node-llama-cpp 3.0.0-beta.9 → 3.0.0

package/dist/config.js.map

@@ -1 +1 @@
-{"version":3,"file":"config.js","sourceRoot":"","sources":["../src/config.ts"],"names":[],"mappings":"AAAA,OAAO,EAAC,aAAa,EAAC,MAAM,KAAK,CAAC;AAClC,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,OAAO,MAAM,SAAS,CAAC;AAC9B,OAAO,MAAM,MAAM,SAAS,CAAC;AAC7B,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,EAAC,wBAAwB,EAAC,MAAM,2CAA2C,CAAC;AACnF,OAAO,EAAC,aAAa,EAAE,mBAAmB,EAAC,MAAM,qBAAqB,CAAC;AAEvE,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAE/D,MAAM,GAAG,GAAG,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;AAGrC,MAAM,CAAC,MAAM,cAAc,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,OAAO,CAAC,CAAC;AAClE,MAAM,CAAC,MAAM,wBAAwB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,YAAY,CAAC,CAAC;AAChF,MAAM,CAAC,MAAM,0BAA0B,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,WAAW,CAAC,CAAC;AAClF,MAAM,CAAC,MAAM,4BAA4B,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,aAAa,CAAC,CAAC;AACrF,MAAM,CAAC,MAAM,0BAA0B,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,OAAO,EAAE,UAAU,CAAC,CAAC;AAC1F,MAAM,CAAC,MAAM,iBAAiB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,WAAW,CAAC,CAAC;AACxE,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,WAAW,EAAE,UAAU,CAAC,CAAC;AAC5F,MAAM,CAAC,MAAM,qBAAqB,GAAG,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE,gBAAgB,EAAE,IAAI,CAAC,EAAE,EAAE,CAAC,CAAC;AACzF,MAAM,CAAC,MAAM,0BAA0B,GAAG,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,EAAE,mCAAmC,CAAC,CAAC;AACvG,MAAM,CAAC,MAAM,qBAAqB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,gBAAgB,CAAC,CAAC;AACjF,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,4BAA4B,CAAC,CAAC;AACjG,MAAM,CAAC,MAAM,6BAA6B,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,qBAAqB,CAAC,CAAC;AAC9F,MAAM,CAAC,MAAM,2BAA2B,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,mBAAmB,CAAC,CAAC;AAC1F,MAAM,CAAC,MAAM,cAAc,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AACjE,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AAC5E,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AAC5E,MAAM,CAAC,MAAM,qBAAqB,GAAG,qBAAqB,CAAC;AAC3D,MAAM,CAAC,MAAM,UAAU,GAAG,SAAS,CAAC;AACpC,MAAM,CAAC,MAAM,yBAAyB,GAAG,qBAAqB,CAAC;AAC/D,MAAM,CAAC,MAAM,sBAAsB,GAAG,MAAM,wBAAwB,EAAE,CAAC;AAEvE,MAAM,CAAC,MAAM,IAAI,GAAG,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC;KAC5B,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,yBAAyB,GAAG,GAAG,CAAC,GAAG,CAAC,qBAAqB,CAAC;KAClE,OAAO,CAAC,yBAAyB,CAAC;KAClC,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,sBAAsB,GAAG,GAAG,CAAC,GAAG,CAAC,6BAA6B,CAAC;KACvE,OAAO,CAAC,sBAAsB,CAAC;KAC/B,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,2BAA2B,GAAG,GAAG,CAAC,GAAG,CAAC,sBAAsB,CAAC;KACrE,OAAO,CAAC,CAAC,OAAO,CAAC,QAAQ,KAAK,QAAQ,IAAI,OAAO,CAAC,IAAI,