
|
| 32 |
+
"<pr_review_state>": 110515,
|
| 33 |
+
"<pr_status>": 110505,
|
| 34 |
+
"<repo_name>": 110491
|
| 35 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if tools is not defined or tools is none %}
|
| 2 |
+
{{- '<|im_start|>tool_list\n<|im_end|>\n' }}
|
| 3 |
+
{%- else %}
|
| 4 |
+
{{- '<|im_start|>tool_list\n[' }}
|
| 5 |
+
{%- for tool in tools %}
|
| 6 |
+
{{- '{"name": "' }}
|
| 7 |
+
{{- tool.function.name }}
|
| 8 |
+
{{- '", ' }}
|
| 9 |
+
{{- '"description": "' }}
|
| 10 |
+
{{- tool.function.description }}
|
| 11 |
+
{{- '"' }}
|
| 12 |
+
{%- if tool.function.parameters is defined %}
|
| 13 |
+
{{- ', "parameters": ' }}
|
| 14 |
+
{{- tool.function.parameters | tojson }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{{- '}' }}
|
| 17 |
+
{%- if not loop.last %}
|
| 18 |
+
{{- ', ' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endfor %}
|
| 21 |
+
{{- ']<|im_end|>\n' }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
|
| 24 |
+
{%- set ns = namespace(is_searching=true, last_query_index=messages|length - 1) %}
|
| 25 |
+
{%- for message in messages[::-1] %}
|
| 26 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 27 |
+
{%- if ns.is_searching and (message.role == 'user' or message.role == 'tool') %}
|
| 28 |
+
{%- set ns.last_query_index = index %}
|
| 29 |
+
{%- set ns.is_searching = false %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
|
| 33 |
+
{%- for message in messages %}
|
| 34 |
+
{%- if loop.index0 == 0 and message.role != 'system' %}
|
| 35 |
+
{{- '<|im_start|>system\n<|im_end|>\n' }}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
|
| 38 |
+
{%- if message.content is string %}
|
| 39 |
+
{%- set content = message.content %}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{%- set content = '' %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
|
| 44 |
+
{%- set reasoning_content = '' %}
|
| 45 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 46 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.role == "assistant" %}
|
| 49 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 50 |
+
{%- if reasoning_content %}
|
| 51 |
+
{{- '<|im_start|>assistant/think\n' + reasoning_content.strip('\n') + '<|im_end|>\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- endif %}
|
| 54 |
+
|
| 55 |
+
{%- if content %}
|
| 56 |
+
{{- '<|im_start|>assistant\n' + content.strip('\n') + '<|im_end|>' }}
|
| 57 |
+
{%- if message.tool_calls %}
|
| 58 |
+
{{- '\n' }}
|
| 59 |
+
{%- else %}
|
| 60 |
+
{{- '<|endofturn|>\n' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
|
| 64 |
+
{%- if message.tool_calls %}
|
| 65 |
+
{{- '<|im_start|>assistant -> tool/function_call\n[' }}
|
| 66 |
+
{%- for tool_call in message.tool_calls %}
|
| 67 |
+
{%- if not loop.first %}
|
| 68 |
+
{{- ', ' }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if tool_call.function %}
|
| 71 |
+
{%- set tool_call = tool_call.function %}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{{- '{"name": "' }}
|
| 74 |
+
{{- tool_call.name }}
|
| 75 |
+
{{- '", "arguments": ' }}
|
| 76 |
+
{%- if tool_call.arguments is string %}
|
| 77 |
+
{{- tool_call.arguments }}
|
| 78 |
+
{%- else %}
|
| 79 |
+
{{- tool_call.arguments | tojson }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{{- '}' }}
|
| 82 |
+
{%- endfor %}
|
| 83 |
+
{{- ']<|im_end|><|stop|>\n' }}
|
| 84 |
+
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{%- elif message.role == "tool" %}
|
| 87 |
+
{{- '<|im_start|>tool/function_call\n' + content + '<|im_end|>\n' }}
|
| 88 |
+
{%- else %}
|
| 89 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' }}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{%- endfor %}
|
| 92 |
+
{%- if add_generation_prompt %}
|
| 93 |
+
{%- if force_reasoning is defined and force_reasoning is true %}
|
| 94 |
+
{{- '<|im_start|>assistant/think\n' }}
|
| 95 |
+
{%- elif skip_reasoning is defined and skip_reasoning is true %}
|
| 96 |
+
{{- '<|im_start|>assistant\n' }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{{- '<|im_start|>assistant' }}
|
| 99 |
+
{%- endif %}
|
| 100 |
+
{%- endif %}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|fim_prefix|>",
|
| 5 |
+
"<|fim_middle|>",
|
| 6 |
+
"<|fim_suffix|>",
|
| 7 |
+
"<|endofprompt|>",
|
| 8 |
+
"<|_unuse_missing_100256|>",
|
| 9 |
+
"<|_unuse_missing_100261|>",
|
| 10 |
+
"<|_unuse_missing_100262|>",
|
| 11 |
+
"<|_unuse_missing_100263|>",
|
| 12 |
+
"<|_unuse_missing_100264|>",
|
| 13 |
+
"<|_unuse_missing_100265|>",
