Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -1
- config.json +1 -1
- model.safetensors +2 -2
- special_tokens_map.json +30 -0
- tokenizer.json +2 -2
- tokenizer_config.json +38 -0
added_tokens.json
CHANGED
|
@@ -1,3 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</answer>": 262148,
|
| 3 |
+
"</reasoning>": 262146,
|
| 4 |
+
"<answer>": 262147,
|
| 5 |
+
"<image_soft_token>": 262144,
|
| 6 |
+
"<reasoning>": 262145
|
| 7 |
}
|
config.json
CHANGED
|
@@ -33,5 +33,5 @@
|
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.51.3",
|
| 35 |
"use_cache": true,
|
| 36 |
-
"vocab_size":
|
| 37 |
}
|
|
|
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.51.3",
|
| 35 |
"use_cache": true,
|
| 36 |
+
"vocab_size": 262149
|
| 37 |
}
|
model.safetensors
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 sha256:253077441ee00e8315d25622b538c3ef8bba348409a8f747dad44c9f348d1a49
|
| 3 |
+
size 1999822728
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,34 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"boi_token": "<start_of_image>",
|
| 3 |
"bos_token": {
|
| 4 |
"content": "<bos>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<reasoning>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "</reasoning>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<answer>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "</answer>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
"boi_token": "<start_of_image>",
|
| 33 |
"bos_token": {
|
| 34 |
"content": "<bos>",
|
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:cb2ef554759b05a06389bee9dba4d467f89ec19caf91fa531094b1d0956f8a52
|
| 3 |
+
size 33385316
|
tokenizer_config.json
CHANGED
|
@@ -51321,8 +51321,46 @@
|
|
| 51321 |
"rstrip": false,
|
| 51322 |
"single_word": false,
|
| 51323 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51324 |
}
|
| 51325 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51326 |
"boi_token": "<start_of_image>",
|
| 51327 |
"bos_token": "<bos>",
|
| 51328 |
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
|
|
|
|
| 51321 |
"rstrip": false,
|
| 51322 |
"single_word": false,
|
| 51323 |
"special": true
|
| 51324 |
+
},
|
| 51325 |
+
"262145": {
|
| 51326 |
+
"content": "<reasoning>",
|
| 51327 |
+
"lstrip": false,
|
| 51328 |
+
"normalized": false,
|
| 51329 |
+
"rstrip": false,
|
| 51330 |
+
"single_word": false,
|
| 51331 |
+
"special": true
|
| 51332 |
+
},
|
| 51333 |
+
"262146": {
|
| 51334 |
+
"content": "</reasoning>",
|
| 51335 |
+
"lstrip": false,
|
| 51336 |
+
"normalized": false,
|
| 51337 |
+
"rstrip": false,
|
| 51338 |
+
"single_word": false,
|
| 51339 |
+
"special": true
|
| 51340 |
+
},
|
| 51341 |
+
"262147": {
|
| 51342 |
+
"content": "<answer>",
|
| 51343 |
+
"lstrip": false,
|
| 51344 |
+
"normalized": false,
|
| 51345 |
+
"rstrip": false,
|
| 51346 |
+
"single_word": false,
|
| 51347 |
+
"special": true
|
| 51348 |
+
},
|
| 51349 |
+
"262148": {
|
| 51350 |
+
"content": "</answer>",
|
| 51351 |
+
"lstrip": false,
|
| 51352 |
+
"normalized": false,
|
| 51353 |
+
"rstrip": false,
|
| 51354 |
+
"single_word": false,
|
| 51355 |
+
"special": true
|
| 51356 |
}
|
| 51357 |
},
|
| 51358 |
+
"additional_special_tokens": [
|
| 51359 |
+
"<reasoning>",
|
| 51360 |
+
"</reasoning>",
|
| 51361 |
+
"<answer>",
|
| 51362 |
+
"</answer>"
|
| 51363 |
+
],
|
| 51364 |
"boi_token": "<start_of_image>",
|
| 51365 |
"bos_token": "<bos>",
|
| 51366 |
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
|