MaziyarPanahi
commited on
Commit
•
448c512
1
Parent(s):
6004bf6
Delete .ipynb_checkpoints (#2)
Browse files- Delete .ipynb_checkpoints (c53ba6604642d7ba88718261f89330c2f734389d)
.ipynb_checkpoints/tokenizer_config-checkpoint.json
DELETED
@@ -1,155 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": false,
|
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": true,
|
27 |
-
"single_word": false,
|
28 |
-
"special": false
|
29 |
-
},
|
30 |
-
"32000": {
|
31 |
-
"content": "<|endoftext|>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
-
},
|
38 |
-
"32001": {
|
39 |
-
"content": "<|assistant|>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": true,
|
43 |
-
"single_word": false,
|
44 |
-
"special": true
|
45 |
-
},
|
46 |
-
"32002": {
|
47 |
-
"content": "<|placeholder1|>",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": false,
|
50 |
-
"rstrip": true,
|
51 |
-
"single_word": false,
|
52 |
-
"special": true
|
53 |
-
},
|
54 |
-
"32003": {
|
55 |
-
"content": "<|placeholder2|>",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"rstrip": true,
|
59 |
-
"single_word": false,
|
60 |
-
"special": true
|
61 |
-
},
|
62 |
-
"32004": {
|
63 |
-
"content": "<|placeholder3|>",
|
64 |
-
"lstrip": false,
|
65 |
-
"normalized": false,
|
66 |
-
"rstrip": true,
|
67 |
-
"single_word": false,
|
68 |
-
"special": true
|
69 |
-
},
|
70 |
-
"32005": {
|
71 |
-
"content": "<|placeholder4|>",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": false,
|
74 |
-
"rstrip": true,
|
75 |
-
"single_word": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
"32006": {
|
79 |
-
"content": "<|system|>",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": false,
|
82 |
-
"rstrip": true,
|
83 |
-
"single_word": false,
|
84 |
-
"special": true
|
85 |
-
},
|
86 |
-
"32007": {
|
87 |
-
"content": "<|end|>",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": false,
|
90 |
-
"rstrip": true,
|
91 |
-
"single_word": false,
|
92 |
-
"special": true
|
93 |
-
},
|
94 |
-
"32008": {
|
95 |
-
"content": "<|placeholder5|>",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": true,
|
99 |
-
"single_word": false,
|
100 |
-
"special": true
|
101 |
-
},
|
102 |
-
"32009": {
|
103 |
-
"content": "<|placeholder6|>",
|
104 |
-
"lstrip": false,
|
105 |
-
"normalized": false,
|
106 |
-
"rstrip": true,
|
107 |
-
"single_word": false,
|
108 |
-
"special": true
|
109 |
-
},
|
110 |
-
"32010": {
|
111 |
-
"content": "<|user|>",
|
112 |
-
"lstrip": false,
|
113 |
-
"normalized": false,
|
114 |
-
"rstrip": true,
|
115 |
-
"single_word": false,
|
116 |
-
"special": true
|
117 |
-
},
|
118 |
-
"32011": {
|
119 |
-
"content": "<|im_end|>",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": false,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false,
|
124 |
-
"special": false
|
125 |
-
},
|
126 |
-
"32012": {
|
127 |
-
"content": "<|end_of_text|>",
|
128 |
-
"lstrip": false,
|
129 |
-
"normalized": false,
|
130 |
-
"rstrip": false,
|
131 |
-
"single_word": false,
|
132 |
-
"special": true
|
133 |
-
},
|
134 |
-
"32013": {
|
135 |
-
"content": "<|im_start|>",
|
136 |
-
"lstrip": false,
|
137 |
-
"normalized": false,
|
138 |
-
"rstrip": false,
|
139 |
-
"single_word": false,
|
140 |
-
"special": false
|
141 |
-
}
|
142 |
-
},
|
143 |
-
"bos_token": "<s>",
|
144 |
-
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
145 |
-
"clean_up_tokenization_spaces": false,
|
146 |
-
"eos_token": "<|endoftext|>",
|
147 |
-
"legacy": false,
|
148 |
-
"model_max_length": 131072,
|
149 |
-
"pad_token": "<|end_of_text|>",
|
150 |
-
"padding_side": "left",
|
151 |
-
"sp_model_kwargs": {},
|
152 |
-
"tokenizer_class": "LlamaTokenizer",
|
153 |
-
"unk_token": "<unk>",
|
154 |
-
"use_default_system_prompt": false
|
155 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|