danielhanchen commited on
Commit
bb46578
·
verified ·
1 Parent(s): a5a2a23

Add files using upload-large-folder tool

Browse files
config.json CHANGED
@@ -7,7 +7,7 @@
7
  "attn_logit_softcapping": null,
8
  "bos_token_id": 2,
9
  "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
  "final_logit_softcapping": null,
12
  "head_dim": 256,
13
  "hidden_activation": "gelu_pytorch_tanh",
@@ -29,6 +29,7 @@
29
  "sliding_window_pattern": 6,
30
  "torch_dtype": "bfloat16",
31
  "transformers_version": "4.50.0.dev0",
 
32
  "use_cache": true,
33
- "vocab_size": 262144
34
  }
 
7
  "attn_logit_softcapping": null,
8
  "bos_token_id": 2,
9
  "cache_implementation": "hybrid",
10
+ "eos_token_id": 106,
11
  "final_logit_softcapping": null,
12
  "head_dim": 256,
13
  "hidden_activation": "gelu_pytorch_tanh",
 
29
  "sliding_window_pattern": 6,
30
  "torch_dtype": "bfloat16",
31
  "transformers_version": "4.50.0.dev0",
32
+ "unsloth_fixed": true,
33
  "use_cache": true,
34
+ "vocab_size": 262145
35
  }
generation_config.json CHANGED
@@ -2,7 +2,11 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "cache_implementation": "hybrid",
 
5
  "eos_token_id": 1,
 
6
  "pad_token_id": 0,
 
 
7
  "transformers_version": "4.50.0.dev0"
8
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "cache_implementation": "hybrid",
5
+ "do_sample": true,
6
  "eos_token_id": 1,
7
+ "max_length": 32768,
8
  "pad_token_id": 0,
9
+ "top_k": 64,
10
+ "top_p": 0.95,
11
  "transformers_version": "4.50.0.dev0"
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d4ef8d71c14db7e448a09ebe891cfb6bf32c57a9b44499ae0d1c098e48516b6
3
- size 1999811208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796d67b3119c541d7caea2df6939ad4fc4551ceb64f6d20879b511576609bdba
3
+ size 1999813512
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
@@ -51328,15 +51328,16 @@
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>",
51335
  "image_token": "<image_soft_token>"
51336
  },
51337
  "image_token": "<image_soft_token>",
51338
- "model_max_length": 1000000000000000019884624838656,
51339
  "pad_token": "<pad>",
 
51340
  "processor_class": "Gemma3Processor",
51341
  "sp_model_kwargs": null,
51342
  "spaces_between_special_tokens": false,
 
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>",
51335
  "image_token": "<image_soft_token>"
51336
  },
51337
  "image_token": "<image_soft_token>",
51338
+ "model_max_length": 32768,
51339
  "pad_token": "<pad>",
51340
+ "padding_side": "left",
51341
  "processor_class": "Gemma3Processor",
51342
  "sp_model_kwargs": null,
51343
  "spaces_between_special_tokens": false,