dp1812 commited on
Commit
d4e8bf2
·
verified ·
1 Parent(s): 78eca56

CELESTIAL tokenizer with special tokens

Browse files
added_tokens.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<DEVOTION>": 32775,
3
+ "<DHARMA>": 32773,
4
+ "<DIRECTION>": 32776,
5
+ "<ELEMENT>": 32777,
6
+ "<ENERGY>": 32778,
7
+ "<GEMSTONE>": 32784,
8
+ "<HOUSE>": 32770,
9
+ "<KARANA>": 32782,
10
+ "<KARMA>": 32774,
11
+ "<KRISHNA>": 32772,
12
+ "<KUNDLI>": 32768,
13
+ "<MANTRA>": 32785,
14
+ "<NAKSHATRA>": 32771,
15
+ "<PLACEMENT>": 32779,
16
+ "<PLANET>": 32769,
17
+ "<REMEDY>": 32783,
18
+ "<RITUAL>": 32786,
19
+ "<TITHI>": 32780,
20
+ "<YOGA>": 32781
21
+ }
chat_template.jinja ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]["role"] == "system" %}
2
+ {%- set system_message = messages[0]["content"] %}
3
+ {%- set loop_messages = messages[1:] %}
4
+ {%- else %}
5
+ {%- set loop_messages = messages %}
6
+ {%- endif %}
7
+ {%- if not tools is defined %}
8
+ {%- set tools = none %}
9
+ {%- endif %}
10
+ {%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
11
+
12
+ {#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
13
+ {%- set ns = namespace() %}
14
+ {%- set ns.index = 0 %}
15
+ {%- for message in loop_messages %}
16
+ {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
17
+ {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
18
+ {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
19
+ {%- endif %}
20
+ {%- set ns.index = ns.index + 1 %}
21
+ {%- endif %}
22
+ {%- endfor %}
23
+
24
+ {{- bos_token }}
25
+ {%- for message in loop_messages %}
26
+ {%- if message["role"] == "user" %}
27
+ {%- if tools is not none and (message == user_messages[-1]) %}
28
+ {{- "[AVAILABLE_TOOLS] [" }}
29
+ {%- for tool in tools %}
30
+ {%- set tool = tool.function %}
31
+ {{- '{"type": "function", "function": {' }}
32
+ {%- for key, val in tool.items() if key != "return" %}
33
+ {%- if val is string %}
34
+ {{- '"' + key + '": "' + val + '"' }}
35
+ {%- else %}
36
+ {{- '"' + key + '": ' + val|tojson }}
37
+ {%- endif %}
38
+ {%- if not loop.last %}
39
+ {{- ", " }}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {{- "}}" }}
43
+ {%- if not loop.last %}
44
+ {{- ", " }}
45
+ {%- else %}
46
+ {{- "]" }}
47
+ {%- endif %}
48
+ {%- endfor %}
49
+ {{- "[/AVAILABLE_TOOLS]" }}
50
+ {%- endif %}
51
+ {%- if loop.last and system_message is defined %}
52
+ {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
53
+ {%- else %}
54
+ {{- "[INST] " + message["content"] + "[/INST]" }}
55
+ {%- endif %}
56
+ {%- elif message.tool_calls is defined and message.tool_calls is not none %}
57
+ {{- "[TOOL_CALLS] [" }}
58
+ {%- for tool_call in message.tool_calls %}
59
+ {%- set out = tool_call.function|tojson %}
60
+ {{- out[:-1] }}
61
+ {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
62
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
63
+ {%- endif %}
64
+ {{- ', "id": "' + tool_call.id + '"}' }}
65
+ {%- if not loop.last %}
66
+ {{- ", " }}
67
+ {%- else %}
68
+ {{- "]" + eos_token }}
69
+ {%- endif %}
70
+ {%- endfor %}
71
+ {%- elif message["role"] == "assistant" %}
72
+ {{- " " + message["content"]|trim + eos_token}}
73
+ {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
74
+ {%- if message.content is defined and message.content.content is defined %}
75
+ {%- set content = message.content.content %}
76
+ {%- else %}
77
+ {%- set content = message.content %}
78
+ {%- endif %}
79
+ {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
80
+ {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
81
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
82
+ {%- endif %}
83
+ {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
84
+ {%- else %}
85
+ {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
86
+ {%- endif %}
87
+ {%- endfor %}
special_tokens_map.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<KUNDLI>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<PLANET>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<HOUSE>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<NAKSHATRA>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<KRISHNA>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<DHARMA>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<KARMA>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<DEVOTION>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<DIRECTION>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<ELEMENT>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<ENERGY>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<PLACEMENT>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<TITHI>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<YOGA>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<KARANA>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<REMEDY>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<GEMSTONE>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<MANTRA>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<RITUAL>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ }
136
+ ],
137
+ "bos_token": {
138
+ "content": "<s>",
139
+ "lstrip": false,
140
+ "normalized": false,
141
+ "rstrip": false,
142
+ "single_word": false
143
+ },
144
+ "eos_token": {
145
+ "content": "</s>",
146
+ "lstrip": false,
147
+ "normalized": false,
148
+ "rstrip": false,
149
+ "single_word": false
150
+ },
151
+ "pad_token": "</s>",
152
+ "unk_token": {
153
+ "content": "<unk>",
154
+ "lstrip": false,
155
+ "normalized": false,
156
+ "rstrip": false,
157
+ "single_word": false
158
+ }
159
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff