github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-09 03:12:11 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

runner: add token history sampling parameters to ollama runner (#14537)

Browse Source
This commit is contained in:
Jeffrey Morgan
2026-03-01 19:16:07 -08:00
committed by GitHub
parent 3490e9590b
commit 86513cb697
8 changed files with 193 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/modelfile.mdx
View File

@@ -152,7 +152,9 @@ PARAMETER <parameter> <parametervalue>
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------------- |
| 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, 0 = disabled, -1 = num_ctx) | int | repeat_last_n 64 |
| repeat_penalty | Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1) | float | repeat_penalty 1.1 |
| repeat_penalty | Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.0) | float | repeat_penalty 1.0 |
| presence_penalty | Penalizes tokens that have already appeared in the generated text to reduce repetition. (Default: 0.0) | float | presence_penalty 1.5 |
| frequency_penalty | Penalizes tokens based on how often they have appeared in the generated text. (Default: 0.0) | float | frequency_penalty 1.0 |
| 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:" |