ModelfileOllama

FROM NeuralNet/openchat-3.6

# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 0.5

# sets the context window size to 8192, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 8192

# tokens to generate set to 4096 (max)
PARAMETER num_predict 4096

# set system
SYSTEM "You are an AI assistant created by NeuralNet, a company specialized in AI solutions, your answer are clear and consice"

# template OpenChat3.6
TEMPLATE "{{ if .System }}<|begin_of_text|><|start_header_id|>System<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>GPT4 Correct User<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>GPT4 Correct Assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"