Delete gemma4_preencoded_dataset

gemma4_preencoded_dataset/processor/chat_template.jinja

@@ -1,330 +0,0 @@
-{%- macro format_parameters(properties, required) -%}
-    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
-    {%- set ns = namespace(found_first=false) -%}
-    {%- for key, value in properties | dictsort -%}
-        {%- set add_comma = false -%}
-        {%- if key not in standard_keys -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {{ key }}:{
-            {%- if value['description'] -%}
-                description:<|"|>{{ value['description'] }}<|"|>
-                {%- set add_comma = true -%}
-            {%- endif -%}
-            {%- if value['type'] | upper == 'STRING' -%}
-                {%- if value['enum'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    enum:{{ format_argument(value['enum']) }}
-                {%- endif -%}
-            {%- elif value['type'] | upper == 'ARRAY' -%}
-                {%- if value['items'] is mapping and value['items'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    items:{
-                    {%- set ns_items = namespace(found_first=false) -%}
-                    {%- for item_key, item_value in value['items'] | dictsort -%}
-                        {%- if item_value is not none -%}
-                            {%- if ns_items.found_first %},{% endif -%}
-                            {%- set ns_items.found_first = true -%}
-                            {%- if item_key == 'properties' -%}
-                                properties:{
-                                {%- if item_value is mapping -%}
-                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
-                                {%- endif -%}
-                                }
-                            {%- elif item_key == 'required' -%}
-                                required:[
-                                {%- for req_item in item_value -%}
-                                    <|"|>{{- req_item -}}<|"|>
-                                    {%- if not loop.last %},{% endif -%}
-                                {%- endfor -%}
-                                ]
-                            {%- elif item_key == 'type' -%}
-                                {%- if item_value is string -%}
-                                    type:{{ format_argument(item_value | upper) }}
-                                {%- else -%}
-                                    type:{{ format_argument(item_value | map('upper') | list) }}
-                                {%- endif -%}
-                            {%- else -%}
-                                {{ item_key }}:{{ format_argument(item_value) }}
-                            {%- endif -%}
-                        {%- endif -%}
-                    {%- endfor -%}
-                    }
-                {%- endif -%}
-            {%- endif -%}
-            {%- if value['nullable'] %}
-                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                nullable:true
-            {%- endif -%}
-            {%- if value['type'] | upper == 'OBJECT' -%}
-                {%- if value['properties'] is defined and value['properties'] is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
-                    }
-                {%- elif value is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value, value['required'] | default([])) -}}
-                    }
-                {%- endif -%}
-                {%- if value['required'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    required:[
-                    {%- for item in value['required'] | default([]) -%}
-                        <|"|>{{- item -}}<|"|>
-                        {%- if not loop.last %},{% endif -%}
-                    {%- endfor -%}
-                    ]
-                {%- endif -%}
-            {%- endif -%}
-            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-            type:<|"|>{{ value['type'] | upper }}<|"|>}
-        {%- endif -%}
-    {%- endfor -%}
-{%- endmacro -%}
-{%- macro format_function_declaration(tool_data) -%}
-    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
-    {%- set params = tool_data['function']['parameters'] -%}
-    {%- if params -%}
-        ,parameters:{
-        {%- if params['properties'] -%}
-            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
-        {%- endif -%}
-        {%- if params['required'] -%}
-            required:[
-            {%- for item in params['required'] -%}
-                <|"|>{{- item -}}<|"|>
-                {{- ',' if not loop.last -}}
