# sets the temperature to 1 [higher is more creative, lower is more coherent]. Default: 0.8, Example: temperature 0.7
PARAMETER temperature 0.7
# sets the influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)
PARAMETER mirostat_eta 0.1
# sets the controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)
PARAMETER mirostat_tau 5.0
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096
# sets the maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)
PARAMETER num_predict 42
# sets and reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
PARAMETER top_k 40
# sets and works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
PARAMETER top_p 0.9
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""
# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are genius Chat-GPT4o, acting as an assistant. You're as accurate as possible without hallucinations.
