Tinker Training Cost
sundial-org/skills
Calculate training costs for Tinker fine-tuning jobs. An agent skill from sundial-org/skills.
Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM.
Install Mindspeed Mm Vlm
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills mindspeed-mm-vlm --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/training/mindspeed-mm/mindspeed-mm-vlm .claude/skills/mindspeed-mm-vlm && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mindspeed-mm-vlm" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlm into .claude/skills/mindspeed-mm-vlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindspeed-mm-vlm", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlmType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills mindspeed-mm-vlm --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/training/mindspeed-mm/mindspeed-mm-vlm .agents/skills/mindspeed-mm-vlm && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mindspeed-mm-vlm" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlm into .agents/skills/mindspeed-mm-vlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindspeed-mm-vlm", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills mindspeed-mm-vlm --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/training/mindspeed-mm/mindspeed-mm-vlm .cursor/skills/mindspeed-mm-vlm && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mindspeed-mm-vlm" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlm into .cursor/skills/mindspeed-mm-vlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindspeed-mm-vlm", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ascend-ai-coding/awesome-ascend-skills.git --path skills/training/mindspeed-mm/mindspeed-mm-vlm--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills mindspeed-mm-vlm --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/training/mindspeed-mm/mindspeed-mm-vlm .gemini/skills/mindspeed-mm-vlm && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mindspeed-mm-vlm" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlm into .gemini/skills/mindspeed-mm-vlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindspeed-mm-vlm", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ascend-ai-coding/awesome-ascend-skills mindspeed-mm-vlmInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/training/mindspeed-mm/mindspeed-mm-vlm .github/skills/mindspeed-mm-vlm && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mindspeed-mm-vlm" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlm into .github/skills/mindspeed-mm-vlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindspeed-mm-vlm", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills mindspeed-mm-vlm --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/training/mindspeed-mm/mindspeed-mm-vlm .opencode/skills/mindspeed-mm-vlm && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mindspeed-mm-vlm" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/mindspeed-mm/mindspeed-mm-vlm into .opencode/skills/mindspeed-mm-vlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindspeed-mm-vlm", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mindspeed-mm-vlm- GitHub stars
- 174
- Token cost
- ~5.2k tokens
- SKILL.md length
- 1,612 words
- Files
- 4 (incl. references)
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- None found
At a glance
Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM.
- Works in 8 steps: Model-Specific Dependencies → Weight Download and Conversion → Dataset Preparation → …
- Fine-tuning any multimodal understanding model on Ascend NPU
- SKILL.md covers Prerequisites, Supported VLM Models, How to Train Any VLM Model and Quick Start: Qwen2.5VL-3B…, plus 5 more sections
- Calls pip, bash and git; reaches gitcode.com and github.com
What it does
Mindspeed Mm Vlm is an agent skill from ascend-ai-coding/awesome-ascend-skills. Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM. Covers all three framework patterns (Megatron, FSDP2, Custom trainers), weight conversion, dataset preparation (MLLM JSON format), fine-tuning, inference, and evaluation. Supports Qwen2.5VL, Qwen2VL, Qwen3VL, InternVL2.5/3/3.5, GLM4.1V, GLM4.5V, DeepSeekVL2, DeepSeekOCR, Ming, and more. Use when training or fine-tuning any multimodal understanding model on Ascend NPU.
Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/data-format.md`, `references/model-delta-cards.md` and `references/per-model-deps.md`).
It sits in AI & LLM Engineering, covering Fine-tuning and Computer vision. It works with NVIDIA AI Platform and Qwen. The repository describes itself as: A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/.
When your agent uses it
- Fine-tuning any multimodal understanding model on Ascend NPU
- Tasks that involve Fine-tuning
- Tasks that involve Computer vision
Example prompts
- “/mindspeed-mm-vlm”
Requirements
- Python 3
- Docker
Workflow steps
8 steps, taken from the step headings in SKILL.md.
- Model-Specific Dependencies
- Weight Download and Conversion
- Dataset Preparation
- Configuration Files
- Training Script Configuration
- Launch Training
- Inference Verification (Optional)
- Evaluation (Optional)
What it can do on your machine
Read from SKILL.md and the folder at commit 62a4ecb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pipbashgitpython3huggingface-clipython
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
gitcode.comgithub.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Mindspeed Mm Vlm loads about 5.2k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 124 tokens; SKILL.md has 1,612 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,612 words (~5,174 tokens).
“This Skill guides users through training multimodal understanding (VLM) models on Huawei Ascend NPU using MindSpeed-MM. It uses Qwen2.5VL-3B as the flagship example and covers the end-to-end fine-tuning workflow.”
- name
- mindspeed-mm-vlm
- keywords
- mindspeed-mm, vlm, multimodal understanding, qwen2.5vl, qwen3vl, internvl, glm4v, deepseekvl, finetune, fine-tuning, vision-language, megatron, fsdp2
Files
SKILL.md and 3 other files (references) in skills/training/mindspeed-mm/mindspeed-mm-vlm of ascend-ai-coding/awesome-ascend-skills.