-            {%- endfor -%}
-            ],
-        {%- endif -%}
-        {%- if params['type'] -%}
-            type:<|"|>{{- params['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    {%- if 'response' in tool_data['function'] -%}
-        {%- set response_declaration = tool_data['function']['response'] -%}
-        ,response:{
-        {%- if response_declaration['description'] -%}
-            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
-        {%- endif -%}
-        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
-            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    }
-{%- endmacro -%}
-{%- macro format_argument(argument, escape_keys=True) -%}
-    {%- if argument is string -%}
-        {{- '<|"|>' + argument + '<|"|>' -}}
-    {%- elif argument is boolean -%}
-        {{- 'true' if argument else 'false' -}}
-    {%- elif argument is mapping -%}
-        {{- '{' -}}
-        {%- set ns = namespace(found_first=false) -%}
-        {%- for key, value in argument | dictsort -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {%- if escape_keys -%}
-                {{- '<|"|>' + key + '<|"|>' -}}
-            {%- else -%}
-                {{- key -}}
-            {%- endif -%}
-            :{{- format_argument(value, escape_keys=escape_keys) -}}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- elif argument is sequence -%}
-        {{- '[' -}}
-        {%- for item in argument -%}
-            {{- format_argument(item, escape_keys=escape_keys) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- ']' -}}
-    {%- else -%}
-        {{- argument -}}
-    {%- endif -%}
-{%- endmacro -%}
-{%- macro strip_thinking(text) -%}
-    {%- set ns = namespace(result='') -%}
-    {%- for part in text.split('<channel|>') -%}
-        {%- if '<|channel>' in part -%}
-            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
-        {%- else -%}
-            {%- set ns.result = ns.result + part -%}
-        {%- endif -%}
-    {%- endfor -%}
-    {{- ns.result | trim -}}
-{%- endmacro -%}
-{%- macro format_tool_response_block(tool_name, response) -%}
-    {{- '<|tool_response>' -}}
-    {%- if response is mapping -%}
-        {{- 'response:' + tool_name + '{' -}}
-        {%- for key, value in response | dictsort -%}
-            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- else -%}
-        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
-    {%- endif -%}
-    {{- '<tool_response|>' -}}
-{%- endmacro -%}
-{%- set ns = namespace(prev_message_type=None) -%}
-{%- set loop_messages = messages -%}
-{{- bos_token -}}
-{#- Handle System/Tool Definitions Block -#}
-{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
-    {{- '<|turn>system\n' -}}
-    {#- Inject Thinking token at the very top of the FIRST system turn -#}
-    {%- if enable_thinking is defined and enable_thinking -%}
-        {{- '<|think|>\n' -}}
-        {%- set ns.prev_message_type = 'think' -%}
-    {%- endif -%}
-    {%- if messages[0]['role'] in ['system', 'developer'] -%}
-        {{- messages[0]['content'] | trim -}}
-        {%- set loop_messages = messages[1:] -%}
-    {%- endif -%}
-    {%- if tools -%}
-        {%- for tool in tools %}
-            {{- '<|tool>' -}}
-            {{- format_function_declaration(tool) | trim -}}
-            {{- '<tool|>' -}}
-        {%- endfor %}
-        {%- set ns.prev_message_type = 'tool' -%}
-    {%- endif -%}
-    {{- '<turn|>\n' -}}
-{%- endif %}
-{#- Pre-scan: find last user message index for reasoning guard -#}
-{%- set ns_turn = namespace(last_user_idx=-1) -%}
-{%- for i in range(loop_messages | length) -%}
-    {%- if loop_messages[i]['role'] == 'user' -%}
-        {%- set ns_turn.last_user_idx = i -%}
-    {%- endif -%}
-{%- endfor -%}
-{#- Loop through messages -#}
-{%- for message in loop_messages -%}
-    {%- if message['role'] != 'tool' -%}
-    {%- set ns.prev_message_type = None -%}
-    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
-    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
-    {%- set prev_nt = namespace(role=None, found=false) -%}
-    {%- if loop.index0 > 0 -%}
-        {%- for j in range(loop.index0 - 1, -1, -1) -%}
-            {%- if not prev_nt.found -%}
-                {%- if loop_messages[j]['role'] != 'tool' -%}
-                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
-                    {%- set prev_nt.found = true -%}
-                {%- endif -%}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- endif -%}
-    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
-    {%- if not continue_same_model_turn -%}
-        {{- '<|turn>' + role + '\n' }}
-    {%- endif -%}
-    {#- Render reasoning/reasoning_content as thinking channel -#}
-    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
-    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
-        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
-    {%- endif -%}
-            {%- if message['tool_calls'] -%}
-                {%- for tool_call in message['tool_calls'] -%}
-                    {%- set function = tool_call['function'] -%}
-                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
-                    {%- if function['arguments'] is mapping -%}
-                        {%- set ns_args = namespace(found_first=false) -%}
-                        {%- for key, value in function['arguments'] | dictsort -%}
-                            {%- if ns_args.found_first %},{% endif -%}
-                            {%- set ns_args.found_first = true -%}
-                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-                        {%- endfor -%}
-                    {%- elif function['arguments'] is string -%}
-                        {{- function['arguments'] -}}
-                    {%- endif -%}
-                    {{- '}<tool_call|>' -}}
-                {%- endfor -%}
-                {%- set ns.prev_message_type = 'tool_call' -%}
-            {%- endif -%}
-            {%- set ns_tr_out = namespace(flag=false) -%}
-            {%- if message.get('tool_responses') -%}
-                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
-                {%- for tool_response in message['tool_responses'] -%}
-                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
-                    {%- set ns_tr_out.flag = true -%}
-                    {%- set ns.prev_message_type = 'tool_response' -%}
-                {%- endfor -%}
-            {%- elif message.get('tool_calls') -%}
-                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
-                {%- set ns_tool_scan = namespace(stopped=false) -%}
-                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
-                    {%- if ns_tool_scan.stopped -%}
-                    {%- elif loop_messages[k]['role'] != 'tool' -%}
-                        {%- set ns_tool_scan.stopped = true -%}
-                    {%- else -%}
-                        {%- set follow = loop_messages[k] -%}
-                        {#- Resolve tool_call_id to function name -#}
-                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
-                        {%- for tc in message['tool_calls'] -%}
-                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
-                                {%- set ns_tname.name = tc['function']['name'] -%}
-                            {%- endif -%}
-                        {%- endfor -%}
-                        {#- Handle content as string or content-parts array -#}
-                        {%- set tool_body = follow.get('content') -%}
-                        {%- if tool_body is string -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- elif tool_body is sequence and tool_body is not string -%}
-                            {%- set ns_txt = namespace(s='') -%}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') == 'text' -%}
-                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
-                                {%- endif -%}
-                            {%- endfor -%}
-                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
-                        {%- else -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- endif -%}
-                        {%- set ns_tr_out.flag = true -%}
-                        {%- set ns.prev_message_type = 'tool_response' -%}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-            {%- if message['content'] is string -%}
-                {%- if role == 'model' -%}
-                    {{- strip_thinking(message['content']) -}}
-                {%- else -%}
-                    {{- message['content'] | trim -}}
-                {%- endif -%}
-            {%- elif message['content'] is sequence -%}
-                {%- for item in message['content'] -%}
-                    {%- if item['type'] == 'text' -%}
-                        {%- if role == 'model' -%}
-                            {{- strip_thinking(item['text']) -}}
-                        {%- else -%}
-                            {{- item['text'] | trim -}}
-                        {%- endif -%}
-                    {%- elif item['type'] == 'image' -%}
