Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
使用 ArkCLI 创建、查询和管理模型精调训练任务,并从训练指标选择最佳 step、导出训练产物为 custom model、衔接模型仓库与推理部署。任何包含精调任务 ID(mcj-)的查询、查不到原因诊断、日志、trajectory、状态或生命周期操作都应使用本 skill;也适用于选择训练方法、查询精调价格和超参数、校验精调训练/验证数据、匹配精调资源组、创建任务及导出部署。本…
$ npx skills add volcengine/ark-cli --skill arkcli-train-finetune -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-train-finetune --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/volcengine/ark-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/arkcli-train-finetune .claude/skills/arkcli-train-finetune && 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 "arkcli-train-finetune" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-train-finetune into .claude/skills/arkcli-train-finetune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-train-finetune", 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/volcengine/ark-cli/tree/main/skills/arkcli-train-finetuneType 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 volcengine/ark-cli --skill arkcli-train-finetune -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-train-finetune --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/arkcli-train-finetune .agents/skills/arkcli-train-finetune && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "arkcli-train-finetune" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-train-finetune into .agents/skills/arkcli-train-finetune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-train-finetune", 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 volcengine/ark-cli --skill arkcli-train-finetune -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-train-finetune --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/arkcli-train-finetune .cursor/skills/arkcli-train-finetune && 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 "arkcli-train-finetune" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-train-finetune into .cursor/skills/arkcli-train-finetune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-train-finetune", 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/volcengine/ark-cli.git --path skills/arkcli-train-finetune--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 volcengine/ark-cli --skill arkcli-train-finetune -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-train-finetune --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/arkcli-train-finetune .gemini/skills/arkcli-train-finetune && 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 "arkcli-train-finetune" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-train-finetune into .gemini/skills/arkcli-train-finetune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-train-finetune", 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 volcengine/ark-cli arkcli-train-finetuneInstalls 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 volcengine/ark-cli --skill arkcli-train-finetune -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/arkcli-train-finetune .github/skills/arkcli-train-finetune && 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 "arkcli-train-finetune" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-train-finetune into .github/skills/arkcli-train-finetune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-train-finetune", 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 volcengine/ark-cli --skill arkcli-train-finetune -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install volcengine/ark-cli arkcli-train-finetune --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/arkcli-train-finetune .opencode/skills/arkcli-train-finetune && 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 "arkcli-train-finetune" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-train-finetune into .opencode/skills/arkcli-train-finetune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-train-finetune", 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.
arkcli-train-finetune使用 ArkCLI 创建、查询和管理模型精调训练任务,并从训练指标选择最佳 step、导出训练产物为 custom model、衔接模型仓库与推理部署。任何包含精调任务 ID(mcj-)的查询、查不到原因诊断、日志、trajectory、状态或生命周期操作都应使用本 skill;也适用于选择训练方法、查询精调价格和超参数、校验精调训练/验证数据、匹配精调资源组、创建任务及导出部署。本…
Arkcli Train Finetune is an agent skill from volcengine/ark-cli. 使用 ArkCLI 创建、查询和管理模型精调训练任务,并从训练指标选择最佳 step、导出训练产物为 custom model、衔接模型仓库与推理部署。任何包含精调任务 ID(mcj-)的查询、查不到原因诊断、日志、trajectory、状态或生命周期操作都应使用本 skill;也适用于选择训练方法、查询精调价格和超参数、校验精调训练/验证数据、匹配精调资源组、创建任务及导出部署。本 skill 不负责独立 Dataset 生命周期管理;精调工作流中的数据校验和 Dataset 引用仍由本 skill 编排。
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/ark-finetune-sdk.md`, `references/create.md` and `references/export-deploy.md`).
It sits in AI & LLM Engineering, covering Fine-tuning. The repository describes itself as: The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API… The licence is Apache-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit fb5b7be. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
volcengine.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Arkcli Train Finetune loads about 1.4k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 423 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.
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.
The full file from volcengine/ark-cli at commit fb5b7be, republished under its Apache-2.0 licence (© volcengine). 423 words, ~1,447 tokens.