|
| 14 |
+
"<|_unuse_missing_100266|>",
|
| 15 |
+
"<|_unuse_missing_100267|>",
|
| 16 |
+
"<|_unuse_missing_100268|>",
|
| 17 |
+
"<|_unuse_missing_100269|>",
|
| 18 |
+
"<|_unuse_missing_100270|>",
|
| 19 |
+
"<|_unuse_missing_100271|>",
|
| 20 |
+
"<|im_start|>",
|
| 21 |
+
"<|im_end|>",
|
| 22 |
+
"<|stop|>",
|
| 23 |
+
"<|endofturn|>",
|
| 24 |
+
"<repo_name>",
|
| 25 |
+
"<file_sep>",
|
| 26 |
+
"<issue_start>",
|
| 27 |
+
"<issue_comment>",
|
| 28 |
+
"<issue_closed>",
|
| 29 |
+
"<jupyter_start>",
|
| 30 |
+
"<jupyter_text>",
|
| 31 |
+
"<jupyter_code>",
|
| 32 |
+
"<jupyter_output>",
|
| 33 |
+
"<jupyter_script>",
|
| 34 |
+
"<empty_output>",
|
| 35 |
+
"<code_to_intermediate>",
|
| 36 |
+
"<intermediate_to_code>",
|
| 37 |
+
"<pr>",
|
| 38 |
+
"<pr_status>",
|
| 39 |
+
"<pr_is_merged>",
|
| 40 |
+
"<pr_base>",
|
| 41 |
+
"<pr_file>",
|
| 42 |
+
"<pr_base_code>",
|
| 43 |
+
"<pr_diff>",
|
| 44 |
+
"<pr_diff_hunk>",
|
| 45 |
+
"<pr_comment>",
|
| 46 |
+
"<pr_event_id>",
|
| 47 |
+
"<pr_review>",
|
| 48 |
+
"<pr_review_state>",
|
| 49 |
+
"<pr_review_comment>",
|
| 50 |
+
"<pr_in_reply_to_review_id>",
|
| 51 |
+
"<pr_in_reply_to_comment_id>",
|
| 52 |
+
"<pr_diff_hunk_comment_line>",
|
| 53 |
+
"<NAME>",
|
| 54 |
+
"<EMAIL>",
|
| 55 |
+
"<KEY>",
|
| 56 |
+
"<PASSWORD>"
|
| 57 |
+
],
|
| 58 |
+
"bos_token": {
|
| 59 |
+
"content": "<|endoftext|>",
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"normalized": false,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"single_word": false
|
| 64 |
+
},
|
| 65 |
+
"eos_token": {
|
| 66 |
+
"content": "<|endoftext|>",
|
| 67 |
+
"lstrip": false,
|
| 68 |
+
"normalized": false,
|
| 69 |
+
"rstrip": false,
|
| 70 |
+
"single_word": false
|
| 71 |
+
},
|
| 72 |
+
"pad_token": {
|
| 73 |
+
"content": "<|endoftext|>",
|
| 74 |
+
"lstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"rstrip": false,
|
| 77 |
+
"single_word": false
|
| 78 |
+
},
|
| 79 |
+
"unk_token": {
|
| 80 |
+
"content": "<|endoftext|>",
|
| 81 |
+
"lstrip": false,
|
| 82 |
+
"normalized": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"single_word": false
|
| 85 |
+
}
|
| 86 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|_unuse_missing_100256|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "<|_unuse_missing_100261|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "<|_unuse_missing_100262|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "<|_unuse_missing_100263|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|_unuse_missing_100264|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|_unuse_missing_100265|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|_unuse_missing_100266|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|_unuse_missing_100267|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|_unuse_missing_100268|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|_unuse_missing_100269|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|_unuse_missing_100270|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|_unuse_missing_100271|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|im_start|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|im_end|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|stop|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|endofturn|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"110491": {
|
| 173 |
+
"content": "<repo_name>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"110492": {
|
| 181 |
+
"content": "<file_sep>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"110493": {
|
| 189 |
+
"content": "<issue_start>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"110494": {
|
| 197 |
+
"content": "<issue_comment>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"110495": {
|
| 205 |
+
"content": "<issue_closed>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"110496": {
|
| 213 |
+
"content": "<jupyter_start>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"110497": {
|
| 221 |
+
"content": "<jupyter_text>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"110498": {
|
| 229 |
+
"content": "<jupyter_code>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"110499": {
|
| 237 |
+
"content": "<jupyter_output>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"110500": {
|
| 245 |
+
"content": "<jupyter_script>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"110501": {
|
| 253 |
+
"content": "<empty_output>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"110502": {
