Views
No views yet
{{ bos_token }}{% if documents %}\n{% set tools = [] %}\n{%- macro document_turn(documents) -%}\n{# format documents into chat turn #}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[\n {\"tool_call_id\": \"0\", \"tool_name\": \"direct-injected-document\", \"parameters\": {}}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n {\n \"tool_call_id\": \"0\",\n \"results\": {\n{% for doc in documents %}\n \"{{ loop.index0 }}\": {{doc|tojson}}{% if not loop.last %},\n {% endif %}\n{% endfor %}\n\n },\n \"is_error\": null\n }\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}\n{%- macro tool_call_id_to_int(messages, tool_call_id) %}\n{%- set counter = namespace(value=0) %}\n{%- set tool_call_id_seen = namespace(value=false) %}\n{%- for msg in messages %}\n {%- if msg.tool_calls %}\n {%- for tool_call in msg.tool_calls %}\n {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}\n {{ counter.value }}\n {%- set tool_call_id_seen.value = true %}\n {%- endif %}\n {%- set counter.value = counter.value + 1 %}\n {%- endfor %}\n {%- endif %}\n{%- endfor %}\n{%- endmacro %}\n{%- macro format_tool_message(messages, tool_msg) -%}\n{# format tool message #}\n {\n \"tool_call_id\": \"{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}\",\n \"results\": {\n \"0\": {{ tool_msg.content|tojson }}\n },\n \"is_error\": null\n }\n{%- endmacro -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n{%- set tool_idx = namespace(value=0) %}\n{%- set tool_ids_seen = namespace(value=[]) %}\n{%- set sent_documents = namespace(value=false) %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n{% if tools or documents %}\n\nYou have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.\n\n## Tool Use\nThink about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.\n\n0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.\n NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.\n\nThen carry out your plan by repeatedly executing the following steps.\n1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing \"tool_name\" and \"parameters\" fields.\n When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.\n2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.\n Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its \"tool_call_id\".\n3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.\n NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.\n\nYou can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.\n\n4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>\n{% if enable_citations %}\n\n## Grounding\nImportantly, note that \"Reflection\" and \"Response\" above can be grounded.\nGrounding means you associate pieces of texts (called \"spans\") with those specific tool results that support them (called \"sources\"). And you use a pair of tags \"[object Object]\" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as \"{tool_call_id}:[{list of result indices}]\", before they are joined together by \",\". E.g., \"[object Object]pip install -U "huggingface_hub[cli]"huggingface-cli download Darkhn-Quants-3/Command-A-111B-Animus-V13.0-EXL3 --revision "6.0bpw_H8" --local-dir ./Command-A-111B-Animus-V13.0-EXL3.json file below and import it into SillyTavern's sampler presets menu.*He walked across the room and stared out the window.**-I wonder what she's thinking.-*Alex (Curious): "What do you see out there?"