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC;KACrF,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,0BAA0B,GAAG,GAAG,CAAC,GAAG,CAAC,qBAAqB,CAAC;KACnE,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,wBAAwB,GAAG,GAAG,CAAC,GAAG,CAAC,0BAA0B,CAAC;KACtE,OAAO,CAAC,aAAa,CAAC,KAAK,CAAC;KAC5B,MAAM,CAAC,mBAAmB,CAAC,CAAC;AACjC,MAAM,CAAC,MAAM,mBAAmB,GAAG,GAAG,CAAC,GAAG,CAAC,8BAA8B,CAAC;KACrE,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,2BAA2B,GAAG,GAAG,CAAC,GAAG,CAAC,oCAAoC,CAAC;KACnF,OAAO,CAAC,yBAAyB,CAAC;KAClC,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,2BAA2B,GAAG,GAAG,CAAC,GAAG,CAAC,oCAAoC,CAAC;KACnF,OAAO,CAAC,yBAAyB,CAAC;KAClC,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,8BAA8B,GAAG,8BAA8B,CAAC;AAC7E,MAAM,CAAC,MAAM,uBAAuB,GAAG,+FAA+F;IAClI,+HAA+H;IAC/H,mFAAmF,CAAC;AACxF,MAAM,CAAC,MAAM,UAAU,GAAG,gBAAgB,CAAC;AAC3C,MAAM,CAAC,MAAM,YAAY,GAAG,WAAW,CAAC;AAExC,MAAM,gBAAgB,GAAG,4CAA4C,CAAC;AACtE,MAAM,CAAC,MAAM,qBAAqB,GAAG;IACjC,IAAI,EAAE,gBAAgB,GAAG,aAAa;CAChC,CAAC"}
+{"version":3,"file":"config.js","sourceRoot":"","sources":["../src/config.ts"],"names":[],"mappings":"AAAA,OAAO,EAAC,aAAa,EAAC,MAAM,KAAK,CAAC;AAClC,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,OAAO,MAAM,SAAS,CAAC;AAC9B,OAAO,MAAM,MAAM,SAAS,CAAC;AAC7B,OAAO,EAAC,MAAM,EAAC,MAAM,QAAQ,CAAC;AAC9B,OAAO,EAAC,wBAAwB,EAAC,MAAM,2CAA2C,CAAC;AACnF,OAAO,EACH,sBAAsB,EAAE,aAAa,EAAE,mBAAmB,EAAE,0BAA0B,EAAE,+BAA+B,EAC1H,MAAM,qBAAqB,CAAC;AAE7B,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAE/D,MAAM,GAAG,GAAG,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;AAGrC,MAAM,CAAC,MAAM,cAAc,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,OAAO,CAAC,CAAC;AAClE,MAAM,CAAC,MAAM,wBAAwB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,YAAY,CAAC,CAAC;AAChF,MAAM,CAAC,MAAM,0BAA0B,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC;AAC7E,MAAM,CAAC,MAAM,4BAA4B,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,aAAa,CAAC,CAAC;AACrF,MAAM,CAAC,MAAM,0BAA0B,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,OAAO,EAAE,UAAU,CAAC,CAAC;AAC1F,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,WAAW,CAAC,CAAC;AACjF,MAAM,CAAC,MAAM,+BAA+B,GAAG,IAAI,CAAC,IAAI,CAAC,yBAAyB,EAAE,QAAQ,CAAC,CAAC;AAC9F,MAAM,CAAC,MAAM,iBAAiB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,WAAW,CAAC,CAAC;AACxE,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,WAAW,EAAE,UAAU,CAAC,CAAC;AAC5F,MAAM,CAAC,MAAM,qBAAqB,GAAG,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE,gBAAgB,EAAE,MAAM,EAAE,CAAC,CAAC;AACxF,MAAM,CAAC,MAAM,mBAAmB,GAAG,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,EAAE,iBAAiB,CAAC,CAAC;AAC9E,MAAM,CAAC,MAAM,0BAA0B,GAAG,IAAI,CAAC,IAAI,CAAC,mBAAmB,EAAE,oBAAoB,CAAC,CAAC;AAC/F,MAAM,CAAC,MAAM,kBAAkB,GAAG,IAAI,CAAC,IAAI,CAAC,mBAAmB,EAAE,QAAQ,CAAC,CAAC;AAC3E,MAAM,CAAC,MAAM,qBAAqB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,gBAAgB,CAAC,CAAC;AACjF,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,4BAA4B,CAAC,CAAC;AACjG,MAAM,CAAC,MAAM,6BAA6B,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,qBAAqB,CAAC,CAAC;AAC9F,MAAM,CAAC,MAAM,2BAA2B,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,mBAAmB,CAAC,CAAC;AAC1F,MAAM,CAAC,MAAM,cAAc,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AACjE,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AAC5E,MAAM,CAAC,MAAM,yBAAyB,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC;AAC5E,MAAM,CAAC,MAAM,qBAAqB,GAAG,wBAAwB,CAAC;AAC9D,MAAM,CAAC,MAAM,UAAU,GAAG,SAAS,CAAC;AACpC,MAAM,CAAC,MAAM,yBAAyB,GAAG,qBAAqB,CAAC;AAC/D,MAAM,CAAC,MAAM,sBAAsB,GAAG,MAAM,wBAAwB,EAAE,CAAC;AAEvE,MAAM,CAAC,MAAM,IAAI,GAAG,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC;KAC5B,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,0BAA0B,GAAG,GAAG,CAAC,GAAG,CAAC,mBAAmB,CAAC;KACjE,OAAO,CAAC,EAAE,CAAC;KACX,QAAQ,EAAE,KAAK,EAAE,CAAC;AACvB,MAAM,CAAC,MAAM,SAAS,GAAG,IAAI,IAAI,0BAA0B,CAAC;AAC5D,MAAM,CAAC,MAAM,yBAAyB,GAAG,GAAG,CAAC,GAAG,CAAC,qBAAqB,CAAC;KAClE,OAAO,CAAC,yBAAyB,CAAC;KAClC,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,sBAAsB,GAAG,GAAG,CAAC,GAAG,CAAC,6BAA6B,CAAC;KACvE,OAAO,CAAC,sBAAsB,CAAC;KAC/B,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,yBAAyB,GAAG,0BAA0B,CAC/D,GAAG,CAAC,GAAG,CAAC,oBAAoB,CAAC;KACxB,OAAO,CAAC,MAAM,CAAC;KACf,MAAM,CACH,sBAAsB;KACjB,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CACjB,MAAM,KAAK,KAAK;IACZ,CAAC,CAAC,+BAA+B;IACjC,CAAC,CAAC,CAAC,MAAM,CAAC,CACjB,CAAC,CACT,CACR,CAAC;AACF,MAAM,CAAC,MAAM,uBAAuB,GAAG,GAAG,CAAC,GAAG,CAAC,0BAA0B,CAAC;KACrE,OAAO,CAAC,aAAa,CAAC,IAAI,CAAC;KAC3B,MAAM,CAAC,mBAAmB,CAAC,CAAC;AACjC,MAAM,CAAC,MAAM,wBAAwB,GAAG,GAAG,CAAC,GAAG,CAAC,sBAAsB,CAAC;KAClE,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,mBAAmB,GAAG,GAAG,CAAC,GAAG,CAAC,8BAA8B,CAAC;KACrE,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,EAAE,CAAC;AACd,MAAM,CAAC,MAAM,2BAA2B,GAAG,GAAG,CAAC,GAAG,CAAC,oCAAoC,CAAC;KACnF,OAAO,CAAC,yBAAyB,CAAC;KAClC,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,2BAA2B,GAAG,GAAG,CAAC,GAAG,CAAC,oCAAoC,CAAC;KACnF,OAAO,CAAC,yBAAyB,CAAC;KAClC,QAAQ,EAAE,CAAC;AAChB,MAAM,CAAC,MAAM,8BAA8B,GAAG,8BAA8B,CAAC;AAC7E,MAAM,CAAC,MAAM,uBAAuB,GAAG,+FAA+F;IAClI,+HAA+H;IAC/H,4EAA4E,CAAC;AACjF,MAAM,CAAC,MAAM,UAAU,GAAG,gBAAgB,CAAC;AAC3C,MAAM,CAAC,MAAM,YAAY,GAAG,WAAW,CAAC;AAExC,kCAAkC;AAClC,4GAA4G;AAC5G,oDAAoD;AACpD,kIAAkI;AAClI,MAAM,CAAC,MAAM,oBAAoB,GAAG,KAAK,CAAC;AAE1C,MAAM,gBAAgB,GAAG,mCAAmC,CAAC;AAC7D,MAAM,mBAAmB,GAAG,gBAAgB,GAAG,MAAM,CAAC;AACtD,MAAM,CAAC,MAAM,qBAAqB,GAAG;IACjC,IAAI,EAAE,gBAAgB,GAAG,aAAa;IACtC,MAAM,EAAE,gBAAgB,GAAG,eAAe;IAC1C,GAAG,EAAE;QACD,KAAK,EAAE,mBAAmB;QAC1B,IAAI,EAAE,mBAAmB,GAAG,OAAO;QACnC,IAAI,EAAE,mBAAmB,GAAG,