venkycs commited on
Commit
31bb118
·
verified ·
1 Parent(s): 3140996

Upload 3 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json CHANGED
@@ -1,4 +1,76 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<|begin_of_text|>",
4
  "lstrip": false,
@@ -12,5 +84,12 @@
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
 
 
 
 
 
 
 
15
  }
16
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<Impersonate>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</Impersonate>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<Knowledge>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</Knowledge>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<Intent>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</Intent>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<Reasoning>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</Reasoning>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<AvoidMistakes>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</AvoidMistakes>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ }
73
+ ],
74
  "bos_token": {
75
  "content": "<|begin_of_text|>",
76
  "lstrip": false,
 
84
  "normalized": false,
85
  "rstrip": false,
86
  "single_word": false
87
+ },
88
+ "pad_token": {
89
+ "content": "<|finetune_right_pad_id|>",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
  }
95
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "128000": {
4
  "content": "<|begin_of_text|>",
@@ -2047,16 +2048,112 @@
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2050
  }
2051
  },
 
 
 
 
 
 
 
 
 
 
 
 
2052
  "bos_token": "<|begin_of_text|>",
2053
  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
 
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
2062
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "added_tokens_decoder": {
4
  "128000": {
5
  "content": "<|begin_of_text|>",
 
2048
  "rstrip": false,
2049
  "single_word": false,
2050
  "special": true
2051
+ },
2052
+ "128256": {
2053
+ "content": "<Impersonate>",
2054
+ "lstrip": false,
2055
+ "normalized": false,
2056
+ "rstrip": false,
2057
+ "single_word": false,
2058
+ "special": true
2059
+ },
2060
+ "128257": {
2061
+ "content": "</Impersonate>",
2062
+ "lstrip": false,
2063
+ "normalized": false,
2064
+ "rstrip": false,
2065
+ "single_word": false,
2066
+ "special": true
2067
+ },
2068
+ "128258": {
2069
+ "content": "<Knowledge>",
2070
+ "lstrip": false,
2071
+ "normalized": false,
2072
+ "rstrip": false,
2073
+ "single_word": false,
2074
+ "special": true
2075
+ },
2076
+ "128259": {
2077
+ "content": "</Knowledge>",
2078
+ "lstrip": false,
2079
+ "normalized": false,
2080
+ "rstrip": false,
2081
+ "single_word": false,
2082
+ "special": true
2083
+ },
2084
+ "128260": {
2085
+ "content": "<Intent>",
2086
+ "lstrip": false,
2087
+ "normalized": false,
2088
+ "rstrip": false,
2089
+ "single_word": false,
2090
+ "special": true
2091
+ },
2092
+ "128261": {
2093
+ "content": "</Intent>",
2094
+ "lstrip": false,
2095
+ "normalized": false,
2096
+ "rstrip": false,
2097
+ "single_word": false,
2098
+ "special": true
2099
+ },
2100
+ "128262": {
2101
+ "content": "<Reasoning>",
2102
+ "lstrip": false,
2103
+ "normalized": false,
2104
+ "rstrip": false,
2105
+ "single_word": false,
2106
+ "special": true
2107
+ },
2108
+ "128263": {
2109
+ "content": "</Reasoning>",
2110
+ "lstrip": false,
2111
+ "normalized": false,
2112
+ "rstrip": false,
2113
+ "single_word": false,
2114
+ "special": true
2115
+ },
2116
+ "128264": {
2117
+ "content": "<AvoidMistakes>",
2118
+ "lstrip": false,
2119
+ "normalized": false,
2120
+ "rstrip": false,
2121
+ "single_word": false,
2122
+ "special": true
2123
+ },
2124
+ "128265": {
2125
+ "content": "</AvoidMistakes>",
2126
+ "lstrip": false,
2127
+ "normalized": false,
2128
+ "rstrip": false,
2129
+ "single_word": false,
2130
+ "special": true
2131
  }
2132
  },
2133
+ "additional_special_tokens": [
2134
+ "<Impersonate>",
2135
+ "</Impersonate>",
2136
+ "<Knowledge>",
2137
+ "</Knowledge>",
2138
+ "<Intent>",
2139
+ "</Intent>",
2140
+ "<Reasoning>",
2141
+ "</Reasoning>",
2142
+ "<AvoidMistakes>",
2143
+ "</AvoidMistakes>"
2144
+ ],
2145
  "bos_token": "<|begin_of_text|>",
2146
  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2147
  "clean_up_tokenization_spaces": true,
2148
  "eos_token": "<|eot_id|>",
2149
+ "extra_special_tokens": {},
2150
  "model_input_names": [
2151
  "input_ids",
2152
  "attention_mask"
2153
  ],
2154
  "model_max_length": 131072,
2155
+ "pad_token": "<|finetune_right_pad_id|>",
2156
+ "padding_side": "left",
2157
+ "tokenizer_class": "PreTrainedTokenizerFast",
2158
+ "unk_token": null
2159
  }