Delete e2b/mlx/tokenizer_config.json

e2b/mlx/tokenizer_config.json

@@ -1,254 +0,0 @@
-{
-  "audio_token": "<|audio|>",
-  "backend": "tokenizers",
-  "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|>",
-  "extra_special_tokens": [
-    "<|video|>"
-  ],
-  "image_token": "<|image|>",
-  "processor_class": "Gemma4Processor",
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "soc_token": "<|channel>",
-  "sot_token": "<|turn>",
-  "stc_token": "<|tool_call>",
-  "std_token": "<|tool>",
-  "str_token": "<|tool_response>",
-  "think_token": "<|think|>",
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<eos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<bos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<mask>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46": {
-      "content": "<|tool>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "47": {
-      "content": "<tool|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "48": {
-      "content": "<|tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49": {
-      "content": "<tool_call|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50": {
-      "content": "<|tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "51": {
-      "content": "<tool_response|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "52": {
-      "content": "<|\"|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "98": {
-      "content": "<|think|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "<|channel>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "<channel|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "105": {
-      "content": "<|turn>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "106": {
-      "content": "<turn|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "255999": {
-      "content": "<|image>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "256000": {
-      "content": "<|audio>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "258880": {
-      "content": "<|image|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "258881": {
-      "content": "<|audio|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "258882": {
-      "content": "<image|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "258883": {
-      "content": "<audio|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "258884": {
-      "content": "<|video|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "<|tool>",
-    "<tool|>",
-    "<|tool_call>",
-    "<tool_call|>",
-    "<|tool_response>",
-    "<tool_response|>",
-    "<|\"|>",
-    "<|think|>",
-    "<|channel>",
-    "<channel|>",
-    "<|turn>",
-    "<turn|>",
-    "<|image>",
-    "<|audio>",
-    "<|image|>",
-    "<|audio|>",
-    "<image|>",
-    "<audio|>",
-    "<|video|>"
-  ],
-  "bos_token": "<bos>",
-  "chat_template": "{%- macro format_parameters(properties, required) -%}\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 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([])) -}}\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 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 iterable -%}\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{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n    {{- '<|turn>system\\n' -}}\n\n    {#- Inject Thinking token at the very top of the FIRST system turn -#}\n    {%- if enable_thinking is defined and enable_thinking -%}\n        {{- '<|think|>\\n' -}}\n        {%- set ns.prev_message_type = 'think' -%}\n    {%- endif -%}\n\n    {%- if messages[0]['role'] in ['system', 'developer'] -%}\n        {{- messages[0]['content'] | trim -}}\n        {%- set loop_messages = messages[1:] -%}\n    {%- endif -%}\n\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\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: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n    {%- set prev_nt = namespace(role=None, found=false) -%}\n    {%- if loop.index0 > 0 -%}\n        {%- for j in range(loop.index0 - 1, -1, -1) -%}\n            {%- if not prev_nt.found -%}\n                {%- if loop_messages[j]['role'] != 'tool' -%}\n                    {%- set prev_nt.role = loop_messages[j]['role'] -%}\n                    {%- set prev_nt.found = true -%}\n                {%- endif -%}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- endif -%}\n    {%- set continue_same_model_turn = (role == 'model' and prev_nt.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    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n        {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n    {%- endif -%}\n\n            {%- if message['tool_calls'] -%}\n                {%- for tool_call in message['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 string -%}\n                        {{- function['arguments'] -}}\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['tool_responses'] -%}\n                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), 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') | default('unknown')) -%}\n                        {%- for tc in message['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 iterable 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                        {%- 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            {%- if message['content'] is string -%}\n                {%- if role == 'model' -%}\n                    {{- strip_thinking(message['content']) -}}\n                {%- else -%}\n                    {{- message['content'] | trim -}}\n                {%- endif -%}\n            {%- elif message['content'] is iterable -%}\n                {%- for item in message['content'] -%}\n                    {%- if item['type'] == 'text' -%}\n                        {%- if role == 'model' -%}\n                            {{- strip_thinking(item['text']) -}}\n                        {%- else -%}\n                            {{- item['text'] | trim -}}\n                        {%- endif -%}\n                    {%- elif item['type'] == 'image' -%}\n                        {{- '<|image><|image|><image|>' -}}\n                        {%- set ns.prev_message_type = 'image' -%}\n                    {%- elif item['type'] == 'audio' -%}\n                        {{- '<|audio><|audio|><audio|>' -}}\n                        {%- set ns.prev_message_type = 'audio' -%}\n                    {%- elif item['type'] == 'video' -%}\n                        {{- '<|video><|video|><video|>' -}}\n                        {%- set ns.prev_message_type = 'video' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n\n        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n            {{- '<|tool_response>' -}}\n        {%- elif not (ns_tr_out.flag and not message.get('content')) -%}\n            {{- '<turn|>\\n' -}}\n        {%- endif -%}\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    {%- endif -%}\n{%- endif -%}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<turn|>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 131072,
-  "pad_token": "<pad>",
-  "padding_side": "left",
-  "split_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>"
-}