Upload processor
Browse files- added_tokens.json +8 -0
- chat_template.json +1 -1
- preprocessor_config.json +4 -4
- tokenizer.json +2 -2
- tokenizer_config.json +74 -5
added_tokens.json
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"<|box_end|>": 151649,
|
| 3 |
"<|box_start|>": 151648,
|
| 4 |
"<|endoftext|>": 151643,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"<|im_end|>": 151645,
|
| 6 |
"<|im_start|>": 151644,
|
| 7 |
"<|image_pad|>": 151655,
|
|
@@ -9,6 +16,7 @@
|
|
| 9 |
"<|object_ref_start|>": 151646,
|
| 10 |
"<|quad_end|>": 151651,
|
| 11 |
"<|quad_start|>": 151650,
|
|
|
|
| 12 |
"<|video_pad|>": 151656,
|
| 13 |
"<|vision_end|>": 151653,
|
| 14 |
"<|vision_pad|>": 151654,
|
|
|
|
| 1 |
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
"<|box_end|>": 151649,
|
| 5 |
"<|box_start|>": 151648,
|
| 6 |
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
"<|im_end|>": 151645,
|
| 13 |
"<|im_start|>": 151644,
|
| 14 |
"<|image_pad|>": 151655,
|
|
|
|
| 16 |
"<|object_ref_start|>": 151646,
|
| 17 |
"<|quad_end|>": 151651,
|
| 18 |
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
"<|video_pad|>": 151656,
|
| 21 |
"<|vision_end|>": 151653,
|
| 22 |
"<|vision_pad|>": 151654,
|
chat_template.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"chat_template": "{
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"chat_template": "{%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'user' -%}\n {%- if loop.first and message['role'] != 'system' -%}\n {{- '<|im_start|>system\n' -}}\n {%- if template -%}\n {#--- If template, extraction task ---#}\n {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}}\n {%- else -%}\n {#--- Else, template generation task ---#}\n {{- 'You are a helpful assistant.' -}}\n {%- endif -%}\n {{ '<|im_end|>\n' }}\n {%- endif -%}\n {{- '<|im_start|>' + message['role'] + '\n' -}}\n {%- if template -%}\n {#--- Template Section ---#}\n {{- '# Template:\n' -}}\n {{- template -}}\n {{- '\n' -}}\n \n {%- if examples -%}\n {#--- Examples can only exist in the extraction task ---#}\n {{- '# Examples:\n' -}}\n {%- for example in examples -%}\n {{- '## Input:\n' -}}\n {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%}\n {{- image_placeholder | trim -}}\n {%- elif example['input'] == '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- Text input example ---#}\n {{- example['input'] -}}\n {%- endif -%}\n {{- '\n' -}}\n {{- '## Output:\n' -}}\n {{- example['output'] -}}\n {{- '\n' -}}\n {%- endfor -%}\n {%- endif -%}\n {{- '# Context:\n' -}}\n {%- endif -%}\n \n {%- if message['content'] is string -%}\n {#--- Simple string content ---#}\n message['content'] | trim -}}\n {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- List of content items (mixed text/images) ---#}\n {#--- First, determine what the actual input content is (not ICL images) ---#}\n {%- set ns = namespace(has_text_input=false, text_content='') -%}\n \n {#--- Count content types and identify actual input document ---#}\n {%- for content in message['content'] -%}\n {%- if content is mapping and content.get('type') == 'text' -%}\n {%- if content.get('text') != '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {%- set ns.has_text_input = true -%}\n {%- set ns.text_content = content['text'] -%}\n {%- endif -%}\n {%- elif content is string -%}\n {%- if content != '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {%- set ns.has_text_input = true -%}\n {%- set ns.text_content = content -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n \n {#--- Determine what to output based on actual input type ---#}\n {%- if ns.has_text_input -%}\n {#--- Main input is text, so output the text content ---#}\n {{- ns.text_content | trim -}}\n {%- else -%}\n {#--- Main input is image or <image> placeholder ---#}\n {%- set ns2 = namespace(found_image=false) -%}\n {%- for content in message['content'] -%}\n {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- elif content is string and content == '<image>' and not ns2.found_image -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {{- '<|im_end|>\n'}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- '<|im_start|>assistant\n' -}}\n{%- endif -%}"
|
| 3 |
}
|
preprocessor_config.json
CHANGED
|
@@ -14,16 +14,16 @@
|
|
| 14 |
0.26130258,
|
| 15 |
0.27577711
|
| 16 |
],
|
| 17 |
-
"max_pixels":
|
| 18 |
"merge_size": 2,
|
| 19 |
"min_pixels": 200704,
|
| 20 |
"patch_size": 14,
|
| 21 |
-
"processor_class": "
|
| 22 |
"resample": 3,
|
| 23 |
"rescale_factor": 0.00392156862745098,
|
| 24 |
"size": {
|
| 25 |
-
"longest_edge":
|
| 26 |
-
"shortest_edge":
|
| 27 |
},
|
| 28 |
"temporal_patch_size": 2
|
| 29 |
}
|
|
|
|
| 14 |
0.26130258,
|
| 15 |
0.27577711
|
| 16 |
],
|
| 17 |
+
"max_pixels": 23000000,
|
| 18 |
"merge_size": 2,
|
| 19 |
"min_pixels": 200704,
|
| 20 |
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
"resample": 3,
|
| 23 |
"rescale_factor": 0.00392156862745098,
|
| 24 |
"size": {
|
| 25 |
+
