danielhanchen commited on
Commit
3f8614e
·
verified ·
1 Parent(s): f78ac10

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,4 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
40
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.model filter=lfs diff=lfs merge=lfs -text
42
+ model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "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"
3
+ }
config.json CHANGED
@@ -3,14 +3,15 @@
3
  "Gemma3ForConditionalGeneration"
4
  ],
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,
12
  "model_type": "gemma3",
13
- "pad_token_id": 0,
14
  "text_config": {
15
  "attention_bias": false,
16
  "attention_dropout": 0.0,
@@ -43,7 +44,6 @@
43
  },
44
  "torch_dtype": "bfloat16",
45
  "transformers_version": "4.52.0.dev0",
46
- "unsloth_fixed": true,
47
  "vision_config": {
48
  "attention_dropout": 0.0,
49
  "hidden_act": "gelu_pytorch_tanh",
 
3
  "Gemma3ForConditionalGeneration"
4
  ],
5
  "boi_token_index": 255999,
 
6
  "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
  "image_token_index": 262144,
12
  "initializer_range": 0.02,
13
  "mm_tokens_per_image": 256,
14
  "model_type": "gemma3",
 
15
  "text_config": {
16
  "attention_bias": false,
17
  "attention_dropout": 0.0,
 
44
  },
45
  "torch_dtype": "bfloat16",
46
  "transformers_version": "4.52.0.dev0",
 
47
  "vision_config": {
48
  "attention_dropout": 0.0,
49
  "hidden_act": "gelu_pytorch_tanh",
generation_config.json CHANGED
@@ -1,12 +1,10 @@
1
  {
2
- "bos_token_id": 2,
3
  "cache_implementation": "hybrid",
4
  "do_sample": true,
5
  "eos_token_id": [
6
  1,
7
  106
8
  ],
9
- "pad_token_id": 0,
10
  "top_k": 64,
11
  "top_p": 0.95,
12
  "transformers_version": "4.52.0.dev0"
 
1
  {
 
2
  "cache_implementation": "hybrid",
3
  "do_sample": true,
4
  "eos_token_id": [
5
  1,
6
  106
7
  ],
 
8
  "top_k": 64,
9
  "top_p": 0.95,
10
  "transformers_version": "4.52.0.dev0"
special_tokens_map.json CHANGED
@@ -9,7 +9,7 @@
9
  },
10
  "eoi_token": "<end_of_image>",
11
  "eos_token": {
12
- "content": "<end_of_turn>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
9
  },
10
  "eoi_token": "<end_of_image>",
11
  "eos_token": {
12
+ "content": "<eos>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
- size 33384568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
3
+ size 33384570
tokenizer_config.json CHANGED
@@ -2160,7 +2160,7 @@
2160
  "normalized": false,
2161
  "rstrip": false,
2162
  "single_word": false,
2163
- "special": true
2164
  },
2165
  "256000": {
2166
  "content": "<end_of_image>",
@@ -2168,7 +2168,7 @@
2168
  "normalized": false,
2169
  "rstrip": false,
2170
  "single_word": false,
2171
- "special": true
2172
  },
2173
  "256001": {
2174
  "content": "<unused99>",
@@ -51325,18 +51325,18 @@
51325
  },
51326
  "boi_token": "<start_of_image>",
51327
  "bos_token": "<bos>",
 
51328
  "clean_up_tokenization_spaces": false,
51329
  "eoi_token": "<end_of_image>",
51330
- "eos_token": "<end_of_turn>",
51331
  "extra_special_tokens": {
51332
  "boi_token": "<start_of_image>",
51333
  "eoi_token": "<end_of_image>",
51334
  "image_token": "<image_soft_token>"
51335
  },
51336
  "image_token": "<image_soft_token>",
51337
- "model_max_length": 131072,
51338
  "pad_token": "<pad>",
51339
- "padding_side": "left",
51340
  "processor_class": "Gemma3Processor",
51341
  "sp_model_kwargs": null,
51342
  "spaces_between_special_tokens": false,
 
2160
  "normalized": false,
2161
  "rstrip": false,
2162
  "single_word": false,
2163
+ "special": false
2164
  },
2165
  "256000": {
2166
  "content": "<end_of_image>",
 
2168
  "normalized": false,
2169
  "rstrip": false,
2170
  "single_word": false,
2171
+ "special": false
2172
  },
2173
  "256001": {
2174
  "content": "<unused99>",
 
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",
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,