OAAO;QACnC,IAAI,EAAE,mBAAmB,GAAG,OAAO;QACnC,QAAQ,EAAE,mBAAmB,GAAG,WAAW;QAC3C,MAAM,EAAE,mBAAmB,GAAG,SAAS;QACvC,OAAO,EAAE;YACL,KAAK,EAAE,mBAAmB,GAAG,UAAU;YACvC,GAAG,EAAE,mBAAmB,GAAG,cAAc;YACzC,IAAI,EAAE,mBAAmB,GAAG,eAAe;YAC3C,OAAO,EAAE,mBAAmB,GAAG,kBAAkB;YACjD,QAAQ,EAAE,mBAAmB,GAAG,mBAAmB;SACtD;QACD,MAAM,EAAE;YACJ,KAAK,EAAE,mBAAmB,GAAG,SAAS;YACtC,QAAQ,EAAE,mBAAmB,GAAG,kBAAkB;YAClD,KAAK,EAAE,mBAAmB,GAAG,eAAe;YAC5C,KAAK,EAAE,mBAAmB,GAAG,eAAe;SAC/C;KACJ;CACK,CAAC;AACX,MAAM,CAAC,MAAM,0BAA0B,GAAG,SAAS,CAAC;AACpD,MAAM,CAAC,MAAM,mCAAmC,GAAG,EAAE,CAAC"}

package/dist/consts.d.ts

@@ -0,0 +1,4 @@
+export declare const maxRecentDetokenizerTokens = 3;
+export declare const UNKNOWN_UNICODE_CHAR = "\uFFFD";
+export declare const clockChar: string;
+export declare const arrowChar: string;

package/dist/consts.js

@@ -0,0 +1,11 @@
+import isUnicodeSupported from "is-unicode-supported";
+const unicodeSupported = isUnicodeSupported();
+export const maxRecentDetokenizerTokens = 3;
+export const UNKNOWN_UNICODE_CHAR = "\ufffd";
+export const clockChar = unicodeSupported
+    ? "\u25f7"
+    : "+";
+export const arrowChar = unicodeSupported
+    ? "\u276f"
+    : ">";
+//# sourceMappingURL=consts.js.map

package/dist/consts.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"consts.js","sourceRoot":"","sources":["../src/consts.ts"],"names":[],"mappings":"AAAA,OAAO,kBAAkB,MAAM,sBAAsB,CAAC;AAEtD,MAAM,gBAAgB,GAAG,kBAAkB,EAAE,CAAC;AAE9C,MAAM,CAAC,MAAM,0BAA0B,GAAG,CAAC,CAAC;AAC5C,MAAM,CAAC,MAAM,oBAAoB,GAAG,QAAQ,CAAC;AAC7C,MAAM,CAAC,MAAM,SAAS,GAAG,gBAAgB;IACrC,CAAC,CAAC,QAAQ;IACV,CAAC,CAAC,GAAG,CAAC;AACV,MAAM,CAAC,MAAM,SAAS,GAAG,gBAAgB;IACrC,CAAC,CAAC,QAAQ;IACV,CAAC,CAAC,GAAG,CAAC"}

package/dist/evaluator/LlamaChat/LlamaChat.d.ts

@@ -1,34 +1,70 @@
-/// <reference types="node" />
 import { EventRelay } from "lifecycle-utils";
 import { ChatWrapper } from "../../ChatWrapper.js";
 import { LlamaContextSequence } from "../LlamaContext/LlamaContext.js";
-import { ChatHistoryItem, ChatModelFunctions, Token } from "../../types.js";
+import { ChatHistoryItem, ChatModelFunctions, LLamaContextualRepeatPenalty, Token } from "../../types.js";
 import { GbnfJsonSchemaToType } from "../../utils/gbnfJson/types.js";
 import { LlamaGrammar } from "../LlamaGrammar.js";
+import { LlamaText, LlamaTextJSON } from "../../utils/LlamaText.js";
 import { EvaluationPriority } from "../LlamaContext/types.js";
+import { TokenBias } from "../TokenBias.js";
 export type LlamaChatOptions = {
     contextSequence: LlamaContextSequence;
     /** `"auto"` is used by default */
     chatWrapper?: "auto" | ChatWrapper;
-    /** Automatically dispose the sequence when the session is disposed */
+    /**
+     * Automatically dispose the sequence when the session is disposed
+     *
+     * Defaults to `false`.
