TypingMindTypingMindThe best frontend for AI
Mindspeed Fsdp2 Data Migration logo

Mindspeed Fsdp2 Data Migration

Organization
Ascend
mindspeed-fsdp2-data-migration

用于将数据预处理与数据加载契约迁移到 MindSpeed-MM FSDP2。适用于实现数据集注册、预处理复用、collate 行为与输入字段兼容时。

Overview

PublisherAscend
Repositoryagent-skills
Skill namemindspeed-fsdp2-data-migration
Stars
54
Forks
4
Bundled files
5
LicenseMulanPSL-2.0
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Ascend on GitHub. Read the source before you install it.

Installation

Install the Mindspeed Fsdp2 Data Migration AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Ascend/agent-skills/tree/master/skills/mindspeed-mm-fsdp2-migration/mindspeed-fsdp2-data-migration
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Ascend/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/mindspeed-mm-fsdp2-migration/mindspeed-fsdp2-data-migration .claude/skills/mindspeed-fsdp2-data-migration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mindspeed Fsdp2 Data Migration in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mindspeed Fsdp2 Data Migration on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mindspeed Fsdp2 Data Migration is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MindSpeed FSDP2 数据迁移

目标

将源数据集逻辑迁移到 MindSpeed-MM FSDP2 数据插件结构中，保持预处理语义并确保 trainer/模型输入兼容。

适用场景

  • 迁移任务需要在 mindspeed_mm/fsdp/data/ 下创建数据插件。
  • 需要复用源预处理函数或进行最小化适配。
  • 需要实现 dataset_type 注册、__getitem__ 与 collate_fn。

不适用场景

  • 任务是模型加载或模型注册。
  • 任务仅做配置映射且不涉及数据行为变更。
  • 任务是最终验证门禁执行。

输入

  • 源数据集入口文件
  • 目标 dataset_type
  • 预期模型输入字段
  • 数据与路径格式假设
  • runtime_assets.dataset_path

输出

  • 数据插件实现
  • 带通过/失败状态的数据迁移检查清单
  • 对“非直接拷贝改动”的适配理由

必检项

  1. 注册契约：
    • @data_register.register("<dataset_type>")
  2. 数据契约：
    • __getitem__ 返回模型前向所需字段
    • collate_fn 能安全处理变长 batch
  3. 复用契约：
    • 兼容时应优先复用源预处理函数
  4. 稳健性契约：
    • 安全处理路径类型变体（str、list[str]）
    • 对无效 schema 假设抛出清晰错误

防偏差执行协议

  1. 实施前必须完成：
    • 校验 runtime_assets.dataset_path 存在且可读
    • 抽样读取前 N 条样本，确认 schema 字段存在
  2. 实施后必须产出：
    • dataset_schema_report.md
    • fields_contract_report.md
  3. 失败即停止：
    • __getitem__ 字段不全或 collate 崩溃时，禁止进入配置/验证阶段

禁止行为

  • 禁止把路径类型假设为仅 str
  • 禁止静默吞掉 schema 错误
  • 禁止删除模态关键字段（pixel_values、image_flags 等）而不声明
  • 禁止以“样例数据通过”替代“真实路径抽样验证”

实施规则

  • 先拷贝源仓核心预处理逻辑。
  • 适配范围仅限导入、注册、字段映射和契约对齐。
  • 不得静默丢弃模态关键字段。
  • 明确记录每个函数不能直接复用的原因。

退出标准

  • 数据集可通过 build_mm_dataset 构建。
  • 数据字段与 collate 输出符合模型预期。
  • 数据侧清单结论均有证据支撑。

渐进式资源

  • checks/data-acceptance.md
  • checks/data-contract-gates.md
  • errors/data-error-dictionary.md
  • errors/triage-severity.md
  • examples/minimal-io.md

仅在验收或数据错误分诊需要详细判据时读取这些文件。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mindspeed Fsdp2 Data Migration AI skill do?

用于将数据预处理与数据加载契约迁移到 MindSpeed-MM FSDP2。适用于实现数据集注册、预处理复用、collate 行为与输入字段兼容时。

Why use Mindspeed Fsdp2 Data Migration on TypingMind?

Because you install it once and use it with any model. Mindspeed Fsdp2 Data Migration is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mindspeed Fsdp2 Data Migration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Ascend/agent-skills/tree/master/skills/mindspeed-mm-fsdp2-migration/mindspeed-fsdp2-data-migration. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mindspeed Fsdp2 Data Migration?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mindspeed Fsdp2 Data Migration?

As many as you like. As long as a model supports skills, you can use Mindspeed Fsdp2 Data Migration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mindspeed Fsdp2 Data Migration AI skill free?

Yes. It is published on GitHub by Ascend under the MulanPSL-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
NousResearch logo

Comps Analysis

NousResearch
OrganizationPopular

Build comparable-company valuation workbooks in Excel.

53.5K
250.4K
Instructions
View
NousResearch logo

Weights And Biases

NousResearch
OrganizationPopular

W&B: log ML experiments, sweeps, model registry, dashboards.

53.5K
250.4K
3 files
View
NousResearch logo

Faiss

NousResearch
OrganizationPopular

Fast vector similarity search at billion scale.

53.5K
250.4K
1 files
View
NousResearch logo

Serving Llms Vllm

NousResearch
OrganizationPopular

vLLM: high-throughput LLM serving, OpenAI API, quantization.

53.5K
250.4K
4 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