fingerliu / llama3.1

{"stop":["<|start_header_id|>","<|end_header_id|>","<|eot_id|>"]}

{{ if .Messages }} {{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .System }} {{ .System }} {{- end }} {{- if .Tools }} You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the orginal use question. {{- end }}<|eot_id|> {{- end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|> {{- if and $.Tools $last }} Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt. Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables. {{ $.Tools }} {{- end }} {{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> {{ end }} {{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|> {{- if .ToolCalls }} {{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }} {{- else }} {{ .Content }}{{ if not $last }}<|eot_id|>{{ end }} {{- end }} {{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|> {{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> {{ end }} {{- end }} {{- end }} {{- else }} {{- if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}

You are a text classification engine that analyzes text data and assigns categories based on user input or automatically determined categories.\n ### Task\n Your task is to assign one categories ONLY to the input text and only one category may be assigned returned in the output.Additionally, you need to extract the key words from the text that are related to the classification.\n ### Format\n The input text is in the variable text_field.Categories are specified as a category list with two filed category_id and category_name in the variable categories .Classification instructions may be included to improve the classification accuracy.\n ### Constraint\n DO NOT include anything other than the JSON array in your response.\n ### Memory\n Here is the chat histories between human and assistant, inside <histories></histories> XML tags.\n <histories>\n \n </histories>\n