Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +1 -0
- chat_template.json +1 -0
- config.json +86 -0
- generation_config.json +8 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +1 -0
- processor_config.json +1 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ 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
|
|
|
|
|
|
| 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
|
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<image_soft_token>": 262144 }
|
chat_template.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"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"}
|
config.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_logit_softcapping": null,
|
| 8 |
+
"boi_token_index": 255999,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"cache_implementation": "hybrid",
|
| 11 |
+
"eoi_token_index": 256000,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"final_logit_softcapping": null,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 16 |
+
"hidden_size": 5376,
|
| 17 |
+
"image_token_index": 262144,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 21504,
|
| 20 |
+
"max_position_embeddings": 131072,
|
| 21 |
+
"mm_tokens_per_image": 256,
|
| 22 |
+
"model_type": "gemma3",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_hidden_layers": 62,
|
| 25 |
+
"num_key_value_heads": 16,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"query_pre_attn_scalar": 168,
|
| 28 |
+
"rms_norm_eps": 1e-06,
|
| 29 |
+
"rope_local_base_freq": 10000.0,
|
| 30 |
+
"rope_scaling": {
|
| 31 |
+
"factor": 8.0,
|
| 32 |
+
"rope_type": "linear"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 1000000.0,
|
| 35 |
+
"sliding_window": 1024,
|
| 36 |
+
"sliding_window_pattern": 6,
|
| 37 |
+
"text_config": {
|
| 38 |
+
"attention_bias": false,
|
| 39 |
+
"attention_dropout": 0.0,
|
| 40 |
+
"attn_logit_softcapping": null,
|
| 41 |
+
"cache_implementation": "hybrid",
|
| 42 |
+
"final_logit_softcapping": null,
|
| 43 |
+
"head_dim": 128,
|
| 44 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 45 |
+
"hidden_size": 5376,
|
| 46 |
+
"initializer_range": 0.02,
|
| 47 |
+
"intermediate_size": 21504,
|
| 48 |
+
"max_position_embeddings": 131072,
|
| 49 |
+
"model_type": "gemma3_text",
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 62,
|
| 52 |
+
"num_key_value_heads": 16,
|
| 53 |
+
"query_pre_attn_scalar": 168,
|
| 54 |
+
"rms_norm_eps": 1e-06,
|
| 55 |
+
"rope_local_base_freq": 10000.0,
|
| 56 |
+
"rope_scaling": {
|
| 57 |
+
"factor": 8.0,
|
| 58 |
+
"rope_type": "linear"
|
| 59 |
+
},
|
| 60 |
+
"rope_theta": 1000000.0,
|
| 61 |
+
"sliding_window": 1024,
|
| 62 |
+
"sliding_window_pattern": 6,
|
| 63 |
+
"torch_dtype": "bfloat16",
|
| 64 |
+
"use_cache": true,
|
| 65 |
+
"vocab_size": 262208
|
| 66 |
+
},
|
| 67 |
+
"torch_dtype": "bfloat16",
|
| 68 |
+
"transformers_version": "4.50.0.dev0",
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"vision_config": {
|
| 71 |
+
"attention_dropout": 0.0,
|
| 72 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 73 |
+
"hidden_size": 1152,
|
| 74 |
+
"image_size": 896,
|
| 75 |
+
"intermediate_size": 4304,
|
| 76 |
+
"layer_norm_eps": 1e-06,
|
| 77 |
+
"model_type": "siglip_vision_model",
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"num_channels": 3,
|
| 80 |
+
"num_hidden_layers": 27,
|
| 81 |
+
"patch_size": 14,
|
| 82 |
+
"torch_dtype": "bfloat16",
|
| 83 |
+
"vision_use_head": false
|
| 84 |
+
},
|
| 85 |
+
"vocab_size": 262208
|
| 86 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 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 |
+
}
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36cf526e16731b42b3b7b826f0b399a32a1d88354081613f368081fe5454c547
|
| 3 |
+
size 4259986008
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:893f0b88efac2ce0315036ddcd63dc9bffd2710cf2add927e099877b2aef7294
|
| 3 |
+
size 4128994104
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4688669023969984322c00ce006c945be6b9f069b9fc943051abc715c91839f4
|
| 3 |
+
size 4128994128
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f24a13a796f05d43646e7f8c002815fb0495ebaf626e192c273f5c3f5d47f76a
|
| 3 |
+
size 4128994168
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abaa32cb55c5f7d047330632e03dae0c9a553aa03f1e203c7f3704c2ca8d99a7
|
| 3 |
+
size 4128994168
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12e0a29753896fd649539127581c36d194477eb0b99c014b0be294226e734bea
|
| 3 |
+
size 4128994168
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e49e3ba300657daec59687c9419978711df162e549563aab898677169632f7
|
| 3 |
+
size 4128994168
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4e7a4ef18d06c2ce96e1c1c090fceefef42f54f94b5a23c5d41e683c5072bda
|
| 3 |
+
size 4128994168
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d5be50e36d4e31ea23b49fae15cf644fb84417e71b2a73dec9787e660eb4dac
|
| 3 |
+
size 4128994168
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d437d057dd1e7d7fe5ce742316159b63418b4b3b707e9dabc5196777ca30bb
|
| 3 |
+
size 4128994168
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03a5a7b1cfcf8c8bb9b550344c8970e142f8d3d7c64990bf81d6c8778203a42d
|
| 3 |
+
size 4128994168
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8892702e0d0ecf28810b6f44ab88f878c1e793ef8c62eadc1a61be8252554499
|
| 3 |
+
size 4128994168
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afc29d831a1af0393834bf734338860ff4da29252f65a49f51cd6f6a5ecf6bf3
|
| 3 |
+
size 4128994168
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7cafa29f4e911e4fc4252fe8335b3aebfcb3ad6369866213b6a203cb2bf9b75
|
| 3 |
+
size 3876324936
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_convert_rgb": null, "do_normalize": true, "do_pan_and_scan": null, "do_rescale": true, "do_resize": true, "image_mean": [0.5, 0.5, 0.5], "image_processor_type": "Gemma3ImageProcessor", "image_seq_length": 256, "image_std": [0.5, 0.5, 0.5], "pan_and_scan_max_num_crops": null, "pan_and_scan_min_crop_size": null, "pan_and_scan_min_ratio_to_activate": null, "processor_class": "Gemma3Processor", "resample": 2, "rescale_factor": 0.00392156862745098, "size": {"height": 896, "width": 896}}
|
processor_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"image_seq_length": 256, "processor_class": "Gemma3Processor"}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 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>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|