Upload processor
Browse files- .gitattributes +1 -0
- chat_template.jinja +49 -0
- preprocessor_config.json +51 -0
- processor_config.json +5 -0
- special_tokens_map.json +36 -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
         | 
    	
        chat_template.jinja
    ADDED
    
    | @@ -0,0 +1,49 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {{ bos_token }}
         | 
| 2 | 
            +
            {%- if messages[0]['role'] == 'system' -%}
         | 
| 3 | 
            +
                {%- if messages[0]['content'] is string -%}
         | 
| 4 | 
            +
                    {%- set first_user_prefix = messages[0]['content'] + '
         | 
| 5 | 
            +
             | 
| 6 | 
            +
            ' -%}
         | 
| 7 | 
            +
                {%- else -%}
         | 
| 8 | 
            +
                    {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
         | 
| 9 | 
            +
             | 
| 10 | 
            +
            ' -%}
         | 
| 11 | 
            +
                {%- endif -%}
         | 
| 12 | 
            +
                {%- set loop_messages = messages[1:] -%}
         | 
| 13 | 
            +
            {%- else -%}
         | 
| 14 | 
            +
                {%- set first_user_prefix = "" -%}
         | 
| 15 | 
            +
                {%- set loop_messages = messages -%}
         | 
| 16 | 
            +
            {%- endif -%}
         | 
| 17 | 
            +
            {%- for message in loop_messages -%}
         | 
| 18 | 
            +
                {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
         | 
| 19 | 
            +
                    {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
         | 
| 20 | 
            +
                {%- endif -%}
         | 
| 21 | 
            +
                {%- if (message['role'] == 'assistant') -%}
         | 
| 22 | 
            +
                    {%- set role = "model" -%}
         | 
| 23 | 
            +
                {%- else -%}
         | 
| 24 | 
            +
                    {%- set role = message['role'] -%}
         | 
| 25 | 
            +
                {%- endif -%}
         | 
| 26 | 
            +
                {{ '<start_of_turn>' + role + '
         | 
| 27 | 
            +
            ' + (first_user_prefix if loop.first else "") }}
         | 
| 28 | 
            +
                {%- if message['content'] is string -%}
         | 
| 29 | 
            +
                    {{ message['content'] | trim }}
         | 
| 30 | 
            +
                {%- elif message['content'] is iterable -%}
         | 
| 31 | 
            +
                    {%- for item in message['content'] -%}
         | 
| 32 | 
            +
                        {%- if item['type'] == 'audio' -%}
         | 
| 33 | 
            +
                            {{ '<audio_soft_token>' }}
         | 
| 34 | 
            +
                        {%- elif item['type'] == 'image' -%}
         | 
| 35 | 
            +
                            {{ '<image_soft_token>' }}
         | 
| 36 | 
            +
                        {%- elif item['type'] == 'text' -%}
         | 
| 37 | 
            +
                            {{ item['text'] | trim }}
         | 
| 38 | 
            +
                        {%- endif -%}
         | 
| 39 | 
            +
                    {%- endfor -%}
         | 
| 40 | 
            +
                {%- else -%}
         | 
| 41 | 
            +
                    {{ raise_exception("Invalid content type") }}
         | 
| 42 | 
            +
                {%- endif -%}
         | 
| 43 | 
            +
                {{ '<end_of_turn>
         | 
| 44 | 
            +
            ' }}
         | 
| 45 | 
            +
            {%- endfor -%}
         | 
| 46 | 
            +
            {%- if add_generation_prompt -%}
         | 
| 47 | 
            +
                {{'<start_of_turn>model
         | 
| 48 | 
            +
            '}}
         | 
| 49 | 
            +
            {%- endif -%}
         | 
    	