-                        {{- '<|image|>' -}}
-                        {%- set ns.prev_message_type = 'image' -%}
-                    {%- elif item['type'] == 'audio' -%}
-                        {{- '<|audio|>' -}}
-                        {%- set ns.prev_message_type = 'audio' -%}
-                    {%- elif item['type'] == 'video' -%}
-                        {{- '<|video|>' -}}
-                        {%- set ns.prev_message_type = 'video' -%}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
-            {{- '<|tool_response>' -}}
-        {%- elif not (ns_tr_out.flag and not message.get('content')) -%}
-            {{- '<turn|>\n' -}}
-        {%- endif -%}
-    {%- endif -%}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
-        {{- '<|turn>model\n' -}}
-    {%- endif -%}
-{%- endif -%}

gemma4_preencoded_dataset/processor/processor_config.json

@@ -1,290 +0,0 @@
-{
-  "audio_ms_per_token": 40,
-  "audio_seq_length": 750,
-  "feature_extractor": {
-    "audio_ms_per_token": 40,
-    "audio_seq_length": 750,
-    "dither": 0.0,
-    "feature_extractor": {
-      "dither": 0.0,
-      "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-      "feature_size": 128,
-      "fft_length": 512,
-      "fft_overdrive": false,
-      "frame_length": 320,
-      "hop_length": 160,
-      "input_scale_factor": 1.0,
-      "max_frequency": 8000.0,
-      "mel_floor": 0.001,
-      "min_frequency": 0.0,
-      "padding_side": "right",
-      "padding_value": 0.0,
-      "per_bin_mean": null,
-      "per_bin_stddev": null,
-      "preemphasis": 0.0,
-      "preemphasis_htk_flavor": true,
-      "return_attention_mask": true,
-      "sampling_rate": 16000
-    },
-    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-    "feature_size": 128,
-    "fft_length": 512,
-    "fft_overdrive": false,
-    "frame_length": 320,
-    "hop_length": 160,
-    "image_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": false,
-      "do_rescale": true,
-      "do_resize": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_processor_type": "Gemma4ImageProcessor",
-      "image_seq_length": 280,
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 280,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098
-    },
-    "image_seq_length": 280,
-    "input_scale_factor": 1.0,
-    "max_frequency": 8000.0,
-    "mel_floor": 0.001,
-    "min_frequency": 0.0,
-    "padding_side": "right",
-    "padding_value": 0.0,
-    "per_bin_mean": null,
-    "per_bin_stddev": null,
-    "preemphasis": 0.0,
-    "preemphasis_htk_flavor": true,
-    "return_attention_mask": true,
-    "sampling_rate": 16000,
-    "video_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": true,
-      "do_rescale": true,
-      "do_resize": true,
-      "do_sample_frames": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 70,
-      "num_frames": 32,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098,
-      "return_metadata": false,
-      "video_processor_type": "Gemma4VideoProcessor"
-    }
-  },
-  "image_processor": {
-    "audio_ms_per_token": 40,
-    "audio_seq_length": 750,
-    "do_convert_rgb": true,
-    "do_normalize": false,
-    "do_rescale": true,
-    "do_resize": true,
-    "feature_extractor": {
-      "dither": 0.0,
-      "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-      "feature_size": 128,
-      "fft_length": 512,
-      "fft_overdrive": false,
-      "frame_length": 320,
-      "hop_length": 160,
-      "input_scale_factor": 1.0,
-      "max_frequency": 8000.0,
-      "mel_floor": 0.001,
-      "min_frequency": 0.0,
-      "padding_side": "right",
-      "padding_value": 0.0,
-      "per_bin_mean": null,
-      "per_bin_stddev": null,
-      "preemphasis": 0.0,
-      "preemphasis_htk_flavor": true,
-      "return_attention_mask": true,
-      "sampling_rate": 16000
-    },
-    "image_mean": [
-      0.0,
-      0.0,
-      0.0
-    ],
-    "image_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": false,
-      "do_rescale": true,
-      "do_resize": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_processor_type": "Gemma4ImageProcessor",
-      "image_seq_length": 280,
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 280,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098
-    },
-    "image_processor_type": "Gemma4ImageProcessor",
-    "image_seq_length": 280,
-    "image_std": [
-      1.0,
-      1.0,
-      1.0
-    ],
-    "max_soft_tokens": 280,
-    "patch_size": 16,
-    "pooling_kernel_size": 3,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "video_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": true,
