Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs.
Install Overmind Training
$ npx skills add overmind-core/overmind --skill overmind-training -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install overmind-core/overmind overmind-training --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/overmind-core/overmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/overmind/skills/overmind-training .claude/skills/overmind-training && 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 "overmind-training" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-training into .claude/skills/overmind-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-training", 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/overmind-core/overmind/tree/main/overmind/skills/overmind-trainingType 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 overmind-core/overmind --skill overmind-training -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install overmind-core/overmind overmind-training --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .agents/skills && cp -r skills-src/overmind/skills/overmind-training .agents/skills/overmind-training && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "overmind-training" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-training into .agents/skills/overmind-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-training", 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 overmind-core/overmind --skill overmind-training -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install overmind-core/overmind overmind-training --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/overmind/skills/overmind-training .cursor/skills/overmind-training && 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 "overmind-training" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-training into .cursor/skills/overmind-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-training", 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/overmind-core/overmind.git --path overmind/skills/overmind-training--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 overmind-core/overmind --skill overmind-training -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install overmind-core/overmind overmind-training --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/overmind/skills/overmind-training .gemini/skills/overmind-training && 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 "overmind-training" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-training into .gemini/skills/overmind-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-training", 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 overmind-core/overmind overmind-trainingInstalls 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 overmind-core/overmind --skill overmind-training -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .github/skills && cp -r skills-src/overmind/skills/overmind-training .github/skills/overmind-training && 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 "overmind-training" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-training into .github/skills/overmind-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-training", 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 overmind-core/overmind --skill overmind-training -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install overmind-core/overmind overmind-training --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/overmind/skills/overmind-training .opencode/skills/overmind-training && 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 "overmind-training" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-training into .opencode/skills/overmind-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-training", 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
overmind-training- GitHub stars
- 597
- Token cost
- ~837 tokens
- SKILL.md length
- 402 words
- Files
- 3 (incl. assets)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs.
- The Training surface
- SKILL.md covers Prepare the training contract, Size and price the run and Launch and verify
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Including held-out evaluation and benchmark selection
What it does
Overmind Training is an agent skill from overmind-core/overmind. Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs. Use for the Training surface, including held-out evaluation and benchmark selection; live model activation belongs to Inference.
Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including assets (for example `agents/openai.yaml`).
It sits in AI & LLM Engineering, covering Fine-tuning. The repository describes itself as: The platform for continuously improving AI agents. The licence is AGPL-3.0.
When your agent uses it
- The Training surface
- Including held-out evaluation and benchmark selection
- Live model activation belongs to Inference
Example prompts
- “/overmind-training”
What it can do on your machine
Read from SKILL.md and the folder at commit 3dec73c. 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
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.
Network
No URLs in SKILL.md.
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
Overmind Training loads about 837 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 402 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
The full file from overmind-core/overmind at commit 3dec73c, republished under its AGPL-3.0 licence (© overmind-core). 402 words, ~837 tokens.
Download SKILL.mdSave it as
.claude/skills/overmind-training/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- overmind-training
- description
- Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs. Use for the Training surface, including held-out evaluation and benchmark selection; live model activation belongs to Inference.
Overmind Training
Start with list_projects and choose the intended accessible project. For an
account connection, pass its project_id on every project tool and resource
URI query; follow returned links. Project API keys retain their narrower access.
Produce or inspect a trained model with an explicit data, evaluation and cost
contract. Use the chosen MCP project. For an existing job, start with
overmind://finetunes/{job_id} and its finetune_job status; do not relaunch it.
Prepare the training contract
Prefer the native finetune-capability prompt with the selected dataset and
optional capability. Resolve datasets with list_datasets; inspect and query
the exact train and held-out eval cells. Inspect whole-frame task families and
workshop findings rather than assuming a sample describes the whole corpus.
Use get_model_catalog for initial model discovery, then
check_finetune_readiness for the selected dataset. A capability is optional;
held-out evaluation data and an applicable eval set are required. Use the
returned requirements to identify technical blockers. Quality findings,
overlap and incomplete semantic reviews remain visible advisory warnings.
Read benchmark_model on the capability when comparing with an incumbent.
set_benchmark_model changes future benchmark selection, not live serving or
existing jobs. Use it only for a requested benchmark change. New jobs pin their
benchmark selection and readable dataset versions.