        preprocessor_config.json
    ADDED
    
    | @@ -0,0 +1,51 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "crop_size": null,
         | 
| 3 | 
            +
              "data_format": "channels_first",
         | 
| 4 | 
            +
              "default_to_square": false,
         | 
| 5 | 
            +
              "device": null,
         | 
| 6 | 
            +
              "disable_grouping": null,
         | 
| 7 | 
            +
              "dither": 0.0,
         | 
| 8 | 
            +
              "do_center_crop": null,
         | 
| 9 | 
            +
              "do_convert_rgb": null,
         | 
| 10 | 
            +
              "do_normalize": false,
         | 
| 11 | 
            +
              "do_rescale": true,
         | 
| 12 | 
            +
              "do_resize": true,
         | 
| 13 | 
            +
              "feature_size": 128,
         | 
| 14 | 
            +
              "fft_length": 1024,
         | 
| 15 | 
            +
              "fft_overdrive": true,
         | 
| 16 | 
            +
              "frame_length": 512,
         | 
| 17 | 
            +
              "hop_length": 160,
         | 
| 18 | 
            +
              "image_mean": [
         | 
| 19 | 
            +
                0.5,
         | 
| 20 | 
            +
                0.5,
         | 
| 21 | 
            +
                0.5
         | 
| 22 | 
            +
              ],
         | 
| 23 | 
            +
              "image_processor_type": "SiglipImageProcessorFast",
         | 
| 24 | 
            +
              "image_seq_length": 256,
         | 
| 25 | 
            +
              "image_std": [
         | 
| 26 | 
            +
                0.5,
         | 
| 27 | 
            +
                0.5,
         | 
| 28 | 
            +
                0.5
         | 
| 29 | 
            +
              ],
         | 
| 30 | 
            +
              "input_data_format": null,
         | 
| 31 | 
            +
              "input_scale_factor": 1.0,
         | 
| 32 | 
            +
              "max_frequency": 7600.0,
         | 
| 33 | 
            +
              "mel_floor": 1e-05,
         | 
| 34 | 
            +
              "min_frequency": 125.0,
         | 
| 35 | 
            +
              "padding_side": "right",
         | 
| 36 | 
            +
              "padding_value": 0.0,
         | 
| 37 | 
            +
              "per_bin_mean": null,
         | 
| 38 | 
            +
              "per_bin_stddev": null,
         | 
| 39 | 
            +
              "preemphasis": 0.97,
         | 
| 40 | 
            +
              "preemphasis_htk_flavor": true,
         | 
| 41 | 
            +
              "processor_class": "Gemma3nProcessor",
         | 
| 42 | 
            +
              "resample": 2,
         | 
| 43 | 
            +
              "rescale_factor": 0.00392156862745098,
         | 
| 44 | 
            +
              "return_attention_mask": true,
         | 
| 45 | 
            +
              "return_tensors": null,
         | 
| 46 | 
            +
              "sampling_rate": 16000,
         | 
| 47 | 
            +
              "size": {
         | 
| 48 | 
            +
                "height": 768,
         | 
| 49 | 
            +
                "width": 768
         | 
| 50 | 
            +
              }
         | 
| 51 | 
            +
            }
         | 
    	
        processor_config.json
    ADDED
    
    | @@ -0,0 +1,5 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "audio_seq_length": 188,
         | 
| 3 | 
            +
              "image_seq_length": 256,
         | 
| 4 | 
            +
              "processor_class": "Gemma3nProcessor"
         | 
| 5 | 
            +
            }
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,36 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "audio_token": "<audio_soft_token>",
         | 
| 3 | 
            +
              "boa_token": "<start_of_audio>",
         | 
| 4 | 
            +
              "boi_token": "<start_of_image>",
         | 
| 5 | 
            +
              "bos_token": {
         | 
| 6 | 
            +
                "content": "<bos>",
         | 
| 7 | 
            +
                "lstrip": false,
         | 
| 8 | 
            +
                "normalized": false,
         | 
| 9 | 
            +
                "rstrip": false,
         | 
| 10 | 
            +
                "single_word": false
         | 
| 11 | 
            +
              },
         | 
| 12 | 
            +
              "eoa_token": "<end_of_audio>",
         | 
| 13 | 
            +
              "eoi_token": "<end_of_image>",
         | 
| 14 | 
            +
              "eos_token": {
         | 
| 15 | 
            +
                "content": "<eos>",
         | 
| 16 | 
            +
                "lstrip": false,
         | 
| 17 | 
            +
                "normalized": false,
         | 
| 18 | 
            +
                "rstrip": false,
         | 
| 19 | 
            +
                "single_word": false
         | 
| 20 | 
            +
              },
         | 
| 21 | 
            +
              "image_token": "<image_soft_token>",
         | 
| 22 | 
            +
              "pad_token": {
         | 
| 23 | 
            +
                "content": "<pad>",
         | 
| 24 | 
            +
                "lstrip": false,
         | 
| 25 | 
            +
                "normalized": false,
         | 
| 26 | 
            +
                "rstrip": false,
         | 
| 27 | 
            +
                "single_word": false
         | 
| 28 | 
            +
              },
         | 
| 29 | 
            +
              "unk_token": {
         | 
| 30 | 
            +
                "content": "<unk>",
         | 
| 31 | 
            +
                "lstrip": false,
         | 
| 32 | 
            +
                "normalized": false,
         | 
| 33 | 
            +
                "rstrip": false,
         | 
| 34 | 
            +
                "single_word": false
         | 
| 35 | 
            +
              }
         | 
| 36 | 
            +
            }
         | 
    	
        tokenizer.json
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
         | 
| 3 | 
            +
            size 33442553
         | 
    	
        tokenizer.model
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:ea5f0cc48abfbfc04d14562270a32e02149a3e7035f368cc5a462786f4a59961
         | 
| 3 | 
            +
            size 4696020
         | 
    	
        tokenizer_config.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
