Puujeeeeeeeeeeee/sft-task-patterns-v2
04
1{2 "audio_token": "<|audio|>",3 "backend": "tokenizers",4 "boa_token": "<|audio>",5 "boi_token": "<|image>",6 "bos_token": "<bos>",7 "eoa_token": "<audio|>",8 "eoc_token": "<channel|>",9 "eoi_token": "<image|>",10 "eos_token": "<eos>",11 "eot_token": "<turn|>",12 "escape_token": "<|\"|>",13 "etc_token": "<tool_call|>",14 "etd_token": "<tool|>",15 "etr_token": "<tool_response|>",16 "extra_special_tokens": [17 "<|video|>"18 ],19 "image_token": "<|image|>",20 "is_local": false,21 "local_files_only": false,22 "mask_token": "<mask>",23 "max_length": 1024,24 "model_max_length": 131072,25 "model_specific_special_tokens": {26 "audio_token": "<|audio|>",27 "boa_token": "<|audio>",28 "boi_token": "<|image>",29 "eoa_token": "<audio|>",30 "eoc_token": "<channel|>",31 "eoi_token": "<image|>",32 "eot_token": "<turn|>",33 "escape_token": "<|\"|>",34 "etc_token": "<tool_call|>",35 "etd_token": "<tool|>",36 "etr_token": "<tool_response|>",37 "image_token": "<|image|>",38 "soc_token": "<|channel>",39 "sot_token": "<|turn>",40 "stc_token": "<|tool_call>",41 "std_token": "<|tool>",42 "str_token": "<|tool_response>",43 "think_token": "<|think|>"44 },45 "pad_token": "<pad>",46 "padding_side": "right",47 "processor_class": "Gemma4Processor",48 "soc_token": "<|channel>",49 "sot_token": "<|turn>",50 "stc_token": "<|tool_call>",51 "std_token": "<|tool>",52 "str_token": "<|tool_response>",53 "stride": 0,54 "think_token": "<|think|>",55 "tokenizer_class": "GemmaTokenizer",56 "truncation_side": "right",57 "truncation_strategy": "longest_first",58 "unk_token": "<unk>",59 "added_tokens_decoder": {60 "0": {61 "content": "<pad>",62 "single_word": false,63 "lstrip": false,64 "rstrip": false,65 "normalized": false,66 "special": true67 },68 "1": {69 "content": "<eos>",70 "single_word": false,71 "lstrip": false,72 "rstrip": false,73 "normalized": false,74 "special": true75 },76 "2": {77 "content": "<bos>",78 "single_word": false,79 "lstrip": false,80 "rstrip": false,81 "normalized": false,82 "special": true83 },84 "3": {85 "content": "<unk>",86 "single_word": false,87 "lstrip": false,88 "rstrip": false,89 "normalized": false,90 "special": true91 },92 "4": {93 "content": "<mask>",94 "single_word": false,95 "lstrip": false,96 "rstrip": false,97 "normalized": false,98 "special": true99 },100 "46": {101 "content": "<|tool>",102 "single_word": false,103 "lstrip": false,104 "rstrip": false,105 "normalized": false,106 "special": true107 },108 "47": {109 "content": "<tool|>",110 "single_word": false,111 "lstrip": false,112 "rstrip": false,113 "normalized": false,114 "special": true115 },116 "48": {117 "content": "<|tool_call>",118 "single_word": false,119 "lstrip": false,120 "rstrip": false,121 "normalized": false,122 "special": true123 },124 "49": {125 "content": "<tool_call|>",126 "single_word": false,127 "lstrip": false,128 "rstrip": false,129 "normalized": false,130 "special": true131 },132 "50": {133 "content": "<|tool_response>",134 "single_word": false,135 "lstrip": false,136 "rstrip": false,137 "normalized": false,138 "special": true139 },140 "51": {141 "content": "<tool_response|>",142 "single_word": false,143 "lstrip": false,144 "rstrip": false,145 "normalized": false,146 "special": true147 },148 "52": {149 "content": "<|\"|>",150 "single_word": false,151 "lstrip": false,152 "rstrip": false,153 "normalized": false,154 "special": true155 },156 "98": {157 "content": "<|think|>",158 "single_word": false,159 "lstrip": false,160 "rstrip": false,161 "normalized": false,162 "special": true163 },164 "100": {165 "content": "<|channel>",166 "single_word": false,167 "lstrip": false,168 "rstrip": false,169 "normalized": false,170 "special": true171 },172 "101": {173 "content": "<channel|>",174 "single_word": false,175 "lstrip": false,176 "rstrip": false,177 "normalized": false,178 "special": true179 },180 "105": {181 "content": "<|turn>",182 "single_word": false,183 "lstrip": false,184 "rstrip": false,185 "normalized": false,186 "special": true187 },188 "106": {189 "content": "<turn|>",190 "single_word": false,191 "lstrip": false,192 "rstrip": false,193 "normalized": false,194 "special": true195 },196 "255999": {197 "content": "<|image>",198 "single_word": false,199 "lstrip": false,200 "rstrip": false,201 "normalized": false,202 "special": true203 },204 "256000": {205 "content": "<|audio>",206 "single_word": false,207 "lstrip": false,208 "rstrip": false,209 "normalized": false,210 "special": true211 },212 "258880": {213 "content": "<|image|>",214 "single_word": false,215 "lstrip": false,216 "rstrip": false,217 "normalized": false,218 "special": true219 },220 "258881": {221 "content": "<|audio|>",222 "single_word": false,223 "lstrip": false,224 "rstrip": false,225 "normalized": false,226 "special": true227 },228 "258882": {229 "content": "<image|>",230 "single_word": false,231 "lstrip": false,232 "rstrip": false,233 "normalized": false,234 "special": true235 },236 "258883": {237 "content": "<audio|>",238 "single_word": false,239 "lstrip": false,240 "rstrip": false,241 "normalized": false,242 "special": true243 },244 "258884": {245 "content": "<|video|>",246 "single_word": false,247 "lstrip": false,248 "rstrip": false,249 "normalized": false,250 "special": true251 }252 },253 "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if not filter_keys or key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is none -%}\n {{- 'null' -}}\n {%- elif argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{#- ===== SETUP ===== -#}\n{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}\n{%- set loop_messages = messages -%}\n{%- set enable_thinking = enable_thinking | default(false) -%}\n{%- set preserve_thinking = preserve_thinking | default(false) -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}\n {%- if messages[0]['content'] is string -%}\n {{- messages[0]['content'] | trim -}}\n {%- elif messages[0]['content'] is sequence -%}\n {%- for item in messages[0]['content'] -%}\n {{- item['text'] | trim + ' '-}}\n {%- endfor -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}\n {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}\n {%- if thinking_text and thinking_gate -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n\n {%- if message.get('tool_calls') -%}\n {%- for tool_call in message.get('tool_calls') -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is none -%}\n {%- elif function['arguments'] is string -%}\n {#- Pre-serialized args (e.g. an OpenAI JSON string). We cannot JSON-parse\n portably in-template, so render non-fatally instead of erroring. Strip an\n outer {...} so it composes with the DSL braces rather than double-wrapping.\n Prefer passing arguments as a mapping for exact Gemma DSL. -#}\n {%- set argstr = function['arguments'] | trim -%}\n {%- if argstr[:1] == '{' and argstr[-1:] == '}' -%}\n {{- argstr[1:-1] -}}\n {%- else -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message.get('tool_responses') -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}\n {%- for tc in message.get('tool_calls') -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- for part in tool_body -%}\n {%- if part.get('type') in ['image', 'image_url'] -%}\n {{- '<|image|>' -}}\n {%- elif part.get('type') in ['audio', 'input_audio'] -%}\n {{- '<|audio|>' -}}\n {%- elif part.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n\n {%- set captured_content -%}\n {%- if message.get('content') is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message.get('content') is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item.get('type') == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item.get('type') in ['image', 'image_url'] -%}\n {{- '<|image|>' -}}\n {%- elif item.get('type') in ['audio', 'input_audio'] -%}\n {{- '<|audio|>' -}}\n {%- elif item.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endset -%}\n\n {{- captured_content -}}\n {%- set has_content = captured_content | trim | length > 0 -%}\n\n {#- Forward-scan: find next non-tool message role for continuation detection -#}\n {%- set next_nt = namespace(role=None, found=false) -%}\n {%- for j in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if not next_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set next_nt.role = loop_messages[j]['role'] -%}\n {%- set next_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n\n {%- set continues_into_next = (\n role == 'model'\n and next_nt.role == 'assistant'\n and (not message.get('tool_calls') or ns_tr_out.flag)\n ) -%}\n\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif continues_into_next -%}\n {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n\n {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}\n {%- set ns.prev_non_tool_role = message['role'] -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}\n {{- '<|channel>thought\\n' -}}\n {%- endif -%}\n{%- endif -%}\n"254}