ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Hide non-supported sampling controls for local safetensors (PR #5711)

Browse source 
The local non-external GGUF path (llama-server) accepts frequency_penalty,
seed, stop and parallel_tool_calls, but the safetensors / HF transformers
worker has no equivalent kwargs and silently drops them. Showing the
controls there has been confusing reviewers: the UI promises a knob that
does nothing.

Gate frequencyPenalty / seed / stop / parallelToolCalls on `isGguf` for
non-external local models so safetensors sessions only show controls the
backend actually honours. External-provider gating is unchanged.

Stale persisted values from a prior GGUF session are still sent on the
wire but the safetensors worker keeps absorbing them via **_unused, so
this is a presentation-only change with no behaviour difference.
This commit is contained in:
Daniel Han 2026-05-24 16:34:14 +00:00
commit 9cd730130e
1 changed files with 20 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

28
studio/frontend/src/features/chat/chat-settings-sheet.tsx
View file

@ -407,10 +407,18 @@ export function ChatSettingsPanel({
externalProviderType = null,
onReloadModel,
}: ChatSettingsPanelProps) {
const isMobile = useIsMobile();
const isGguf = useChatRuntimeStore((s) => s.activeGgufVariant) != null;
// For non-external (local) models we show every knob — providerCapabilities
// is only consulted when `isExternalModel` is true. An external model with an
// unknown provider falls back to the OpenAI-compat shape via
// getProviderCapabilities, so these flags never undercount support.
// GGUF (llama-server) honours frequency_penalty/seed/stop/parallel_tool_calls;
// the safetensors / HF transformers path does not, so we hide those toggles
// on local non-GGUF backends to keep the UI honest. Anything still set in
// params from a prior GGUF session is harmlessly ignored by the safetensors
// worker, so this is purely a presentation gate.
const localSamplerSupportsExtras = !isExternalModel ? isGguf : true;
const showTemperature =
!isExternalModel || Boolean(providerCapabilities?.temperature);
const showTopP = !isExternalModel || Boolean(providerCapabilities?.topP);
@ -420,21 +428,25 @@ export function ChatSettingsPanel({
!isExternalModel || Boolean(providerCapabilities?.repetitionPenalty);
const showPresencePenalty =
!isExternalModel || Boolean(providerCapabilities?.presencePenalty);
const showFrequencyPenalty =
!isExternalModel || Boolean(providerCapabilities?.frequencyPenalty);
const showSeed = !isExternalModel || Boolean(providerCapabilities?.seed);
const showStop = !isExternalModel || Boolean(providerCapabilities?.stop);
const showFrequencyPenalty = isExternalModel
? Boolean(providerCapabilities?.frequencyPenalty)
: localSamplerSupportsExtras;
const showSeed = isExternalModel
? Boolean(providerCapabilities?.seed)
: localSamplerSupportsExtras;
const showStop = isExternalModel
? Boolean(providerCapabilities?.stop)
: localSamplerSupportsExtras;
const showServiceTier =
isExternalModel && Boolean(providerCapabilities?.serviceTier);
const showParallelToolCalls =
!isExternalModel || Boolean(providerCapabilities?.parallelToolCalls);
const showParallelToolCalls = isExternalModel
? Boolean(providerCapabilities?.parallelToolCalls)
: localSamplerSupportsExtras;
// Per-provider stop cap from provider-capabilities.ts; backend
// re-trims on the wire if a stale UI sends more than the upstream
// accepts.
const stopMaxEntries = getProviderStopMax(externalProviderType);
const serviceTierOptions = getServiceTierOptions(externalProviderType);
const isMobile = useIsMobile();
const isGguf = useChatRuntimeStore((s) => s.activeGgufVariant) != null;
const hasModelContent =
!isExternalModel && (isGguf || Boolean(params.checkpoint));
const speculativeType = useChatRuntimeStore((s) => s.speculativeType);