Modelfile-llama3.1

#  ollama create reflection-llama-3.1-70b:Q4_K_M -f modelfiles/Modelfile-llama3.1

#  FROM ../llama-3-1-8b-smcleod-golang-coder-v3.etf16-Q8_0.gguf
FROM ../Reflection-Llama-3.1-70B-q4_k_m.gguf


#  template version 948af2743fc7 2024-09-18 (with my spelling fix for 'original')
TEMPLATE """{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{- if .System }}

{{ .System }}
{{- end }}
{{- if .Tools }}

Cutting Knowledge Date: December 2023

When you receive a tool call response, use the output to format an answer to the orginal user question.

You are a helpful assistant with tool calling capabilities.
{{- 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.

{{ range $.Tools }}
{{- . }}
{{ end }}
Question: {{ .Content }}<|eot_id|>
{{- else }}

{{ .Content }}<|eot_id|>
{{- end }}{{ 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 }}
{{- end }}{{ if not $last }}<|eot_id|>{{ 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 }}"""


PARAMETER num_ctx 32768
#  PARAMETER num_batch 64

PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"


## For codegen ##
#  PARAMETER temperature 0.3
#  PARAMETER top_p 0.8

#  PARAMETER presence_penalty 0.2
#  PARAMETER frequency_penalty 0.2
#  PARAMETER repeat_last_n 50


### min_p sampling ##
# min_p works best with a bit of temperature
PARAMETER temperature 0.2
# 1.0 disables top_p, so we can use min_p
PARAMETER top_p 1.0
PARAMETER min_p 0.9
### min_p sampling ##