feat(ui): Ollama parameter catalog (defaults/ranges/help) as single source of truth
This commit is contained in:
iamdoubz committed
1 parent
b980c833c4
commit
a0ce2e2321
1 file changed
+317
@@ -0,0 +1,317 @@
|
||||
// Ollama advanced `options` parameters (T5.2) — the single source of truth that
|
||||
// drives the Settings ▸ AI advanced form: rendering, defaults, per-field reset,
|
||||
// and only-send-if-changed. System prompt / think / keep_alive are top-level
|
||||
// request fields handled separately in the UI; everything here goes in `options`.
|
||||
//
|
||||
// Defaults + ranges per the Ollama Modelfile/API reference.
|
||||
|
||||
export type OllamaGroup = "sampling" | "repetition" | "mirostat" | "context" | "hardware";
|
||||
|
||||
export interface OllamaOption {
|
||||
key: string;
|
||||
group: OllamaGroup;
|
||||
label: string;
|
||||
kind: "number" | "bool" | "enum" | "tags";
|
||||
/** Undefined = "auto" (no fixed default): the field is empty until set. */
|
||||
default?: number | boolean;
|
||||
min?: number;
|
||||
max?: number;
|
||||
step?: number;
|
||||
enumOptions?: { value: number; label: string }[];
|
||||
help: string;
|
||||
/** Dimmed unless Mirostat is enabled (mirostat != 0). */
|
||||
needsMirostat?: boolean;
|
||||
}
|
||||
|
||||
export const OLLAMA_OPTIONS: OllamaOption[] = [
|
||||
// ── Sampling ──────────────────────────────────────────────────────────────
|
||||
{
|
||||
key: "temperature",
|
||||
group: "sampling",
|
||||
label: "Temperature",
|
||||
kind: "number",
|
||||
default: 0.8,
|
||||
min: 0,
|
||||
max: 2,
|
||||
step: 0.05,
|
||||
help: "Randomness / creativity. Higher is more creative.",
|
||||
},
|
||||
{
|
||||
key: "top_k",
|
||||
group: "sampling",
|
||||
label: "Top K",
|
||||
kind: "number",
|
||||
default: 40,
|
||||
min: 0,
|
||||
max: 200,
|
||||
step: 1,
|
||||
help: "Sample only from the K most likely tokens.",
|
||||
},
|
||||
{
|
||||
key: "top_p",
|
||||
group: "sampling",
|
||||
label: "Top P",
|
||||
kind: "number",
|
||||
default: 0.9,
|
||||
min: 0,
|
||||
max: 1,
|
||||
step: 0.05,
|
||||
help: "Nucleus sampling cumulative probability.",
|
||||
},
|
||||
{
|
||||
key: "min_p",
|
||||
group: "sampling",
|
||||
label: "Min P",
|
||||
kind: "number",
|
||||
default: 0.0,
|
||||
min: 0,
|
||||
max: 1,
|
||||
step: 0.01,
|
||||
help: "Minimum probability relative to the top token.",
|
||||
},
|
||||
{
|
||||
key: "typical_p",
|
||||
group: "sampling",
|
||||
label: "Typical P",
|
||||
kind: "number",
|
||||
default: 1.0,
|
||||
min: 0,
|
||||
max: 1,
|
||||
step: 0.05,
|
||||
help: "Locally-typical sampling.",
|
||||
},
|
||||
{
|
||||
key: "tfs_z",
|
||||
group: "sampling",
|
||||
label: "Tail-free (tfs_z)",
|
||||
kind: "number",
|
||||
default: 1.0,
|
||||
min: 0,
|
||||
max: 2,
|
||||
step: 0.05,
|
||||
help: "Tail-free sampling. 1.0 disables it (legacy).",
|
||||
},
|
||||
{
|
||||
key: "seed",
|
||||
group: "sampling",
|
||||
label: "Seed",
|
||||
kind: "number",
|
||||
default: 0,
|
||||
min: 0,
|
||||
step: 1,
|
||||
help: "Fixed seed → reproducible output. 0 = random.",
|
||||
},
|
||||
{
|
||||
key: "num_predict",
|
||||
group: "sampling",
|
||||
label: "Max tokens (num_predict)",
|
||||
kind: "number",
|
||||
default: -1,
|
||||
min: -2,
|
||||
step: 1,
|
||||
help: "Max tokens to generate. -1 = unlimited, -2 = fill context.",
|
||||
},
|
||||
|
||||
// ── Repetition ────────────────────────────────────────────────────────────
|
||||
{
|
||||
key: "repeat_penalty",
|
||||
group: "repetition",
|
||||
label: "Repeat penalty",
|
||||
kind: "number",
|
||||
default: 1.1,
|
||||
min: 0,
|
||||
max: 2,
|
||||
step: 0.05,
|
||||
help: "How strongly to penalize repetition.",
|
||||
},
|
||||
{
|
||||
key: "repeat_last_n",
|
||||
group: "repetition",
|
||||
label: "Repeat lookback",
|
||||
kind: "number",
|
||||
default: 64,
|
||||
min: -1,
|
||||
step: 1,
|
||||
help: "Tokens to look back for repetition. 0 = off, -1 = num_ctx.",
|
||||
},
|
||||
{
|
||||
key: "presence_penalty",
|
||||
group: "repetition",
|
||||
label: "Presence penalty",
|
||||
kind: "number",
|
||||
default: 0.0,
|
||||
min: -2,
|
||||
max: 2,
|
||||
step: 0.1,
|
||||
help: "Penalize tokens that already appeared.",
|
||||
},
|
||||
{
|
||||
key: "frequency_penalty",
|
||||
group: "repetition",
|
||||
label: "Frequency penalty",
|
||||
kind: "number",
|
||||
default: 0.0,
|
||||
min: -2,
|
||||
max: 2,
|
||||
step: 0.1,
|
||||
help: "Penalize tokens by how often they appear.",
|
||||
},
|
||||
{
|
||||
key: "penalize_newline",
|
||||
group: "repetition",
|
||||
label: "Penalize newlines",
|
||||
kind: "bool",
|
||||
default: true,
|
||||
help: "Apply the repeat penalty to newline tokens.",
|
||||
},
|
||||
|
||||
// ── Mirostat ──────────────────────────────────────────────────────────────
|
||||
{
|
||||
key: "mirostat",
|
||||
group: "mirostat",
|
||||
label: "Mirostat",
|
||||
kind: "enum",
|
||||
default: 0,
|
||||
enumOptions: [
|
||||
{ value: 0, label: "Off" },
|
||||
{ value: 1, label: "Mirostat 1" },
|
||||
{ value: 2, label: "Mirostat 2" },
|
||||
],
|
||||
help: "Adaptive perplexity control.",
|
||||
},
|
||||
{
|
||||
key: "mirostat_tau",
|
||||
group: "mirostat",
|
||||
label: "Mirostat τ (tau)",
|
||||
kind: "number",
|
||||
default: 5.0,
|
||||
min: 0,
|
||||
max: 10,
|
||||
step: 0.1,
|
||||
help: "Balance of coherence vs diversity.",
|
||||
needsMirostat: true,
|
||||
},
|
||||
{
|
||||
key: "mirostat_eta",
|
||||
group: "mirostat",
|
||||
label: "Mirostat η (eta)",
|
||||
kind: "number",
|
||||
default: 0.1,
|
||||
min: 0,
|
||||
max: 1,
|
||||
step: 0.01,
|
||||
help: "How fast it adapts to feedback.",
|
||||
needsMirostat: true,
|
||||
},
|
||||
|
||||
// ── Context & session ─────────────────────────────────────────────────────
|
||||
{
|
||||
key: "num_ctx",
|
||||
group: "context",
|
||||
label: "Context size (num_ctx)",
|
||||
kind: "number",
|
||||
default: 4096,
|
||||
min: 256,
|
||||
step: 256,
|
||||
help: "Context window in tokens.",
|
||||
},
|
||||
{
|
||||
key: "num_keep",
|
||||
group: "context",
|
||||
label: "Keep tokens (num_keep)",
|
||||
kind: "number",
|
||||
default: 4,
|
||||
min: 0,
|
||||
step: 1,
|
||||
help: "Tokens kept from the start of the prompt when truncating.",
|
||||
},
|
||||
{
|
||||
key: "stop",
|
||||
group: "context",
|
||||
label: "Stop sequences",
|
||||
kind: "tags",
|
||||
help: "Comma-separated strings that end generation.",
|
||||
},
|
||||
|
||||
// ── Runtime & hardware (rarely needed) ────────────────────────────────────
|
||||
{
|
||||
key: "num_batch",
|
||||
group: "hardware",
|
||||
label: "Batch size (num_batch)",
|
||||
kind: "number",
|
||||
default: 512,
|
||||
min: 1,
|
||||
step: 1,
|
||||
help: "Prompt processing batch size.",
|
||||
},
|
||||
{
|
||||
key: "num_gpu",
|
||||
group: "hardware",
|
||||
label: "GPU layers (num_gpu)",
|
||||
kind: "number",
|
||||
min: 0,
|
||||
step: 1,
|
||||
help: "Layers to offload to the GPU. Blank = auto.",
|
||||
},
|
||||
{
|
||||
key: "main_gpu",
|
||||
group: "hardware",
|
||||
label: "Main GPU",
|
||||
kind: "number",
|
||||
default: 0,
|
||||
min: 0,
|
||||
step: 1,
|
||||
help: "Which GPU to use for a single-GPU offload.",
|
||||
},
|
||||
{
|
||||
key: "num_thread",
|
||||
group: "hardware",
|
||||
label: "CPU threads (num_thread)",
|
||||
kind: "number",
|
||||
min: 1,
|
||||
step: 1,
|
||||
help: "Threads for computation. Blank = auto.",
|
||||
},
|
||||
{
|
||||
key: "low_vram",
|
||||
group: "hardware",
|
||||
label: "Low VRAM",
|
||||
kind: "bool",
|
||||
default: false,
|
||||
help: "Reduce VRAM use at the cost of speed.",
|
||||
},
|
||||
{
|
||||
key: "numa",
|
||||
group: "hardware",
|
||||
label: "NUMA",
|
||||
kind: "bool",
|
||||
default: false,
|
||||
help: "Enable NUMA support.",
|
||||
},
|
||||
{
|
||||
key: "use_mmap",
|
||||
group: "hardware",
|
||||
label: "Use mmap",
|
||||
kind: "bool",
|
||||
default: true,
|
||||
help: "Memory-map the model file.",
|
||||
},
|
||||
{
|
||||
key: "use_mlock",
|
||||
group: "hardware",
|
||||
label: "Use mlock",
|
||||
kind: "bool",
|
||||
default: false,
|
||||
help: "Lock the model in RAM (no swap).",
|
||||
},
|
||||
];
|
||||
|
||||
export const THINK_OPTIONS = ["off", "low", "medium", "high", "max"] as const;
|
||||
|
||||
export const OLLAMA_GROUP_LABELS: Record<OllamaGroup, string> = {
|
||||
sampling: "Sampling",
|
||||
repetition: "Repetition",
|
||||
mirostat: "Mirostat",
|
||||
context: "Context & session",
|
||||
hardware: "Runtime & hardware",
|
||||
};
|
||||
Reference in new issue
Block a user