MISHANM commited on
Commit
fd46698
·
verified ·
1 Parent(s): 883766b

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 49155,
3
+ "<|end_of_role|>": 49153,
4
+ "<|start_of_role|>": 49152,
5
+ "<|tool_call|>": 49154
6
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{%- if tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>\n' }}\n {%- for tool in tools %}\n {{- tool | tojson(indent=4) }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- endif %}\n {%- endfor %}\n {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in messages if message['role'] == 'system'%}{% else %}<|system|>\nA chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n{% endfor %}{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {{- '<|system|>\n' + message['content'][0]['text'] + '\n' }}\n {%- elif message['role'] == 'user' %}<|user|>\n {# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + '\n' }}{% endfor %}\n{%- elif message['role'] == 'assistant' %}\n {{- '<|assistant|>\n' + message['content'][0]['text'] + '<|end_of_text|>' }}\n {%- elif message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'][0]['text'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'tool_response' %}\n {{- '<|start_of_role|>tool_response<|end_of_role|>' + message['content'][0]['text'] + '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|assistant|>\n' }}\n {%- endif %}\n{%- endfor %}"
3
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 384,
4
+ "width": 384
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": null,
8
+ "do_normalize": true,
9
+ "do_pad": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_grid_pinpoints": [
13
+ [
14
+ 384,
15
+ 384
16
+ ],
17
+ [
18
+ 384,
19
+ 768
20
+ ],
21
+ [
22
+ 384,
23
+ 1152
24
+ ],
25
+ [
26
+ 384,
27
+ 1536
28
+ ],
29
+ [
30
+ 384,
31
+ 1920
32
+ ],
33
+ [
34
+ 384,
35
+ 2304
36
+ ],
37
+ [
38
+ 384,
39
+ 2688
40
+ ],
41
+ [
42
+ 384,
43
+ 3072
44
+ ],
45
+ [
46
+ 384,
47
+ 3456
48
+ ],
49
+ [
50
+ 384,
51
+ 3840
52
+ ],
53
+ [
54
+ 768,
55
+ 384
56
+ ],
57
+ [
58
+ 768,
59
+ 768
60
+ ],
61
+ [
62
+ 768,
63
+ 1152
64
+ ],
65
+ [
66
+ 768,
67
+ 1536
68
+ ],
69
+ [
70
+ 768,
71
+ 1920
72
+ ],
73
+ [
74
+ 1152,
75
+ 384
76
+ ],
77
+ [
78
+ 1152,
79
+ 768
80
+ ],
81
+ [
82
+ 1152,
83
+ 1152
84
+ ],
85
+ [
86
+ 1536,
87
+ 384
88
+ ],
89
+ [
90
+ 1536,
91
+ 768
92
+ ],
93
+ [
94
+ 1920,
95
+ 384
96
+ ],
97
+ [
98
+ 1920,
99
+ 768
100
+ ],
101
+ [
102
+ 2304,
103
+ 384
104
+ ],
105
+ [
106
+ 2688,
107
+ 384
108
+ ],
109
+ [
110
+ 3072,
111
+ 384
112
+ ],
113
+ [
114
+ 3456,
115
+ 384
116
+ ],
117
+ [
118
+ 3840,
119
+ 384
120
+ ]
121
+ ],
122
+ "image_mean": [
123
+ 0.5,
124
+ 0.5,
125
+ 0.5
126
+ ],
127
+ "image_processor_type": "LlavaNextImageProcessor",
128
+ "image_std": [
129
+ 0.5,
130
+ 0.5,
131
+ 0.5
132
+ ],
133
+ "processor_class": "LlavaNextProcessor",
134
+ "resample": 3,
135
+ "rescale_factor": 0.00392156862745098,
136
+ "size": {
137
+ "height": 384,
138
+ "width": 384
139
+ }
140
+ }
processor_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "patch_size": 14,
4
+ "processor_class": "LlavaNextProcessor",
5
+ "vision_feature_select_strategy": "full"
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|start_of_role|>",
4
+ "<|end_of_role|>",
5
+ "<|tool_call|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|end_of_text|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|end_of_text|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<|end_of_text|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<|end_of_text|>",
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_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|end_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<fim_prefix>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<fim_middle>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<fim_suffix>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<fim_pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<filename>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<gh_stars>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<issue_start>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<issue_comment>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<issue_closed>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<jupyter_start>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<jupyter_text>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<jupyter_code>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<jupyter_output>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<empty_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<commit_before>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<commit_msg>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<commit_after>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<reponame>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "49152": {
158
+ "content": "<|start_of_role|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "49153": {
166
+ "content": "<|end_of_role|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "49154": {
174
+ "content": "<|tool_call|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "49155": {
182
+ "content": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|start_of_role|>",
192
+ "<|end_of_role|>",
193
+ "<|tool_call|>"
194
+ ],
195
+ "bos_token": "<|end_of_text|>",
196
+ "chat_template": "{%- if tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>\n' }}\n {%- for tool in tools %}\n {{- tool | tojson(indent=4) }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- endif %}\n {%- endfor %}\n {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in messages if message['role'] == 'system'%}{% else %}<|system|>\nA chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n{% endfor %}{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {{- '<|system|>\n' + message['content'] + '\n' }}\n {%- elif message['role'] == 'user' %}\n {{- '<|user|>\n' + message['content'] + '\n' }}\n {%- elif message['role'] == 'assistant' %}\n {{- '<|assistant|>\n' + message['content'] + '<|end_of_text|>' }}\n {%- elif message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'tool_response' %}\n {{- '<|start_of_role|>tool_response<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|assistant|>\n' }}\n {%- endif %}\n{%- endfor %}",
197
+ "clean_up_tokenization_spaces": true,
198
+ "eos_token": "<|end_of_text|>",
199
+ "errors": "replace",
200
+ "model_max_length": 16384,
201
+ "pad_token": "<|end_of_text|>",
202
+ "padding_side": "right",
203
+ "processor_class": "LlavaNextProcessor",
204
+ "tokenizer_class": "GPT2Tokenizer",
205
+ "unk_token": "<|end_of_text|>",
206
+ "vocab_size": 49152
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff