danielhanchen commited on
Commit
71517f0
·
verified ·
1 Parent(s): c62b27a

Add files using upload-large-folder tool

Browse files
Files changed (3) hide show
  1. config.json +2 -1
  2. special_tokens_map.json +1 -7
  3. tokenizer_config.json +1 -1
config.json CHANGED
@@ -5,7 +5,7 @@
5
  "boi_token_index": 255999,
6
  "bos_token_id": 2,
7
  "eoi_token_index": 256000,
8
- "eos_token_id": 1,
9
  "image_token_index": 262144,
10
  "initializer_range": 0.02,
11
  "mm_tokens_per_image": 256,
@@ -16,6 +16,7 @@
16
  "attention_dropout": 0.0,
17
  "attn_logit_softcapping": null,
18
  "cache_implementation": "hybrid",
 
19
  "final_logit_softcapping": null,
20
  "head_dim": 256,
21
  "hidden_activation": "gelu_pytorch_tanh",
 
5
  "boi_token_index": 255999,
6
  "bos_token_id": 2,
7
  "eoi_token_index": 256000,
8
+ "eos_token_id": 106,
9
  "image_token_index": 262144,
10
  "initializer_range": 0.02,
11
  "mm_tokens_per_image": 256,
 
16
  "attention_dropout": 0.0,
17
  "attn_logit_softcapping": null,
18
  "cache_implementation": "hybrid",
19
+ "eos_token_id": 106,
20
  "final_logit_softcapping": null,
21
  "head_dim": 256,
22
  "hidden_activation": "gelu_pytorch_tanh",
special_tokens_map.json CHANGED
@@ -8,13 +8,7 @@
8
  "single_word": false
9
  },
10
  "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
  "image_token": "<image_soft_token>",
19
  "pad_token": {
20
  "content": "<pad>",
 
8
  "single_word": false
9
  },
10
  "eoi_token": "<end_of_image>",
11
+ "eos_token": "<end_of_turn>",
 
 
 
 
 
 
12
  "image_token": "<image_soft_token>",
13
  "pad_token": {
14
  "content": "<pad>",
tokenizer_config.json CHANGED
@@ -51328,7 +51328,7 @@
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",
51329
  "clean_up_tokenization_spaces": false,
51330
  "eoi_token": "<end_of_image>",
51331
- "eos_token": "<eos>",
51332
  "extra_special_tokens": {
51333
  "boi_token": "<start_of_image>",
51334
  "eoi_token": "<end_of_image>",
 
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",
51329
  "clean_up_tokenization_spaces": false,
51330
  "eoi_token": "<end_of_image>",
51331
+ "eos_token": "<end_of_turn>",
51332
  "extra_special_tokens": {
51333
  "boi_token": "<start_of_image>",
51334
  "eoi_token": "<end_of_image>",