feat(AI): LLM 迁移到 mlx-swift-lm 2.31.3 + Qwen3.5-2B
将 SPM 依赖从 mlx-swift-examples 2.29.1 迁到改名延续仓库 mlx-swift-lm 2.31.3(含 qwen3_5 架构、旧 loadContainer API 兼容),文本 LLM 由 Qwen3-1.7B 换为 Qwen3.5-2B-4bit(走 qwen3_5→Qwen35Model 文本路径)。 连带 mlx-swift 0.29.1→0.31.4,顺修弃用 API: - MLX.GPU.clearCache() → MLX.Memory.clearCache() - MLX.GPU.set(cacheLimit:) → MLX.Memory.cacheLimit 更新 ModelManifest(.llm 文件清单+精确字节数,~1.63GiB)、ModelManifestTests、 HealthExport.modelTag 默认值。App BUILD SUCCEEDED + ModelManifestTests 通过。 保留作 MNN 改造的 GPU 兜底基线。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -18,16 +18,23 @@ nonisolated enum ModelManifest {
|
||||
static func files(for kind: ModelKind) -> [ModelFile] {
|
||||
switch kind {
|
||||
case .llm:
|
||||
// Qwen3.5-2B-4bit:多模态仓库,但走 LLMModelFactory 的 qwen3_5 文本路径加载。
|
||||
// 字节数取自 mlx-community/Qwen3.5-2B-4bit 仓库实际 blob 大小(HF API,2026-06 核对)。
|
||||
// 该仓库 tokenizer 体系为 vocab.json + tokenizer.json(无 merges.txt /
|
||||
// special_tokens_map.json / added_tokens.json),chat_template 改为 .jinja。
|
||||
// 一并镜像视觉预处理配置(preprocessor / processor / video_preprocessor),
|
||||
// 文本加载用不到但体积可忽略,保持与仓库一致避免漏文件。
|
||||
return [
|
||||
ModelFile(path: "config.json", bytes: 937),
|
||||
ModelFile(path: "model.safetensors", bytes: 968_080_210),
|
||||
ModelFile(path: "model.safetensors.index.json", bytes: 49_731),
|
||||
ModelFile(path: "tokenizer.json", bytes: 11_422_654),
|
||||
ModelFile(path: "tokenizer_config.json", bytes: 9_706),
|
||||
ModelFile(path: "vocab.json", bytes: 2_776_833),
|
||||
ModelFile(path: "merges.txt", bytes: 1_671_853),
|
||||
ModelFile(path: "special_tokens_map.json", bytes: 613),
|
||||
ModelFile(path: "added_tokens.json", bytes: 707),
|
||||
ModelFile(path: "config.json", bytes: 3_113),
|
||||
ModelFile(path: "model.safetensors", bytes: 1_722_271_785),
|
||||
ModelFile(path: "model.safetensors.index.json", bytes: 81_722),
|
||||
ModelFile(path: "tokenizer.json", bytes: 19_989_343),
|
||||
ModelFile(path: "tokenizer_config.json", bytes: 1_139),
|
||||
ModelFile(path: "vocab.json", bytes: 6_722_759),
|
||||
ModelFile(path: "chat_template.jinja", bytes: 7_755),
|
||||
ModelFile(path: "preprocessor_config.json", bytes: 390),
|
||||
ModelFile(path: "processor_config.json", bytes: 1_300),
|
||||
ModelFile(path: "video_preprocessor_config.json", bytes: 385),
|
||||
]
|
||||
case .vl:
|
||||
// Qwen3-VL-4B-Instruct-4bit:字节数取自 mlx-community 仓库实际 blob 大小
|
||||
|
||||
Reference in New Issue
Block a user