Show full SKILL.md (202 more words)Show less
Size and price the run
For Modal training, call prepare_training_data for the chosen model, context
length and cell, then poll the returned training_preparation job. Inspect
exact token counts, supervised content and incompatible rows. Send concrete
source-row repairs to message_dataset_agent; keep model-specific preprocessing
in Training. Reprepare a changed cell rather than reusing a stale report.
Use estimate_finetune and evaluation readiness to present training plus
before/after evaluation spend. Each selected evaluation uses the full pinned
eval dataset. Context warnings do not automatically block launch or change
model selection. An approved preview's judge_model becomes
eval_judge_model on start_finetune; omission preserves the set's judges.
Launch and verify
Launch only the authorized model/configuration with start_finetune. Keep the
selected data, benchmark, evaluator choices and expected spend in the receipt.
Poll get_job(kind=finetune_job, id=...), then inspect the linked deployment
separately. Training completion, evaluation completion and serving readiness
are distinct outcomes.
Report measured before/after results with trust flags and any unresolved
preparation findings. A successful training job does not authorize activation
or a repository model swap. For requested checkpoint export, use
download-checkpoint or the overmind://checkpoint-download CLI handoff.
Open training under the project's Console base with its projectId for the
visual job dashboard. Retain the exact job and deployment IDs in the report.
© overmind-core, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (assets) in overmind/skills/overmind-training of overmind-core/overmind.
- SKILL.md
- agents/openai.yaml
- assets/icon.png
Open the folder on GitHubat commit 3dec73c
Compare with similar skills
Overmind Training 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 |
|---|---|---|---|---|---|---|
| Overmind Training this skillovermind-core/overmind | 597 | — | ~837 | Automated safety check: Pass | AGPL-3.0 | |
| 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 | 915 | 2 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Train RlOpenPipe/ART | 11k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Hugging Face LLM Trainer
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.
- Official
Sentence-Transformers Training Router
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.
- Official
Dataset Evaluation
awslabs/agent-plugins
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).
Train Rl
OpenPipe/ART
RL training reference for the ART framework. An agent skill from OpenPipe/ART.
Qwopus27b Rl Training
R6410418/Jackrong-llm-finetuning-guide
Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.
More from overmind-core/overmind
All 20 skills in this repoAPI Endpoints
overmind-core/overmind
End-to-end workflow for adding or changing a backend API endpoint — which module the serializer and view belong in, URL registration, OpenAPI client regeneration, and typed consumption from the…
Finetuning Model Onboarding
overmind-core/overmind
Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…
Frontend Design
overmind-core/overmind
Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.
MCP
overmind-core/overmind
End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, and required…
PR Etiquette
overmind-core/overmind
How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…
Seed Demo Data
overmind-core/overmind
Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.
Related
Categories
Questions about Overmind Training
What does Overmind Training do?
Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs. Overmind Training is an agent skill from overmind-core/overmind. Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs.
When should I use Overmind Training?
Overmind Training fits situations like: the Training surface; including held-out evaluation and benchmark selection; live model activation belongs to Inference.
How do I install Overmind Training in Claude Code?
Run `npx skills add overmind-core/overmind --skill overmind-training -a claude-code`. Or copy the skill folder (overmind/skills/overmind-training in overmind-core/overmind) into .claude/skills/overmind-training in your project. Claude Code loads it when a task matches its description.
How do I install Overmind Training in Codex?
Run `npx skills add overmind-core/overmind --skill overmind-training -a codex`. Or copy the skill folder (overmind/skills/overmind-training in overmind-core/overmind) into .agents/skills/overmind-training in your project. Codex loads it when a task matches its description.
Can I use Overmind Training 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 overmind-core/overmind --skill overmind-training -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/overmind-training, .gemini/skills/overmind-training, .github/skills/overmind-training and .opencode/skills/overmind-training in your project.
What does Overmind Training need to run?
SKILL.md names no scripts, command-line tools or credentials: Overmind Training is instructions for the agent only.
Does Overmind Training access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Overmind Training 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 Overmind Training use?
Overmind Training is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Overmind Training use?
About 837 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Overmind Training?
Skills that share tags, products or a category with Overmind Training: 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, 915 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Overmind Training?
overmind-core (a GitHub organization) maintains it in overmind-core/overmind, which has 597 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.
Source: overmind-core/overmind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.