api: stop applying repeat_penalty 1.1 to models that don't set one

Request options are the model's published parameters and the request's
own options layered over the server defaults, so the default
repeat_penalty of 1.1 reaches every model whose parameters leave it
unset. No maker of the library's current models recommends 1.1: their
generation configs either omit the penalty, meaning 1.0, or pin 1.05.
llama.cpp dropped the same 1.1 default in 2024; vLLM, SGLang, and
transformers apply no penalty. An always-on penalty also distorts
output that legitimately repeats tokens, such as code, JSON, and long
reasoning traces.

The penalty is especially costly for speculative decoding, where
drafts are proposed without it: the penalized target rejects drafted
tokens and the depth controller backs off. On muse-glimmer 30B (DFlash
on M5 Max, HumanEval) the 1.1 default costs 13-16% of end-to-end
throughput at greedy and temperature 1 alike, and drops prose
acceptance at temperature 0.8 from 0.44 to 0.30. On qwen3.6-35B it
cuts the mean accepted draft length from 4.3 to 3.5 tokens and makes
the controller stop speculating on prose.

Defaulting to 1.0 disables the penalty unless a model's parameters or
the request set one. Across the library:

- qwen3, qwen3.6, and qwen3-coder pin their own values (1.0, 1.0, and
  Qwen's recommended 1.05) and are unchanged.
- Everything else local now matches its maker's no-penalty
  recommendation, including gemma2 through gemma4, muse-glimmer, both
  laguna 2.1 models, qwen3.5 (previously 1.1 stacked on its
  presence_penalty of 1.5), gpt-oss, deepseek-r1 and v3.1, the
  nemotron family, granite4, the mistral and llama3/llama4 families,
  phi4, glm4, llava, and devstral.
- qwen2.5 recommends 1.05 but ships no parameters, so it moves from
  1.1 to 1.0 and still needs a parameters layer to conform.
- Cloud models (kimi-k3, deepseek-v4-flash) never receive these
  defaults.

Small older models may repeat themselves more without the penalty
masking it; the remedy is a per-model parameter, not a penalty applied
to every model.

api/types.go

@@ -1105,7 +1105,7 @@ func DefaultOptions() Options {
 		TopP:             0.9,
 		TypicalP:         1.0,
 		RepeatLastN:      64,
-		RepeatPenalty:    1.1,
+		RepeatPenalty:    1.0,
 		PresencePenalty:  0.0,
 		FrequencyPenalty: 0.0,
 		Seed:             -1,

docs/modelfile.mdx

@@ -148,7 +148,7 @@ 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, 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:" |