lucas2024 / karakuri-lm-8x7b-instruct-v0.1

llama

Q5_K_M

2

32

8

1e-05

32

32768

4096

8

2

14336

128

1e+06

32128

{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\'s needs as best you can, which will be wide-ranging.\n\n## Style Guide\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# System Instructions' }}{{ ' ## Basic Rules' }}{{ ' You are KARAKURI LM, a powerful conversational AI trained by KARAKURI to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ ' # User Instructions' }}{{ ' ' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{% set helpfulness = message['helpfulness']|string or '4' %}{% set correctness = message['correctness']|string or '4' %}{% set coherence = message['coherence']|string or '4' %}{% set complexity = message['complexity']|string or '4' %}{% set verbosity = message['verbosity']|string or '4' %}{% set quality = message['quality']|string or '4' %}{% set toxicity = message['toxicity']|string or '0' %}{% set humor = message['humor']|string or '0' %}{% set creativity = message['creativity']|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{{ content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ ' Document: ' }}{{ loop.index0 }} {% for key, value in document.items() %}{{ key }}: {{value}} {% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Write a detailed, high-quality and natural response to the user\'s last input. Use the retrieved documents to help you.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{% set helpfulness = helpfulness|string or '4' %}{% set correctness = correctness|string or '4' %}{% set coherence = coherence|string or '4' %}{% set complexity = complexity|string or '4' %}{% set verbosity = verbosity|string or '4' %}{% set quality = quality|string or '4' %}{% set toxicity = toxicity|string or '0' %}{% set humor = humor|string or '0' %}{% set creativity = creativity|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{% endif %}

{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\'s needs as best you can, which will be wide-ranging.\n\n## Style Guide\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# System Instructions' }}{{ ' ## Basic Rules' }}{{ ' You are KARAKURI LM, a powerful conversational AI trained by KARAKURI to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ ' # User Instructions' }}{{ ' ' + system_message }}{{' ## Available Tools Here is a list of tools that you have available to you: '}}{{ '```json ' }}{{ tools|tojson(indent=2) }}{{ ' ```' }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{% set helpfulness = message['helpfulness']|string or '4' %}{% set correctness = message['correctness']|string or '4' %}{% set coherence = message['coherence']|string or '4' %}{% set complexity = message['complexity']|string or '4' %}{% set verbosity = message['verbosity']|string or '4' %}{% set quality = message['quality']|string or '4' %}{% set toxicity = message['toxicity']|string or '0' %}{% set humor = message['humor']|string or '0' %}{% set creativity = message['creativity']|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{{ content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \'Action:\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example: ```json [ { "tool_name": title of the tool in the specification, "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters } ]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{% set helpfulness = helpfulness|string or '4' %}{% set correctness = correctness|string or '4' %}{% set coherence = coherence|string or '4' %}{% set complexity = complexity|string or '4' %}{% set verbosity = verbosity|string or '4' %}{% set quality = quality|string or '4' %}{% set toxicity = toxicity|string or '0' %}{% set humor = humor|string or '0' %}{% set creativity = creativity|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{% endif %}

[rag tool_use]

true

false

1

32001

llama

default

[-1000 -1000 -1000 -1000 -1000 ...]

[3 3 1 6 6 ...]

[<unk> <s> </s> <0x00> <0x01> ...]

0