+     */
     autoDisposeSequence?: boolean;
 };
 export type LLamaChatGenerateResponseOptions<Functions extends ChatModelFunctions | undefined = undefined> = {
+    /**
+     * Called as the model generates a response with the generated text chunk.
+     *
+     * Useful for streaming the generated response as it's being generated.
+     */
+    onTextChunk?: (text: string) => void;
+    /**
+     * Called as the model generates a response with the generated tokens.
+     *
+     * Preferably, you'd want to use `onTextChunk` instead of this.
+     */
     onToken?: (tokens: Token[]) => void;
     signal?: AbortSignal;
+    /**
+     * When a response already started being generated and then the signal is aborted,
+     * the generation will stop and the response will be returned as is instead of throwing an error.
+     *
+     * Defaults to `false`.
+     */
+    stopOnAbortSignal?: boolean;
     maxTokens?: number;
     /**
      * Temperature is a hyperparameter that controls the randomness of the generated text.
      * It affects the probability distribution of the model's output tokens.
+     *
      * A higher temperature (e.g., 1.5) makes the output more random and creative,
      * while a lower temperature (e.g., 0.5) makes the output more focused, deterministic, and conservative.
+     *
      * The suggested temperature is 0.8, which provides a balance between randomness and determinism.
+     *
      * At the extreme, a temperature of 0 will always pick the most likely next token, leading to identical outputs in each run.
      *
      * Set to `0` to disable.
      * Disabled by default (set to `0`).
      */
     temperature?: number;
+    /**
+     * From the next token candidates, discard the percentage of tokens with the lowest probability.
+     * For example, if set to `0.05`, 5% of the lowest probability tokens will be discarded.
+     * This is useful for generating more high-quality results when using a high temperature.
+     * Set to a value between `0` and `1` to enable.
+     *
+     * Only relevant when `temperature` is set to a value greater than `0`.
+     * Disabled by default.
+     */
+    minP?: number;
     /**
      * Limits the model to consider only the K most likely next tokens for sampling at each step of sequence generation.
      * An integer number between `1` and the size of the vocabulary.
@@ -46,17 +82,36 @@ export type LLamaChatGenerateResponseOptions<Functions extends ChatModelFunction
      * Only relevant when `temperature` is set to a value greater than `0`.
      */
     topP?: number;
+    /**
+     * Used to control the randomness of the generated text.
+     *
+     * Change the seed to get different results.
+     *
+     * Only relevant when using `temperature`.
+     */
+    seed?: number;
     /**
      * Trim whitespace from the end of the generated text
-     * Disabled by default.
+     *
+     * Defaults to `false`.
      */
     trimWhitespaceSuffix?: boolean;
-    repeatPenalty?: false | LLamaChatRepeatPenalty;
+    repeatPenalty?: false | LLamaContextualRepeatPenalty;
+    /**
+     * Adjust the probability of tokens being generated.
+     * Can be used to bias the model to generate tokens that you want it to lean towards,
+     * or to avoid generating tokens that you want it to avoid.
+     */
+    tokenBias?: TokenBias | (() => TokenBias);
     /**
      * See the parameter `evaluationPriority` on the `LlamaContextSequence.evaluate()` function for more information.
      */
     evaluationPriority?: EvaluationPriority;
     contextShift?: LLamaChatContextShiftOptions;
+    /**
+     * Custom stop triggers to stop the generation of the response when any of the provided triggers are found.
+     */
+    customStopTriggers?: readonly (LlamaText | string | readonly (string | Token)[])[];
     /**
      * The evaluation context window returned from the last evaluation.
      * This is an optimization to utilize existing context sequence state better when possible.
@@ -68,6 +123,8 @@ export type LLamaChatGenerateResponseOptions<Functions extends ChatModelFunction
          * Minimum overlap percentage with existing context sequence state to use the last evaluation context window.
          * If the last evaluation context window is not used, a new context will be generated based on the full history,
          * which will decrease the likelihood of another context shift happening so soon.
+         *
+         * A number between `0` (exclusive) and `1` (inclusive).
          */
         minimumOverlapPercentageToPreventContextShift?: number;
     };
@@ -75,11 +132,71 @@ export type LLamaChatGenerateResponseOptions<Functions extends ChatModelFunction
     grammar?: LlamaGrammar;
     functions?: never;
     documentFunctionParams?: never;
+    maxParallelFunctionCalls?: never;
+    onFunctionCall?: never;
 } | {
     grammar?: never;
     functions?: Functions | ChatModelFunctions;
     documentFunctionParams?: boolean;
+    maxParallelFunctionCalls?: number;
+    onFunctionCall?: (functionCall: LlamaChatResponseFunctionCall<Functions extends ChatModelFunctions ? Functions : ChatModelFunctions>) => void;
 });
+export type LLamaChatLoadAndCompleteUserMessageOptions<Functions extends ChatModelFunctions | undefined = undefined> = {
+    /**
+     * Complete the given user prompt without adding it or the completion to the returned context window.
+     */
+    initialUserPrompt?: string;
+    /**
+     * When a completion already started being generated and then the signal is aborted,
+     * the generation will stop and the completion will be returned as is instead of throwing an error.
+     *
+     * Defaults to `false`.
+     */
+    stopOnAbortSignal?: boolean;
+    /**
+     * Called as the model generates a completion with the generated text chunk.
+     *
+     * Useful for streaming the generated completion as it's being generated.
+     */
+    onTextChunk?: LLamaChatGenerateResponseOptions<Functions>["onTextChunk"];
+    /**
+     * Called as the model generates a completion with the generated tokens.
+     *
+     * Preferably, you'd want to use `onTextChunk` instead of this.
+     */
+    onToken?: LLamaChatGenerateResponseOptions<Functions>["onToken"];
+    signal?: LLamaChatGenerateResponseOptions<Functions>["signal"];
+    maxTokens?: LLamaChatGenerateResponseOptions<Functions>["maxTokens"];
+    temperature?: LLamaChatGenerateResponseOptions<Functions>["temperature"];
+    minP?: LLamaChatGenerateResponseOptions<Functions>["minP"];
+    topK?: LLamaChatGenerateResponseOptions<Functions>["topK"];
+    topP?: LLamaChatGenerateResponseOptions<Functions>["topP"];
+    seed?: LLamaChatGenerateResponseOptions<Functions>["seed"];
+    trimWhitespaceSuffix?: LLamaChatGenerateResponseOptions<Functions>["trimWhitespaceSuffix"];
+    repeatPenalty?: LLamaChatGenerateResponseOptions<Functions>["repeatPenalty"];
+    tokenBias?: LLamaChatGenerateResponseOptions<Functions>["tokenBias"];
+    evaluationPriority?: LLamaChatGenerateResponseOptions<Functions>["evaluationPriority"];
+    contextShift?: LLamaChatGenerateResponseOptions<Functions>["contextShift"];
+    customStopTriggers?: LLamaChatGenerateResponseOptions<Functions>["customStopTriggers"];
+    lastEvaluationContextWindow?: LLamaChatGenerateResponseOptions<Functions>["lastEvaluationContextWindow"];
+    grammar?: LlamaGrammar;
+    /**
+     * Functions are not used by the model here,
+     * but are used for keeping the instructions given to the model about the functions in the current context state,
+     * to avoid context shifts.
+     *
+     * It's best to provide the same functions that were used for the previous prompt here.
+     */
+    functions?: Functions | ChatModelFunctions;
+    /**
+     * Functions are not used by the model here,
+     * but are used for keeping the instructions given to the model about the functions in the current context state,
+     * to avoid context shifts.
+     *
+     * It's best to provide the same value that was used for the previous prompt here.
+     */
+    documentFunctionParams?: boolean;
+};
 export type LLamaChatContextShiftOptions = {
     /**
      * The number of tokens to delete from the context window to make space for new ones.
@@ -109,37 +226,6 @@ export type LLamaChatContextShiftOptions = {
      */
     lastEvaluationMetadata?: object | undefined | null;
 };
-export type LLamaChatRepeatPenalty = {
-    /**
-     * Number of recent tokens generated by the model to apply penalties to repetition of.
-     * Defaults to `64`.
-     */
-    lastTokens?: number;
-    punishTokensFilter?: (tokens: Token[]) => Token[];
-    /**
-     * Penalize new line tokens.
-     * Enabled by default.
-     */
-    penalizeNewLine?: boolean;
-    /**
-     * The relative amount to lower the probability of the tokens in `punishTokens` by
-     * Defaults to `1.1`.
-     * Set to `1` to disable.
