feat: add MiniCPM5-2B model

.cspell-wordlist.txt

@@ -432,3 +432,5 @@ yunjian
 yunxi
 yunxia
 yunyang
+apos
+minicpm

apps/nlp/constants/llm.ts

@@ -284,6 +284,77 @@ export function parseLfmToolCalls(text: string): llm.ToolParserResult | undefine
   return { toolCalls, textContent: textContent || undefined };
 }
 
+function decodeMiniCpmArgument(value: string): string {
+  const trimmed = value.trim();
+  if (trimmed.startsWith('<![CDATA[') && trimmed.endsWith(']]>')) {
+    return trimmed.slice(9, -3);
+  }
+  const entities: Record<string, string> = {
+    amp: '&',
+    lt: '<',
+    gt: '>',
+    quot: '"',
+    apos: "'",
+  };
+  return trimmed.replace(/&(#x[\da-f]+|#\d+|amp|lt|gt|quot|apos);/gi, (_, entity: string) => {
+    if (entity.startsWith('#')) {
+      const code = entity.slice(1).toLowerCase();
+      return String.fromCodePoint(
+        code.startsWith('x') ? parseInt(code.slice(1), 16) : Number(code)
+      );
+    }
+    return entities[entity.toLowerCase()]!;
+  });
+}
+
+export function parseMiniCpmToolCalls(text: string): llm.ToolParserResult | undefined {
+  const thinkingEnd = text.lastIndexOf('</think>');
+  if (thinkingEnd === -1) return undefined;
+  const answer = text.slice(thinkingEnd + '</think>'.length);
+  const callRegex =
+    /<function\s+name=(["'])([^"']+)\1\s*>((?:<!\[CDATA\[[\s\S]*?\]\]>|[\s\S])*?)<\/function>/g;
+  const toolCalls: llm.ToolCall[] = [];
+
+  for (const match of answer.matchAll(callRegex)) {
+    const name = match[2]!;
+    const body = match[3]!;
+    const tool = TOOLS.find((candidate) => candidate.function.name === name);
+    if (!tool) return undefined;
+    const params = tool.function.parameters;
+    const paramRegex =
+      /<param\s+name=(["'])([^"']+)\1\s*>((?:<!\[CDATA\[[\s\S]*?\]\]>|[\s\S])*?)<\/param>/g;
+    const args: Record<string, unknown> = {};
+
+    try {
+      for (const param of body.matchAll(paramRegex)) {
+        const key = param[2]!;
+        const schema = params?.properties?.[key] as { type?: string } | undefined;
+        if (!schema || Object.prototype.hasOwnProperty.call(args, key)) return undefined;
+        const value = decodeMiniCpmArgument(param[3]!);
+        const parsed = schema.type === 'string' ? value : JSON.parse(value);
+        if (schema.type === 'number' && (typeof parsed !== 'number' || !Number.isFinite(parsed))) {
+          return undefined;
+        }
+        args[key] = parsed;
+      }
+    } catch {
+      return undefined;
+    }
+    if (body.replace(paramRegex, '').trim()) return undefined;
+    if (params?.required?.some((key) => !Object.prototype.hasOwnProperty.call(args, key))) {
+      return undefined;
+    }
+    toolCalls.push({ type: 'function', function: { name, arguments: args } });
+  }
+
+  if (toolCalls.length === 0) return undefined;
+  const textContent = answer
+    .replace(callRegex, '')
+    .replace(/<\|im_end\|>/g, '')
+    .trim();
+  return { toolCalls, textContent: textContent || undefined };
+}
+
 export const QWEN_TOOL_STOP_REGEX = /(?:<\/tool_call>|<\|im_end\|>)/;
 
 export function parseQwenToolCalls(text: string): llm.ToolParserResult | undefined {
@@ -375,6 +446,14 @@ export function parseLlamaToolCalls(text: string): llm.ToolParserResult | undefi
 
 // --- Model Family Generation Configurations ---
 
+/** Sampling defaults recommended by the MiniCPM5-2B model card. */
+export const MINICPM5_GENERATION_CONFIG: llm.LLMGenerationConfig = {
+  temperature: 1.0,
+  topP: 0.95,
+  minP: 0.0,
+  maxNewTokens: 512,
+};
+
 /**
  * Liquid AI LFM 2.5 recommended generation parameters.
  * Sampling parameters are specified in the official Liquid AI GGUF model cards
@@ -532,6 +611,11 @@ export const LFM_TOOL_OPTS: LLMToolOpts = {
   parseToolCalls: parseLfmToolCalls,
 };
 
+export const MINICPM5_TOOL_OPTS: LLMToolOpts = {
+  tools: TOOLS,
+  parseToolCalls: parseMiniCpmToolCalls,
+};
+
 export const GEMMA_TOOL_OPTS: LLMToolOpts = {
   tools: TOOLS,
   parseToolCalls: parseGemmaToolCalls,
@@ -571,6 +655,27 @@ export interface LLMModelConfig {
 // --- Quantized LLM Models List ---
 
