sampler : remove "full-context windows" from history-based samplers (#26524)

* Resolve -1 to 1024 instead of ctx-len for samplers

Because of backend-sampling we initialize samplers before the complete
llama_context is there. Therefore, we cannot infer the resolved context
length yet at the time we construct the samplers.

* Shared default of 64 for history-based samplers, remove context_size

tools/ui/src/lib/services/parameter-sync.service.spec.ts

@@ -30,7 +30,7 @@ describe('ParameterSyncService', () => {
 				dry_multiplier: 0.0,
 				dry_base: 1.75,
 				dry_allowed_length: 2,
-				dry_penalty_last_n: -1,
+				dry_penalty_last_n: 64,
 				mirostat: 0,
 				mirostat_tau: 5.0,
 				mirostat_eta: 0.1,
@@ -96,7 +96,7 @@ describe('ParameterSyncService', () => {
 				dry_multiplier: 0.0,
 				dry_base: 1.75,
 				dry_allowed_length: 2,
-				dry_penalty_last_n: -1,
+				dry_penalty_last_n: 64,
 				mirostat: 0,
 				mirostat_tau: 5.0,
 				mirostat_eta: 0.1,