-     */
-    penalty?: number;
-    /**
-     * For n time a token is in the `punishTokens` array, lower its probability by `n * frequencyPenalty`
-     * Disabled by default (`0`).
-     * Set to a value between `0` and `1` to enable.
-     */
-    frequencyPenalty?: number;
-    /**
-     * Lower the probability of all the tokens in the `punishTokens` array by `presencePenalty`
-     * Disabled by default (`0`).
-     * Set to a value between `0` and `1` to enable.
-     */
-    presencePenalty?: number;
-};
 export declare class LlamaChat {
     readonly onDispose: EventRelay<void>;
     constructor({ contextSequence, chatWrapper, autoDisposeSequence }: LlamaChatOptions);
@@ -152,12 +238,13 @@ export declare class LlamaChat {
     get chatWrapper(): ChatWrapper;
     get sequence(): LlamaContextSequence;
     get context(): import("../LlamaContext/LlamaContext.js").LlamaContext;
-    get model(): import("../LlamaModel.js").LlamaModel;
-    generateResponse<const Functions extends ChatModelFunctions | undefined = undefined>(history: ChatHistoryItem[], { onToken, signal, maxTokens, temperature, topK, topP, grammar, trimWhitespaceSuffix, repeatPenalty, evaluationPriority, functions, documentFunctionParams, contextShift, lastEvaluationContextWindow: { history: lastEvaluationContextWindowHistory, minimumOverlapPercentageToPreventContextShift } }?: LLamaChatGenerateResponseOptions<Functions>): Promise<LlamaChatResponse<Functions>>;
+    get model(): import("../LlamaModel/LlamaModel.js").LlamaModel;
+    generateResponse<const Functions extends ChatModelFunctions | undefined = undefined>(history: ChatHistoryItem[], options?: LLamaChatGenerateResponseOptions<Functions>): Promise<LlamaChatResponse<Functions>>;
+    loadChatAndCompleteUserMessage<const Functions extends ChatModelFunctions | undefined = undefined>(history: ChatHistoryItem[], options?: LLamaChatLoadAndCompleteUserMessageOptions<Functions>): Promise<LlamaChatLoadAndCompleteUserResponse>;
 }
 export type LlamaChatResponse<Functions extends ChatModelFunctions | undefined = undefined> = {
     response: string;
-    functionCall?: Functions extends ChatModelFunctions ? LlamaChatResponseFunctionCall<Functions> : never;
+    functionCalls?: Functions extends ChatModelFunctions ? LlamaChatResponseFunctionCall<Functions>[] : never;
     lastEvaluation: {
         cleanHistory: ChatHistoryItem[];
         contextWindow: ChatHistoryItem[];
@@ -165,11 +252,34 @@ export type LlamaChatResponse<Functions extends ChatModelFunctions | undefined =
     };
     metadata: {
         remainingGenerationAfterStop?: string | Token[];
-        stopReason: "eosToken" | "stopGenerationTrigger" | "functionCall" | "maxTokens";
+        stopReason: "eogToken" | "stopGenerationTrigger" | "functionCalls" | "maxTokens" | "abort";
+    } | {
+        remainingGenerationAfterStop?: string | Token[];
+        stopReason: "customStopTrigger";
+        customStopTrigger: (string | Token)[];
     };
 };
 export type LlamaChatResponseFunctionCall<Functions extends ChatModelFunctions, FunctionCallName extends keyof Functions & string = string & keyof Functions, Params = Functions[FunctionCallName]["params"] extends undefined | null | void ? undefined : GbnfJsonSchemaToType<Functions[FunctionCallName]["params"]>> = {
     functionName: FunctionCallName;
     params: Params;
-    raw: string;
+    raw: LlamaTextJSON;
+};
+export type LlamaChatLoadAndCompleteUserResponse = {
+    completion: string;
+    lastEvaluation: {
+        /**
+         * The completion and initial user prompt are not added to this context window result,
+         * but are loaded to the current context sequence state as tokens
+         */
+        contextWindow: ChatHistoryItem[];
+        contextShiftMetadata: any;
+    };
+    metadata: {
+        remainingGenerationAfterStop?: string | Token[];
+        stopReason: "eogToken" | "stopGenerationTrigger" | "maxTokens" | "abort";
+    } | {
+        remainingGenerationAfterStop?: string | Token[];
+        stopReason: "customStopTrigger";
+        customStopTrigger: (string | Token)[];
+    };
 };