 export const LLM_MODELS: LLMModelConfig[] = [
+  // MiniCPM5
+  {
+    id: 'minicpm-5-2b-xnnpack',
+    name: 'MiniCPM5 2B',
+    backend: 'xnnpack',
+    model: models.llm.MINICPM5_2B.XNNPACK_8DA4W,
+    generationConfig: MINICPM5_GENERATION_CONFIG,
+    systemPrompt: `${DEFAULT_SYSTEM_PROMPT}. Always reply in the language of the user's latest message.`,
+    toolOpts: MINICPM5_TOOL_OPTS,
+  },
+  {
+    id: 'minicpm-5-2b-mlx',
+    name: 'MiniCPM5 2B',
+    backend: 'mlx',
+    model: models.llm.MINICPM5_2B.MLX_INT4,
+    generationConfig: MINICPM5_GENERATION_CONFIG,
+    systemPrompt: `${DEFAULT_SYSTEM_PROMPT}. Always reply in the language of the user's latest message.`,
+    toolOpts: MINICPM5_TOOL_OPTS,
+    iosOnly: true,
+  },
+
   // LFM 2.5 family
   {
     id: 'lfm-2.5-2.6b-xnnpack',
@@ -1107,7 +1212,7 @@ export const LLM_MODELS: LLMModelConfig[] = [
     backend: 'xnnpack',
     model: models.llm.BIELIK_V3_1_5B.XNNPACK_8DA4W,
     generationConfig: BIELIK_V3_GENERATION_CONFIG,
-    // eslint-disable-next-line @cspell/spellchecker
+    // cspell:disable-next-line
     systemPrompt: 'Jesteś pomocnym asystentem AI mówiącym po polsku.',
     stopRegex: undefined,
     toolOpts: undefined,

docs/docs/02-extensions/natural-language/02-llm-chat-and-generation.md

@@ -381,6 +381,7 @@ The library provides ready-to-use models from the [Software Mansion HuggingFace
 | **Microsoft Phi-4 Mini** | [`3.8B`](../../06-api-reference/variables/models.md#llmphi4_mini)                                                                                                                                                  | 2.62 GB – 7.15 GB | XNNPACK (CPU), MLX (Apple)                   | High-density reasoning model for STEM problem solving & coding.             |
 | **HuggingFace SmolLM2**  | [`135M`](../../06-api-reference/variables/models.md#llmsmollm2_135m), [`360M`](../../06-api-reference/variables/models.md#llmsmollm2_360m), [`1.7B`](../../06-api-reference/variables/models.md#llmsmollm2_1_7b)   | 158 MB – 1.83 GB  | XNNPACK (CPU), MLX (Apple)                   | Smallest footprint family, for constrained devices and fast drafting.       |
 | **SpeakLeash Bielik v3** | [`1.5B`](../../06-api-reference/variables/models.md#llmbielik_v3_1_5b)                                                                                                                                             | 923 MB – 2.97 GB  | XNNPACK (CPU)                                | Bilingual Polish & English instruction model.                               |
+| **OpenBMB MiniCPM5**     | [`2B`](../../06-api-reference/variables/models.md#llmminicpm5_2b)                                                                                                                                                  | 1.36 GB – 1.42 GB | XNNPACK (CPU), MLX (Apple)                   | Compact reasoning model with thinking and tool calling.                     |
 
 :::tip Using Custom Models
 To use your own fine-tuned LLM `.pte` model, pass an [`LLMModel`](../../06-api-reference/type-aliases/LLMModel.md) configuration object to [`useLLMChatSession`](../../06-api-reference/functions/useLLMChatSession.md) or [`createLLMChatSession`](../../06-api-reference/functions/createLLMChatSession.md):

packages/react-native-executorch/src/models.ts

@@ -1874,7 +1874,7 @@
 
 // Chinese is published from the next tag. Its phonemizer segments the text
 // into words, with the segmenter data in the tagger slot, and reads each word
 // from the lexicon. Upstream's zf_xiaoni is left out: it is unintelligible even
 // in the reference PyTorch model.
 const KOKORO_NEXT_ROOT = `${BASE_URL}-kokoro/${NEXT_VERSION_TAG}`;
 const KOKORO_ZH_PHONEMIZER = {
@@ -2098,6 +2098,19 @@
 // =============================================================================
 // LLMs
 // =============================================================================
+const MINICPM5_BASE_URL = `${BASE_URL}-minicpm-5/${NEXT_VERSION_TAG}`;
+
+const MINICPM5_2B_XNNPACK_8DA4W: LLMModel = {
+  modelPath: `${MINICPM5_BASE_URL}/xnnpack/minicpm_5_2b_xnnpack_8da4w.pte`,
+  tokenizerPath: `${MINICPM5_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${MINICPM5_BASE_URL}/tokenizer_config.json`,
+};
+const MINICPM5_2B_MLX_INT4: LLMModel = {
+  modelPath: `${MINICPM5_BASE_URL}/mlx/minicpm_5_2b_mlx_4w.pte`,
+  tokenizerPath: `${MINICPM5_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${MINICPM5_BASE_URL}/tokenizer_config.json`,
+};
+
 const LFM2_5_BASE_URL = `${BASE_URL}-lfm-2.5/${NEXT_VERSION_TAG}`;
 
 const LFM2_5_1_2B_XNNPACK_8DA4W: LLMModel = {
@@ -3225,6 +3238,11 @@
    * text generation, and reasoning.
    */
   llm: {
+    /** OpenBMB MiniCPM5 2B chat model with an 8K context window. */
+    MINICPM5_2B: variants({
+      XNNPACK_8DA4W: MINICPM5_2B_XNNPACK_8DA4W,
+      MLX_INT4: MINICPM5_2B_MLX_INT4,
+    }),
     /**
      * Liquid AI LFM 2.5 1.2B general-purpose hybrid language model. Built on
      * the Liquid Foundation Model architecture for low memory bandwidth usage,