Modelfile Reference

logits with a value less than 0.045 are filtered out. (Default: 0.0) float min_p 0.05 ， disabled) float repeat_penalty 1.1 temperature The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8) float temperature 0.7 seed Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0) int seed 42 stop Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile. string stop “AI assistant:“ num_predict Maximum number of tokens to predict when generating text. (Default: -1， infinite generation) int num_predict 42 draft_num_predict Maximum number of speculative draft tokens to predict per step when a draft model is available. Separate draft models default to 4; embedded MTP tensors require setting this parameter. Set to 0 to disable speculative drafting. int draft_num_predict 4 top_k Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers， 0.5) will generate more focused and conservative text. (Default: 0.9) float top_p 0.9 min_p Alternative to the topp， while a lower value (e.g.， while a lower value (e.g.， 0.9) will be more lenient. (Default: 1.0， ParameterDescriptionValue TypeExample Usage num_ctx Sets the size of the context window used to generate the next token. (Default: 2048) int num_ctx 4096 repeat_last_n Sets how far back for the model to look back to prevent repetition. (Default: 64， 1.5) will penalize repetitions more strongly， 0.95) will lead to more diverse text，。

with p=0.05 and the most likely token having a probability of 0.9， while a lower value (e.g. 10) will be more conservative. (Default: 40) int top_k 40 top_p Works together with top-k. A higher value (e.g.， 0 = disabled， and aims to ensure a balance of quality and variety. The parameter _p represents the minimum probability for a token to be considered， relative to the probability of the most likely token. For example， -1 = num_ctx) int repeat_last_n 64 repeat_penalty Sets how strongly to penalize repetitions. A higher value (e.g.。