.claude/skills/arkcli-train-finetune/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.先读取 ../arkcli-shared/SKILL.md,遵循认证、输出、安全和二次确认规则。
references/create.mdreferences/list.mdreferences/manage.mdreferences/export-deploy.mdarkcli dataset validate;不要因为命令路径属于 dataset 就切换 skill。../arkcli-datasets/SKILL.md。创建精调任务时可以直接消费本地文件、TOS URL、ds-*/dsv-* 引用和模型支持的 preset。--train-dataset(Multiplier=1);需要重复引用、倍率或采样数时改用可重复的 --train-path。每项最多设置 multiplier 或 sample_count 之一,均不设置时仍默认 Multiplier=1。preset 必须在 inject_multiplier 与 inject_sample_count 中二选一。只加载当前任务需要的 reference。不要为了熟悉全部命令一次性读取所有文件。
../arkcli-models/SKILL.md。../arkcli-infer-endpoint/SKILL.md。../arkcli-auth/SKILL.md 或 ../arkcli-config/SKILL.md。mcj-* 并询问任务状态、查不到原因、日志或 trajectory 时,必须加载本 skill 并读取 references/manage.md。arkcli train finetune get <mcj-id>,再按该权威 API 的原始结果解释。mcj-* 是不透明资源 ID。不得根据日期片段、后缀单词或臆测的哈希格式断言 ID 无效,也不得改写用户给出的 ID。train finetune list、扫描其他任务、切换 profile/project/region,或查询其他账号。目标 get 失败时保留错误 code、message 和 request ID;只有用户另行授权后才能扩大范围。arkcli train finetune logs <mcj-id> --output <path>。不得先 list 全部任务或用脚本遍历;目标命令失败时原样报告,不建议切环境。arkcli train finetune trajectory list <mcj-id> --full。不存在 arkcli train trajectory 路径;无轨迹或未开启记录时保留原错误,不探索 profile、MCP 或其他任务。logs --follow 仅在任务活跃且可能继续产生日志时持续轮询;任务已终态时输出当前快照后自动退出,轮询中发现终态且无新日志也会退出。不要再用外部 timeout 作为正常终止机制。pause 与 resume 是明确的可逆关系:pause 将运行任务置为 Paused,resume 用于恢复 Paused;后端允许时也可用 resume 重试 Failed / Terminated,以当前 API 结果为准。以下信息会变化,不在 skill 中硬编码:
关键命令执行前或执行报错,使用当前安装版本的 --help 和 ArkCLI 查询命令获取实时结果。若 CLI 输出与本文命令骨架不一致,以当前 CLI 为准。
训练和验证数据优先通过 arkcli dataset validate 按目标模型、精确版本和训练类型完成服务端校验,具体流程见 references/create.md。不默认由 Agent 对照文档逐行检查或自写校验器。火山方舟模型精调数据集格式说明仅用于解释校验错误、辅助修复或说明命令未覆盖的格式;文档比对不能替代命令的校验结果。不在 reference 中维护容易过期的格式说明及样例。
--type)时,默认按 SFT 处理。精调 SDK 是 fallback,不是默认入口。
仅当 ArkCLI 无法完成,而精调 SDK 能完成时进入 fallback,例如:
需要 fallback 时,先检查当前 ArkCLI 的 train finetune、models finetune-config 和相关 --help 是否能够完整表达用户配置。若 ArkCLI 已提供对应参数或 pipeline 配置并能完整完成任务,继续走标准创建流程。
命中 fallback 时暂停执行,询问用户:
当前任务需要精调 SDK,ArkCLI 标准创建流程无法表达该配置。是否现在自动安装精调 SDK 并继续?
只有用户明确确认后,才读取并执行 references/ark-finetune-sdk.md;由该 reference 负责安装 SDK、准备配置或代码并提交任务。用户拒绝时不要安装、不要提交。
提交前以精确模型/版本查询 train finetune capability get --model <name> --version <version>,或复用同版本 models finetune-config ... --type <type> 的权威校验。支持类型为空/未知时停下核对模型与版本,不暴力枚举 SFT/LoRA/DPO 直到碰巧成功。
价格查询的 --model 使用权威基础模型名,不把带版本的拼接 ID 当名称;需要精确版本时用当前 help 支持的独立版本参数。能力、超参、价格与 create 必须对应同一训练方法。
DPO / DPO-LoRA 不机械继承 SFT 的数据容错与 shuffle 参数;只有该模型/类型的当前配置明确支持时才传。超参名和值按实时 schema,不能照抄历史 dpo_beta,也不能把当前已注册的 --beta 误说成不存在。
数据必须是用户提供或明确授权的真实文件、TOS URI、Dataset/preset 引用;占位 bucket/path 只用于说明,不发真实提交。缺数据就请求补充。
本地 create --dry-run 不需要以 --yes 绕过,也不校验远端 TOS 存在性;在线数据校验、费用 estimate 和真实提交分别报告,不把任一步成功当成训练已创建。
用户给出模型名和训练类型询问“精调/SFT/LoRA 价格”时,首选且必须执行 arkcli train finetune pricing --model <model> --type <type>。不要改走通用 arkcli pricing models:通用账单目录不会按目标模型交叉校验训练方法能力。
显式选择训练方法时,必须用精确的模型版本调用 models finetune-config <model> <version> --type <type>。该命令会先按同版本 FinetuneTypes 校验能力;不支持时停止,不继续询价、estimate 或创建任务。
手动分页时,train finetune list --page-number 必须 >=1,--page-size 必须在 1-100;第 2 页及以后超出当前过滤条件对应的 total_count 时是参数错误,不要把空页当成有效结果。
同时传入 train finetune metrics --from-step 和 --to-step 时,to-step 必须严格大于 from-step;非法区间应在查询指标名称或曲线前停止。
train finetune pricing --billing-method token 按 Token 计费项查询;instance 必须提供精确的 --model-version 和 --type,并保持超参与后续创建一致。实例结果只有 price_complete=true 才能作为完整小时价范围;否则必须报告 missing_flavor_ids。
使用稳定资源组前,必须用与 create 完全相同的模型、版本、训练类型和超参数执行 train finetune resource-group list。只有 allowed=true 且 matched=true 的资源组 ID 才能传给 create --resource-group;ID 是不透明字符串,必须按查询结果原样传入;有多个匹配项时让用户选择。
arkcli auth status,认证失败时按 shared skill 恢复。© volcengine, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 8 other files (references) in skills/arkcli-train-finetune of volcengine/ark-cli.
