#syntax=ghcr.io/sozercan/aikit:latest

apiVersion: v1alpha1

debug: true

runtime: cuda

models:

- name: llama-3.1-8b-instruct

source: https://huggingface.co/QuantFactory/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf

sha256: "6d86fb9d2910178f5c744234fdf91910e033ef7b03c5e23dcc6d25e98687e5fa"

promptTemplates:

- name: chatMsg

template: |

<|start_header_id|>{{if eq .RoleName \"assistant\"}}assistant{{else if eq .RoleName \"system\"}}system{{else if eq .RoleName \"tool\"}}tool{{else if eq .RoleName \"user\"}}user{{end}}<|end_header_id|>

{{ if .FunctionCall -}}

Function call:

{{ else if eq .RoleName \"tool\" -}}

Function response:

{{ end -}}

{{ if .Content -}}

{{.Content -}}

{{ else if .FunctionCall -}}

{{ toJson .FunctionCall -}}

{{ end -}}

<|eot_id|>

- name: function

template: |

<|start_header_id|>system<|end_header_id|>

You have access to the following functions:

{{range .Functions}}

Use the function '{{.Name}}' to '{{.Description}}'

{{toJson .Parameters}}

{{end}}

Think very carefully before calling functions.

If a you choose to call a function ONLY reply in the following format with no prefix or suffix:

<function=example_function_name>{{`{{\"example_name\": \"example_value\"}}`}}</function>

Reminder:

- If looking for real time information use relevant functions before falling back to searching on internet

- Function calls MUST follow the specified format, start with <function= and end with </function>

- Required parameters MUST be specified

- Only call one function at a time

- Put the entire function call reply on one line

<|eot_id|>

{{.Input }}

<|start_header_id|>assistant<|end_header_id|>

- name: chat

template: |

{{.Input }}

<|start_header_id|>assistant<|end_header_id|>

- name: completion

{{.Input}}

config: |

- name: llama-3.1-8b-instruct

backend: llama

function:

disable_no_action: true

grammar:

disable: true

response_regex:

- <function=(?P<name>\w+)>(?P<arguments>.*)</function>

parameters:

model: Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf

context_size: 8192

f16: true

template:

chat_message: \"chatMsg\"

function: \"function\"

chat: \"chat\"

completion: \"completion\"

stopwords:

- <|im_end|>

- <dummy32000>

- \"<|eot_id|>\"

- <|end_of_text|>