mjschock commited on
Commit
84ed4f8
1 Parent(s): a49a98c

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": "<s>",
26
+ "eos_token": "</s>",
27
+ "pad_token": "</s>",
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<s>",
33
+ "</s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "chat_template": "{%- set system_message_present = messages | selectattr('role', 'equalto', 'system') | list -%}{%- if not system_message_present -%}{%- set messages = [{ \"content\": \"You are an AI agent acting as a human assistant.\", \"role\": \"system\" }] + messages -%}{%- endif -%}{%- for message in messages -%}<|{{ message.role }}|>{{ '\n' }}{%- if message.role == 'system' -%}{{ message.content }}{%- if tools and tools | length > 0 -%}{{ '\n\n' }}You are aware of the following tools in your environment:{{ '\n' }}{\n \"tools\": [{{ '\n' }}{%- for tool in tools -%}{{ ' ' }}{\n \"function\": {\n \"description\": \"{{ tool.function.description }}\",{{ '\n' }} \"name\": \"{{ tool.function.name }}\",{{ '\n' }} \"parameters\": {{ tool.function.parameters | tojson }}{{ '\n' }} },{{ '\n' }} \"type\": \"{{ tool.type }}\"{{ '\n' }} }{%- if not loop.last -%},{%- endif -%}{{ '\n' }}{%- endfor -%}{{ ' ' }}]{{ '\n' }}}{{ '\n\n' }}If you would like to suggest one or more tool calls, please respond in the following format:{{ '\n' }}{\n \"finish_reason\": \"tool_calls\",{{ '\n' }} \"tool_calls\": [{{ '\n' }}{{ ' ' }}{\n \"arguments\": \"{\\\"parameter_name\\\": \\\"parameter_value\\\"}\",{{ '\n' }} \"id\": \"call_id\",{{ '\n' }} \"name\": \"tool_name\"{{ '\n' }} }{{ '\n' }} ]{{ '\n' }}}{%- endif -%}{{ eos_token }}{{ '\n' }}{%- endif -%}{%- if message.role == 'user' -%}{{ message.content }}{{ eos_token }}{{ '\n' }}{%- endif -%}{%- if message.role == 'assistant' -%}{% generation %}{%- if message.tool_calls and message.tool_calls | length > 0 -%}{\n \"finish_reason\": \"tool_calls\",{{ '\n' }} \"tool_calls\": [{{ '\n' }}{%- for tool_call in message.tool_calls -%}{{ ' ' }}{\n \"arguments\": {{ tool_call.function.arguments | tojson }},{{ '\n' }} \"id\": \"{{ tool_call.id }}\",{{ '\n' }} \"name\": \"{{ tool_call.function.name }}\"{{ '\n' }} }{%- if not loop.last -%},{%- endif -%}{{ '\n' }}{%- endfor -%}{{ ' ' }}]{{ '\n' }}}{%- else -%}{{ message.content }}{%- endif -%}{% endgeneration %}{{ eos_token }}{{ '\n' }}{%- endif -%}{%- if message.role == 'tool' -%}{\n \"content\": {{ message.content | tojson }},{{ '\n' }} \"name\": \"{{ message.name }}\",{{ '\n' }} \"tool_call_id\": \"{{ message.tool_call_id }}\"{{ '\n' }}}{{ eos_token }}{{ '\n' }}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{ '<|assistant|>\n' }}{%- endif -%}",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "legacy": false,
41
+ "model_max_length": 2048,
42
+ "pad_token": "</s>",
43
+ "padding_side": "right",
44
+ "sp_model_kwargs": {},
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": false
48
+ }