Open the folder on GitHubat commit fb5b7be
Arkcli Train Finetune 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 |
|---|---|---|---|---|---|---|
| Arkcli Train Finetune this skillvolcengine/ark-cli | 140 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Peft Fine TuningOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Hugging Face LLM Trainerhuggingface/skills | 11k | 3 repos | ~7.2k | Automated safety check: Pass | Apache-2.0 | |
| Sentence-Transformers Training Routerhuggingface/skills | 11k | 1 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Dataset Evaluationawslabs/agent-plugins | 912 | 2 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Train RlOpenPipe/ART | 11k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
huggingface/skills
Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.
huggingface/skills
Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.
awslabs/agent-plugins
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).
OpenPipe/ART
RL training reference for the ART framework. An agent skill from OpenPipe/ART.
R6410418/Jackrong-llm-finetuning-guide
Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.
volcengine/ark-cli
Inspect or invoke locally registered ArkCLI actions when product commands cannot cover a task.
volcengine/ark-cli
arkcli +code-example:为指定基础模型生成多语言(Python / Go / Java / Node / curl)调用示例代码并写入本地文件。数据源是火山方舟 OpenTOP OpenGetSampleCode。当用户需要拿某个基础模型的 SDK / curl 调用示例、保存为本地接入模板时使用。反触发:TTS/ASR/语音模型没有 arkcli…
volcengine/ark-cli
arkcli 本地配置管理。处理 profile 配置归因、update.mode 的 automatic/disabled 策略、config reset 与历史 yaml 排障;profile 类操作优先使用 arkcli profile <subcmd。
volcengine/ark-cli
arkcli 自定义模型仓库管理:从 TOS 导入自定义模型、查询/筛选自定义模型、查看详情、改名、删除、查询可用量化模式、量化已就绪的模型。任何提到自定义模型 ID(cm-)的管理、部署准备,或要求用 cm- 直接对话/推理/试效果的边界判断,都必须使用本 skill。注意:查询火山公共基础模型(doubao 等 foundation models)走 arkcli-models;本…
volcengine/ark-cli
arkcli +deploy:普通创建推理接入点(Endpoint)的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里;但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外,必须改走 arkcli-infer-endpoint,不能由本 skill…
volcengine/ark-cli
检索、读取与总结方舟官方文档。用户给出 ark.volcengine.com 文档 URL 或 /docs/ 路径、要求读链接、官方说明、API 契约或必填字段,询问 CC Switch 等第三方客户端的方舟图形配置流程,以及官方网页读取失败时使用。不用于业务调用、资源操作、CLI 帮助或通用知识。
Categories
使用 ArkCLI 创建、查询和管理模型精调训练任务,并从训练指标选择最佳 step、导出训练产物为 custom model、衔接模型仓库与推理部署。任何包含精调任务 ID(mcj-)的查询、查不到原因诊断、日志、trajectory、状态或生命周期操作都应使用本 skill;也适用于选择训练方法、查询精调价格和超参数、校验精调训练/验证数据、匹配精调资源组、创建任务及导出部署。本…. Arkcli Train Finetune is an agent skill from volcengine/ark-cli.
Arkcli Train Finetune fits situations like: tasks that involve Fine-tuning.
Run `npx skills add volcengine/ark-cli --skill arkcli-train-finetune -a claude-code`. Or copy the skill folder (skills/arkcli-train-finetune in volcengine/ark-cli) into .claude/skills/arkcli-train-finetune in your project. Claude Code loads it when a task matches its description.
Run `npx skills add volcengine/ark-cli --skill arkcli-train-finetune -a codex`. Or copy the skill folder (skills/arkcli-train-finetune in volcengine/ark-cli) into .agents/skills/arkcli-train-finetune in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add volcengine/ark-cli --skill arkcli-train-finetune -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/arkcli-train-finetune, .gemini/skills/arkcli-train-finetune, .github/skills/arkcli-train-finetune and .opencode/skills/arkcli-train-finetune in your project.
SKILL.md names no scripts, command-line tools or credentials: Arkcli Train Finetune is instructions for the agent only.
SKILL.md names 1 domain. As links in the text: volcengine.com. This is read from the text; nothing was executed.
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.
Arkcli Train Finetune is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.8k 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 13k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Arkcli Train Finetune: Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face LLM Trainer (huggingface/skills, 11k stars), Sentence-Transformers Training Router (huggingface/skills, 11k stars) and Dataset Evaluation (awslabs/agent-plugins, 912 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
volcengine (a GitHub organization) maintains it in volcengine/ark-cli, which has 140 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on September 29, 2026.
Source: volcengine/ark-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.