-      "do_rescale": true,
-      "do_resize": true,
-      "do_sample_frames": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 70,
-      "num_frames": 32,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098,
-      "return_metadata": false,
-      "video_processor_type": "Gemma4VideoProcessor"
-    }
-  },
-  "image_seq_length": 280,
-  "processor_class": "Gemma4Processor",
-  "video_processor": {
-    "audio_ms_per_token": 40,
-    "audio_seq_length": 750,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "feature_extractor": {
-      "dither": 0.0,
-      "feature_extractor_type": "Gemma4AudioFeatureExtractor",
-      "feature_size": 128,
-      "fft_length": 512,
-      "fft_overdrive": false,
-      "frame_length": 320,
-      "hop_length": 160,
-      "input_scale_factor": 1.0,
-      "max_frequency": 8000.0,
-      "mel_floor": 0.001,
-      "min_frequency": 0.0,
-      "padding_side": "right",
-      "padding_value": 0.0,
-      "per_bin_mean": null,
-      "per_bin_stddev": null,
-      "preemphasis": 0.0,
-      "preemphasis_htk_flavor": true,
-      "return_attention_mask": true,
-      "sampling_rate": 16000
-    },
-    "image_mean": [
-      0.0,
-      0.0,
-      0.0
-    ],
-    "image_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": false,
-      "do_rescale": true,
-      "do_resize": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_processor_type": "Gemma4ImageProcessor",
-      "image_seq_length": 280,
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 280,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098
-    },
-    "image_seq_length": 280,
-    "image_std": [
-      1.0,
-      1.0,
-      1.0
-    ],
-    "max_soft_tokens": 70,
-    "num_frames": 32,
-    "patch_size": 16,
-    "pooling_kernel_size": 3,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "video_processor": {
-      "do_convert_rgb": true,
-      "do_normalize": true,
-      "do_rescale": true,
-      "do_resize": true,
-      "do_sample_frames": true,
-      "image_mean": [
-        0.0,
-        0.0,
-        0.0
-      ],
-      "image_std": [
-        1.0,
-        1.0,
-        1.0
-      ],
-      "max_soft_tokens": 70,
-      "num_frames": 32,
-      "patch_size": 16,
-      "pooling_kernel_size": 3,
-      "resample": 3,
-      "rescale_factor": 0.00392156862745098,
-      "return_metadata": false,
-      "video_processor_type": "Gemma4VideoProcessor"
-    },
-    "video_processor_type": "Gemma4VideoProcessor"
-  }
-}

gemma4_preencoded_dataset/processor/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
-size 32169626

gemma4_preencoded_dataset/processor/tokenizer_config.json

@@ -1,96 +0,0 @@
-{
-  "audio_token": "<|audio|>",
-  "backend": "tokenizers",
-  "boa_token": "<|audio>",
-  "boi_token": "<|image>",
-  "bos_token": "<bos>",
-  "eoa_token": "<audio|>",
-  "eoc_token": "<channel|>",
-  "eoi_token": "<image|>",
-  "eos_token": "<eos>",
-  "eot_token": "<turn|>",
-  "escape_token": "<|\"|>",
-  "etc_token": "<tool_call|>",
-  "etd_token": "<tool|>",
-  "etr_token": "<tool_response|>",
-  "extra_special_tokens": [
-    "<|video|>"
-  ],
-  "image_token": "<|image|>",
-  "is_local": false,
-  "local_files_only": false,
-  "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
-  "pad_token": "<pad>",
-  "padding_side": "right",
-  "processor_class": "Gemma4Processor",
-  "response_schema": {
-    "properties": {
-      "content": {
-        "type": "string"
-      },
-      "role": {
-        "const": "assistant"
-      },
-      "thinking": {
-        "type": "string"
-      },
-      "tool_calls": {
-        "items": {
-          "properties": {
-            "function": {
-              "properties": {
-                "arguments": {
-                  "additionalProperties": {},
-                  "type": "object",
-                  "x-parser": "gemma4-tool-call"
-                },
-                "name": {
-                  "type": "string"
-                }
-              },
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
-            },
-            "type": {
-              "const": "function"
-            }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
-      }
-    },
-    "type": "object",
-    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
-  },
-  "soc_token": "<|channel>",
-  "sot_token": "<|turn>",
-  "stc_token": "<|tool_call>",
-  "std_token": "<|tool>",
-  "str_token": "<|tool_response>",
-  "think_token": "<|think|>",
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>"
-}