"longest_edge": 23000000,
|
| 26 |
+
"shortest_edge": 200704
|
| 27 |
},
|
| 28 |
"temporal_patch_size": 2
|
| 29 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
|
| 3 |
+
size 11422064
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"151643": {
|
|
@@ -112,6 +114,70 @@
|
|
| 112 |
"rstrip": false,
|
| 113 |
"single_word": false,
|
| 114 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
}
|
| 116 |
},
|
| 117 |
"additional_special_tokens": [
|
|
@@ -130,17 +196,20 @@
|
|
| 130 |
"<|video_pad|>"
|
| 131 |
],
|
| 132 |
"bos_token": null,
|
| 133 |
-
"chat_template": "{
|
| 134 |
"clean_up_tokenization_spaces": false,
|
| 135 |
"eos_token": "<|im_end|>",
|
| 136 |
"errors": "replace",
|
| 137 |
"extra_special_tokens": {},
|
| 138 |
-
"
|
|
|
|
| 139 |
"min_pixels": 200704,
|
| 140 |
-
"model_max_length":
|
|
|
|
| 141 |
"pad_token": "<|endoftext|>",
|
| 142 |
-
"
|
| 143 |
-
"
|
|
|
|
| 144 |
"split_special_tokens": false,
|
| 145 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 146 |
"unk_token": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"_commit_hash": null,
|
| 3 |
+
"add_bos_token": false,
|
| 4 |
"add_prefix_space": false,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"151643": {
|
|
|
|
| 114 |
"rstrip": false,
|
| 115 |
"single_word": false,
|
| 116 |
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
}
|
| 182 |
},
|
| 183 |
"additional_special_tokens": [
|
|
|
|
| 196 |
"<|video_pad|>"
|
| 197 |
],
|
| 198 |
"bos_token": null,
|
| 199 |
+
"chat_template": "{%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'user' -%}\n {%- if loop.first and message['role'] != 'system' -%}\n {{- '<|im_start|>system\n' -}}\n {%- if template -%}\n {#--- If template, extraction task ---#}\n {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}}\n {%- else -%}\n {#--- Else, template generation task ---#}\n {{- 'You are a helpful assistant.' -}}\n {%- endif -%}\n {{ '<|im_end|>\n' }}\n {%- endif -%}\n {{- '<|im_start|>' + message['role'] + '\n' -}}\n {%- if template -%}\n {#--- Template Section ---#}\n {{- '# Template:\n' -}}\n {{- template -}}\n {{- '\n' -}}\n \n {%- if examples -%}\n {#--- Examples can only exist in the extraction task ---#}\n {{- '# Examples:\n' -}}\n {%- for example in examples -%}\n {{- '## Input:\n' -}}\n {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%}\n {{- image_placeholder | trim -}}\n {%- elif example['input'] == '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- Text input example ---#}\n {{- example['input'] -}}\n {%- endif -%}\n {{- '\n' -}}\n {{- '## Output:\n' -}}\n {{- example['output'] -}}\n {{- '\n' -}}\n {%- endfor -%}\n {%- endif -%}\n {{- '# Context:\n' -}}\n {%- endif -%}\n \n {%- if message['content'] is string -%}\n {#--- Simple string content ---#}\n message['content'] | trim -}}\n {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- List of content items (mixed text/images) ---#}\n {#--- First, determine what the actual input content is (not ICL images) ---#}\n {%- set ns = namespace(has_text_input=false, text_content='') -%}\n \n {#--- Count content types and identify actual input document ---#}\n {%- for content in message['content'] -%}\n {%- if content is mapping and content.get('type') == 'text' -%}\n {%- if content.get('text') != '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {%- set ns.has_text_input = true -%}\n {%- set ns.text_content = content['text'] -%}\n {%- endif -%}\n {%- elif content is string -%}\n {%- if content != '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {%- set ns.has_text_input = true -%}\n {%- set ns.text_content = content -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n \n {#--- Determine what to output based on actual input type ---#}\n {%- if ns.has_text_input -%}\n {#--- Main input is text, so output the text content ---#}\n {{- ns.text_content | trim -}}\n {%- else -%}\n {#--- Main input is image or <image> placeholder ---#}\n {%- set ns2 = namespace(found_image=false) -%}\n {%- for content in message['content'] -%}\n {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- elif content is string and content == '<image>' and not ns2.found_image -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {{- '<|im_end|>\n'}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- '<|im_start|>assistant\n' -}}\n{%- endif -%}",
|
| 200 |
"clean_up_tokenization_spaces": false,
|
| 201 |
"eos_token": "<|im_end|>",
|
| 202 |
"errors": "replace",
|
| 203 |
"extra_special_tokens": {},
|
| 204 |
+
"max_length": null,
|
| 205 |
+
"max_pixels": 23000000,
|
| 206 |
"min_pixels": 200704,
|
| 207 |
+
"model_max_length": 131072,
|
| 208 |
+
"pad_to_multiple_of": null,
|
| 209 |
"pad_token": "<|endoftext|>",
|
| 210 |
+
"pad_token_type_id": 0,
|
| 211 |
+
"padding_side": "right",
|
| 212 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 213 |
"split_special_tokens": false,
|
| 214 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 215 |
"unk_token": null
|