Duplicate from Itorgow/dippy_33

Co-authored-by: Rasheed elhindi <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1 @@
+{"<image_soft_token>": 262144}      

chat_template.json

@@ -0,0 +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

@@ -0,0 +1 @@
+  {"architectures": ["Gemma3ForConditionalGeneration"], "boi_token_index": 255999, "eoi_token_index": 256000, "eos_token_id": [1, 106], "image_token_index": 262144, "initializer_range": 0.02, "mm_tokens_per_image": 256, "model_type": "gemma3", "text_config": {"head_dim": 128, "hidden_size": 5376, "intermediate_size": 21504, "model_type": "gemma3_text", "num_attention_heads": 32, "num_hidden_layers": 62, "num_key_value_heads": 16, "query_pre_attn_scalar": 168, "rope_scaling": {"factor": 8.0, "rope_type": "linear"}, "sliding_window": 1024}, "torch_dtype": "bfloat16", "transformers_version": "4.50.0.dev0", "vision_config": {"hidden_size": 1152, "image_size": 896, "intermediate_size": 4304, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_hidden_layers": 27, "patch_size": 14, "vision_use_head": false}}          

generation_config.json

@@ -0,0 +1 @@
+   {"bos_token_id": 2, "cache_implementation": "hybrid", "do_sample": true, "eos_token_id": [1, 106], "pad_token_id": 0, "top_k": 64, "top_p": 0.95, "transformers_version": "4.50.0.dev0"}   

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75bbf6440ab3579b12ee34240f3b9f3d70360a66a0d80cebdd40a217dbfc6b1e
+size 4854573664

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331580dfd87d22478e24af59d085b9da90edb101b635a5ebed729ee5d8fc7ea3
+size 4954792912

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3d7137386e2e7f4433a7e8e4975abf2afa5f474d56cc04a367baa8d5e15456
+size 4954792944

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1cadb4f64d714f418d4665835f5412564dafae476f2deb5bdecd80bf75ae25c
+size 4954792984

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfa5725daf776f92262d4e8ad3178cd81de6973d25b2ecb9b4867f9742cb1b8
+size 4954792984

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31a04f184ba4696f6d0805c42e9204233f29ea96dc5e38275e2b2fc384b1e7d
+size 4954792984

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7828b2e94c0a0b15fe427d25c85c67b95d4f5d0ffe276e75ff612a136fb82e69
+size 4954792984

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c631715486b47762f60a809322b2674dba357c66022819aa6f4c8c1507cdbc65
+size 4954792984

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287f982850418c45c135d3b1d6449b5205b222420833b2088f59dd1432bae2ef
+size 4954792984

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6149b7d0d36b1e121522149ed852e1879fe2cc314fd778fe5cddefb992a41841
+size 4954792984

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf0aa85ce2cb7c1f383085cde3c3cf593188e3d00c70a62278fd0742b8f0018
+size 4954792984

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8796d88227a30afaba7cc9503cb8944bd13098692f81a127aac7ec253786c9c6
+size 462476664

preprocessor_config.json

@@ -0,0 +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

@@ -0,0 +1 @@
+{"image_seq_length": 256, "processor_class": "Gemma3Processor"}       

special_tokens_map.json

@@ -0,0 +1 @@
+ {"boi_token": "<start_of_image>", "bos_token": {"content": "<bos>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false}, "eoi_token": "<end_of_image>", "eos_token": {"content": "<eos>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false}, "image_token": "<image_soft_token>", "pad_token": {"content": "<pad>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false}, "unk_token": {"content": "<unk>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false}}    

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae19b3c81b38ae9e4e5953d7ee23bb397bc689c9841f95f71ef279d2a390bd2
+size 20323114

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074