|
| 261 |
+
"content": "<code_to_intermediate>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"110503": {
|
| 269 |
+
"content": "<intermediate_to_code>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"110504": {
|
| 277 |
+
"content": "<pr>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"110505": {
|
| 285 |
+
"content": "<pr_status>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"110506": {
|
| 293 |
+
"content": "<pr_is_merged>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"110507": {
|
| 301 |
+
"content": "<pr_base>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"110508": {
|
| 309 |
+
"content": "<pr_file>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"110509": {
|
| 317 |
+
"content": "<pr_base_code>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"110510": {
|
| 325 |
+
"content": "<pr_diff>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"110511": {
|
| 333 |
+
"content": "<pr_diff_hunk>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"110512": {
|
| 341 |
+
"content": "<pr_comment>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"110513": {
|
| 349 |
+
"content": "<pr_event_id>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"110514": {
|
| 357 |
+
"content": "<pr_review>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"110515": {
|
| 365 |
+
"content": "<pr_review_state>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"110516": {
|
| 373 |
+
"content": "<pr_review_comment>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"110517": {
|
| 381 |
+
"content": "<pr_in_reply_to_review_id>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"110518": {
|
| 389 |
+
"content": "<pr_in_reply_to_comment_id>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"110519": {
|
| 397 |
+
"content": "<pr_diff_hunk_comment_line>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"110520": {
|
| 405 |
+
"content": "<NAME>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"110521": {
|
| 413 |
+
"content": "<EMAIL>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"110522": {
|
| 421 |
+
"content": "<KEY>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"110523": {
|
| 429 |
+
"content": "<PASSWORD>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
}
|
| 436 |
+
},
|
| 437 |
+
"additional_special_tokens": [
|
| 438 |
+
"<|endoftext|>",
|
| 439 |
+
"<|fim_prefix|>",
|
| 440 |
+
"<|fim_middle|>",
|
| 441 |
+
"<|fim_suffix|>",
|
| 442 |
+
"<|endofprompt|>",
|
| 443 |
+
"<|_unuse_missing_100256|>",
|
| 444 |
+
"<|_unuse_missing_100261|>",
|
| 445 |
+
"<|_unuse_missing_100262|>",
|
| 446 |
+
"<|_unuse_missing_100263|>",
|
| 447 |
+
"<|_unuse_missing_100264|>",
|
| 448 |
+
"<|_unuse_missing_100265|>",
|
| 449 |
+
"<|_unuse_missing_100266|>",
|
| 450 |
+
"<|_unuse_missing_100267|>",
|
| 451 |
+
"<|_unuse_missing_100268|>",
|
| 452 |
+
"<|_unuse_missing_100269|>",
|
| 453 |
+
"<|_unuse_missing_100270|>",
|
| 454 |
+
"<|_unuse_missing_100271|>",
|
| 455 |
+
"<|im_start|>",
|
| 456 |
+
"<|im_end|>",
|
| 457 |
+
"<|stop|>",
|
| 458 |
+
"<|endofturn|>",
|
| 459 |
+
"<repo_name>",
|
| 460 |
+
"<file_sep>",
|
| 461 |
+
"<issue_start>",
|
| 462 |
+
"<issue_comment>",
|
| 463 |
+
"<issue_closed>",
|
| 464 |
+
"<jupyter_start>",
|
| 465 |
+
"<jupyter_text>",
|
| 466 |
+
"<jupyter_code>",
|
| 467 |
+
"<jupyter_output>",
|
| 468 |
+
"<jupyter_script>",
|
| 469 |
+
"<empty_output>",
|
| 470 |
+
"<code_to_intermediate>",
|
| 471 |
+
"<intermediate_to_code>",
|
| 472 |
+
"<pr>",
|
| 473 |
+
"<pr_status>",
|
| 474 |
+
"<pr_is_merged>",
|
| 475 |
+
"<pr_base>",
|
| 476 |
+
"<pr_file>",
|
| 477 |
+
"<pr_base_code>",
|
| 478 |
+
"<pr_diff>",
|
| 479 |
+
"<pr_diff_hunk>",
|
| 480 |
+
"<pr_comment>",
|
| 481 |
+
"<pr_event_id>",
|
| 482 |
+
"<pr_review>",
|
| 483 |
+
"<pr_review_state>",
|
| 484 |
+
"<pr_review_comment>",
|
| 485 |
+
"<pr_in_reply_to_review_id>",
|
| 486 |
+
"<pr_in_reply_to_comment_id>",
|
| 487 |
+
"<pr_diff_hunk_comment_line>",
|
| 488 |
+
"<NAME>",
|
| 489 |
+
"<EMAIL>",
|
| 490 |
+
"<KEY>",
|
| 491 |
+
"<PASSWORD>"
|
| 492 |
+
],
|
| 493 |
+
"bos_token": "<|endoftext|>",
|
| 494 |
+
"clean_up_tokenization_spaces": true,
|
| 495 |
+
"eos_token": "<|endoftext|>",
|
| 496 |
+
"extra_special_tokens": {},
|
| 497 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 498 |
+
"pad_token": "<|endoftext|>",
|
| 499 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 500 |
+
"unk_token": "<|endoftext|>"
|
| 501 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|