mcesbrondarnaud commited on
Commit
d6f692f
·
verified ·
1 Parent(s): a587e14

Upload tokenizer

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +31 -0
  3. tokenizer.json +3 -0
  4. tokenizer_config.json +30 -0
.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
chat_template.jinja ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ {%- set enable_thinking = true %}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {%- set system_message = messages[0]['content'] %}
5
+ {%- set messages = messages[1:] %}
6
+ {%- else %}
7
+ {%- set system_message = 'You are a helpful assistant . Reason carefully. The final answer should always be strictly inside \\boxed{}. For MCQ the answer should be 1 letter.Always output final answer in \\boxed{} no matter the question. Strictly respect this condition.' %}
8
+ {%- endif %}
9
+ {%- for message in messages %}
10
+ {%- if message['role'] == 'user' %}
11
+ {%- if loop.first and system_message %}
12
+ {{- "<|im_start|>system\n" + system_message + "<|im_end|>\n" }}
13
+ {%- endif %}
14
+ {{- "<|im_start|>user\n" + message['content'] + "<|im_end|>\n" }}
15
+ {%- elif message['role'] == 'assistant' %}
16
+ {{- "<|im_start|>assistant\n" }}
17
+ {%- if enable_thinking %}
18
+ {%- if message.get('think') %}
19
+ {{- "<think>\n" + message['think'] + "\n</think>\n" }}
20
+ {%- else %}
21
+ {{- "<think>\n" }}
22
+ {%- endif %}
23
+ {%- endif %}
24
+ {{- message['content'] + "<|im_end|>\n" }}
25
+ {%- endif %}
26
+ {%- endfor %}
27
+ {%- if enable_thinking %}
28
+ {{- "<|im_start|>assistant\n<think>\n" }}
29
+ {%- else %}
30
+ {{- "<|im_start|>assistant\n" }}
31
+ {%- endif %}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": true,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }