feat(AI): MNN 文本模型升到 Qwen3.5-4B(taobao-mnn 预转换)
现场机 iPhone 17(A19/SME2)内存与加速均可承载 4B,质量优于 2B。 - ModelKind.mnnLLM rawValue → "Qwen3.5-4B-MNN",displayName → Qwen3.5-4B (MNN/SME2) - ModelManifest:7 个运行时文件(llm.mnn.weight ~2.45GB + 拆分的 visual.mnn.weight 188MB),总计 2,836,770,850 bytes(~2.64GiB) - ModelManifestTests:文件数 7 / 总字节 / URL 更新到 Qwen3.5-4B-MNN - CLAUDE.md §2:MNN 主模型记为 Qwen3.5-4B,MLX 兜底仍 2B 模拟器 ModelManifestTests TEST SUCCEEDED。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -60,17 +60,18 @@ nonisolated enum ModelManifest {
|
||||
ModelFile(path: "video_preprocessor_config.json", bytes: 817),
|
||||
]
|
||||
case .mnnLLM:
|
||||
// taobao-mnn/Qwen3.5-2B-MNN 预转换 MNN 格式(HF API 实测,2026-06)。
|
||||
// taobao-mnn/Qwen3.5-4B-MNN 预转换 MNN 格式(HF API 实测,2026-06)。
|
||||
// 运行时必需:config.json(MNN llm 配置)+ llm_config.json(超参)+ llm.mnn(图)
|
||||
// + llm.mnn.weight(量化权重 ~1.1GB)+ tokenizer.txt + visual.mnn(多模态,文本路径不用但配置含 mllm)。
|
||||
// 排除 README/.gitattributes 与可读 dump(llm.mnn.json / export_args.json)。
|
||||
// + llm.mnn.weight(量化权重 ~2.45GB)+ tokenizer.txt + visual.mnn/visual.mnn.weight(多模态,
|
||||
// 文本路径不用但配置含 mllm,带上避免缺文件)。排除 README/.gitattributes 与可读 dump。
|
||||
return [
|
||||
ModelFile(path: "config.json", bytes: 652),
|
||||
ModelFile(path: "llm_config.json", bytes: 8_692),
|
||||
ModelFile(path: "llm.mnn", bytes: 2_148_136),
|
||||
ModelFile(path: "llm.mnn.weight", bytes: 1_176_647_702),
|
||||
ModelFile(path: "llm_config.json", bytes: 8_693),
|
||||
ModelFile(path: "llm.mnn", bytes: 3_651_096),
|
||||
ModelFile(path: "llm.mnn.weight", bytes: 2_629_387_626),
|
||||
ModelFile(path: "tokenizer.txt", bytes: 6_465_727),
|
||||
ModelFile(path: "visual.mnn", bytes: 488_096),
|
||||
ModelFile(path: "visual.mnn.weight", bytes: 196_768_960),
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user