- SKILL.md
- references/data-format.md
- references/model-delta-cards.md
- references/per-model-deps.md
Open the folder on GitHubat commit 62a4ecb
Compare with similar skills
Mindspeed Mm Vlm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mindspeed Mm Vlm this skillascend-ai-coding/awesome-ascend-skills | 174 | — | ~5.2k | Automated safety check: Pass | None | |
| Tinker Training Costsundial-org/skills | 153 | — | ~1.2k | Automated safety check: Pass | None | |
| Tao Finetune ClipNVIDIA/skills | 3.6k | — | ~4k | Automated safety check: Notes | Apache-2.0 | |
| Tao Finetune Huggingface ModelNVIDIA/skills | 3.6k | — | ~4.9k | Automated safety check: Notes | Apache-2.0 | |
| Defect Image Generation with Cosmos AnomalyGenNVIDIA/skills | 3.6k | — | ~5k | Automated safety check: Notes | Apache-2.0 | |
| Fix Art IssuesOpenPipe/ART | 11k | — | ~840 | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
Tao Finetune Clip
NVIDIA/skills
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.
- Official
Tao Finetune Huggingface Model
NVIDIA/skills
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches.
- Official
Defect Image Generation with Cosmos AnomalyGen
NVIDIA/skills
Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.
Fix Art Issues
OpenPipe/ART
Fix a GitHub issue on OpenPipe/ART and open a PR. An agent skill from OpenPipe/ART.
RuView Model Training
ruvnet/RuView
Trains and evaluates several WiFi-signal-based pose and sensing models, from unsupervised pose estimation to domain adaptation and publishing.
More from ascend-ai-coding/awesome-ascend-skills
All 70 skills in this repoAscend Dmi
ascend-ai-coding/awesome-ascend-skills
当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景： - 查看 NPU 卡的状态、温度、利用率 - 测试内存带宽（h2d/d2h/d2d/p2p） - 跑算力/功耗基准测试（TFLOPS、TOPS） - 诊断 NPU 硬件故障或做健康检查 - 对 NPU 卡做压力测试（aicore、内存） - 复位/恢复卡住或异常的 NPU 卡 典型用户问题（即使不提…
Ascendc
ascend-ai-coding/awesome-ascend-skills
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.
Atc Model Converter
ascend-ai-coding/awesome-ascend-skills
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.
External Cannbot Ops Pypto Op Develop
ascend-ai-coding/awesome-ascend-skills
当需要编写 PyPTO 算子实现时使用此 skill。基于需求规格、设计方案和参考实现，生成完整可运行的 PyPTO 算子实现与配套测试、文档。Triggers: 实现算子、写 kernel、编写实现、写 impl、算子编码、开始编码、code the op、写 test、生成测试、写实现代码、op develop、kernel 实现。
External Gitcode Ascend Megatron Change Analyzer
ascend-ai-coding/awesome-ascend-skills
Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.
External Gitcode Ascend Megatron Commit Tracker
ascend-ai-coding/awesome-ascend-skills
Track and normalize change requests against the official Megatron-LM repository by branch, PR, commit, commit range, or time window.
Related
Works with
Categories
Questions about Mindspeed Mm Vlm
What does Mindspeed Mm Vlm do?
Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM. Mindspeed Mm Vlm is an agent skill from ascend-ai-coding/awesome-ascend-skills. Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM.
When should I use Mindspeed Mm Vlm?
Mindspeed Mm Vlm fits situations like: fine-tuning any multimodal understanding model on Ascend NPU; tasks that involve Fine-tuning; tasks that involve Computer vision.
How do I install Mindspeed Mm Vlm in Claude Code?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a claude-code`. Or copy the skill folder (skills/training/mindspeed-mm/mindspeed-mm-vlm in ascend-ai-coding/awesome-ascend-skills) into .claude/skills/mindspeed-mm-vlm in your project. Claude Code loads it when a task matches its description.
How do I install Mindspeed Mm Vlm in Codex?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a codex`. Or copy the skill folder (skills/training/mindspeed-mm/mindspeed-mm-vlm in ascend-ai-coding/awesome-ascend-skills) into .agents/skills/mindspeed-mm-vlm in your project. Codex loads it when a task matches its description.
Can I use Mindspeed Mm Vlm in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill mindspeed-mm-vlm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mindspeed-mm-vlm, .gemini/skills/mindspeed-mm-vlm, .github/skills/mindspeed-mm-vlm and .opencode/skills/mindspeed-mm-vlm in your project.
What does Mindspeed Mm Vlm need to run?
Going by SKILL.md and its folder, Mindspeed Mm Vlm needs the command-line tools its instructions call (pip, bash, git, python3, huggingface-cli and python). Our summary lists: Python 3; Docker.
Does Mindspeed Mm Vlm access the network?
SKILL.md names 2 domains. In commands or code: gitcode.com and github.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Mindspeed Mm Vlm safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Mindspeed Mm Vlm use?
No licence was found for Mindspeed Mm Vlm or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Mindspeed Mm Vlm use?
About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.2k tokens, read only when the agent opens those files.
What are the alternatives to Mindspeed Mm Vlm?
Skills that share tags, products or a category with Mindspeed Mm Vlm: Tinker Training Cost (sundial-org/skills, 153 stars), Tao Finetune Clip (NVIDIA/skills, 3.6k stars), Tao Finetune Huggingface Model (NVIDIA/skills, 3.6k stars) and Defect Image Generation with Cosmos AnomalyGen (NVIDIA/skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mindspeed Mm Vlm?
ascend-ai-coding (a GitHub organization) maintains it in ascend-ai-coding/awesome-ascend-skills, which has 174 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 10, 2026.
Source: ascend-ai-coding/awesome-ascend-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.