Files
kangkang/康康/AI/ModelManifest.swift
link2026 836f3d4234 ```
feat(AI): 统一多模态模型架构,整合文本和视觉推理路径

- 将文本生成和VL(图→文)功能合并到单一的Qwen3.5-4B多模态MNN模型
- 移除独立的Qwen3-VL-4B模型依赖,MLX VL改为使用.llm的多模态模型
- 更新ModelKind枚举,新增userFacing集合用于面向用户展示
- MNN后端现在同时支持文本和视觉任务,模拟器回退到MLX

refactor(models): 模型管理和界面调整以适应新的多模态架构

- 更新模型管理界面,只显示统一的Qwen3.5-4B(MNN)模型给用户
- 修改就绪状态检查逻辑,使用ModelKind.userFacing替代allCases
- 更新模型文件清单,从Qwen3.5-2B升级到Qwen3.5-4B-4bit
- 调整模型管理页面UI,突出MNN+SME2端侧加速功能

feat(camera): 添加拍照识别引擎切换功能

- 实现双路径拍照识别:Apple Vision OCR + 文本模型 和 Qwen3-VL直接识别
- 添加预处理逻辑,优化Qwen3-VL对窄长区域图片的识别效果
- 在模型管理页面添加拍照识别引擎选择组件
- 提供用户界面选项,在两种识别方式间切换

style(ui): 优化输入框样式和颜色主题一致性

- 为指标快速表单添加浅色主题偏好
- 统一所有文本输入框的颜色样式(theme)
- 创建EntryInputField组件,替换原有的单行输入+按钮模式
- 实现聊天框风格的条目输入,支持多行自适应和圆形发送按钮

fix(build): 修正Xcode项目配置中的重复框架搜索路径

- 清理project.pbxproj中重复的FRAMEWORK_SEARCH_PATHS配置
- 重新排列Swift桥接头文件配置确保正确引用
- 修复因路径配置重复导致的编译警告问题

test: 增加区域图片预处理和模型清单测试覆盖

- 添加RegionImageCropper.prepareForQwenVL的单元测试
- 验证宽而矮图片的放大和填充逻辑
- 更新ModelManifestTests中的字节数预期值以匹配新模型
- 修正OCRService中VNRecognizedTextObservation类型的处理
```
2026-06-08 23:25:31 +08:00

88 lines
4.9 KiB
Swift

import Foundation
/// : + ()
struct ModelFile: Equatable, Sendable {
let path: String
let bytes: Int
}
///
/// , README.md / .gitattributes()
/// ,
/// docs/superpowers/specs/2026-05-29-model-download-design.md A
nonisolated enum ModelManifest {
/// Caddy ( HTTPS )
/// IP( App ATS ): http://101.132.124.52:5244/
static let baseURL = URL(string: "https://file.myv0.com/")!
static func files(for kind: ModelKind) -> [ModelFile] {
switch kind {
case .llm:
// Qwen3.5-4B-4bit:,MLX (LLMModelFactory qwen3_5 )
// (VLMModelFactory qwen3_5) mlx-community/Qwen3.5-4B-4bit
// blob (HF API,2026-06 )(),
// README.md / .gitattributes
return [
ModelFile(path: "config.json", bytes: 3_366),
ModelFile(path: "model.safetensors", bytes: 3_034_300_695),
ModelFile(path: "model.safetensors.index.json", bytes: 101_944),
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_756),
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: mlx-community blob
// (HF API blobs=true,2026-05 ),
// :( README.md / .gitattributes),
// mlx-vlm , VLMModelFactory
// chat_template(.json + .jinja ) video ,
// swift-transformers / Qwen3VLProcessor
return [
ModelFile(path: "config.json", bytes: 7_137),
ModelFile(path: "model.safetensors", bytes: 3_093_767_283),
ModelFile(path: "model.safetensors.index.json", bytes: 64_742),
ModelFile(path: "tokenizer.json", bytes: 11_422_654),
ModelFile(path: "tokenizer_config.json", bytes: 5_445),
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: "generation_config.json", bytes: 269),
ModelFile(path: "chat_template.json", bytes: 5_502),
ModelFile(path: "chat_template.jinja", bytes: 5_292),
ModelFile(path: "preprocessor_config.json", bytes: 782),
ModelFile(path: "video_preprocessor_config.json", bytes: 817),
]
case .mnnLLM:
// taobao-mnn/Qwen3.5-4B-MNN MNN (HF API ,2026-06)
// :config.json(MNN llm )+ llm_config.json()+ llm.mnn()
// + llm.mnn.weight( ~2.45GB)+ tokenizer.txt + visual.mnn/visual.mnn.weight(,
// mllm,) README/.gitattributes dump
return [
ModelFile(path: "config.json", bytes: 652),
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),
]
}
}
static func totalBytes(for kind: ModelKind) -> Int {
files(for: kind).reduce(0) { $0 + $1.bytes }
}
/// URL = baseURL / <> / <>
static func fileURL(for kind: ModelKind, file: ModelFile) -> URL {
baseURL
.appendingPathComponent(kind.rawValue, isDirectory: true)
.appendingPathComponent(file.path)
}
}