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.
Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings.
Install Training And Distillation
$ npx skills add VectorSpaceLab/AREX-Skill --skill training-and-distillation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill training-and-distillation --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/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation .claude/skills/training-and-distillation && 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 "training-and-distillation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation into .claude/skills/training-and-distillation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-and-distillation", 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/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillationType 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 VectorSpaceLab/AREX-Skill --skill training-and-distillation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill training-and-distillation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation .agents/skills/training-and-distillation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "training-and-distillation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation into .agents/skills/training-and-distillation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-and-distillation", 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 VectorSpaceLab/AREX-Skill --skill training-and-distillation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill training-and-distillation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation .cursor/skills/training-and-distillation && 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 "training-and-distillation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation into .cursor/skills/training-and-distillation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-and-distillation", 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/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation--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 VectorSpaceLab/AREX-Skill --skill training-and-distillation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill training-and-distillation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation .gemini/skills/training-and-distillation && 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 "training-and-distillation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation into .gemini/skills/training-and-distillation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-and-distillation", 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 VectorSpaceLab/AREX-Skill training-and-distillationInstalls 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 VectorSpaceLab/AREX-Skill --skill training-and-distillation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation .github/skills/training-and-distillation && 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 "training-and-distillation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation into .github/skills/training-and-distillation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-and-distillation", 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 VectorSpaceLab/AREX-Skill --skill training-and-distillation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill training-and-distillation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation .opencode/skills/training-and-distillation && 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 "training-and-distillation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation into .opencode/skills/training-and-distillation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-and-distillation", 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
training-and-distillation- GitHub stars
- 331
- Token cost
- ~850 tokens
- SKILL.md length
- 283 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- MIT
At a glance
Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings.
- Tasks mention ColBERT Trainer
- SKILL.md covers Route Tasks, Core API, Bundled Helpers and Training Scope
- Runs Python scripts from its folder
- Fine-tuning checkpoints
What it does
Training And Distillation is an agent skill from VectorSpaceLab/AREX-Skill. Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings. Use when tasks mention ColBERT Trainer, fine-tuning checkpoints, training triples, distillation scores, nway/bsize/accumsteps choices, or training-file validation.
Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/api-reference.md`, `references/training-workflows.md` and `references/troubleshooting.md`).
It sits in AI & LLM Engineering, covering Fine-tuning. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- Tasks mention ColBERT Trainer
- Fine-tuning checkpoints
- Training triples
- Distillation scores
Example prompts
- “/training-and-distillation”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. 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
Ships 2 files in scripts/ (Python), which the agent can run.
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
Training And Distillation loads about 850 tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 283 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); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its MIT licence (© VectorSpaceLab). 283 words, ~850 tokens.
Download SKILL.mdSave it as
.claude/skills/training-and-distillation/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- training-and-distillation
- description
- Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings. Use when tasks mention ColBERT Trainer, fine-tuning checkpoints, training triples, distillation scores, nway/bsize/accumsteps choices, or training-file validation.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
ColBERT Training And Distillation
Use this sub-skill when the user needs to configure or troubleshoot ColBERT training. It covers the Trainer API, JSONL examples/triples, scored distillation examples, resource planning, and safe helper scripts. Do not use it for post-training indexing/search, evaluation benchmarks, or tokenizer internals.
Route Tasks
- For a runnable training starting point, read
references/training-workflows.mdand generate a script withscripts/training_template.py. - For API details, checkpoint precedence, data shapes, and config fields, use
references/api-reference.md. - For validation before GPU work, run
scripts/validate_training_files.pyagainst triples, queries, and collection files. - For launch, data, scored-example, OOM, and dependency failures, use
references/troubleshooting.md. - For indexing or searching a trained checkpoint, switch to the
indexing-and-searchsub-skill. - For ranking metrics, LoTTE/MS MARCO evaluation, qrels, and dataset conventions outside training, switch to the
data-and-evaluationsub-skill. - For tokenization behavior, max lengths, dimensions, and model architecture details, switch to the
modeling-and-tokenizationsub-skill.
Core API
The verified public training entry point is:
from colbert import Trainer
from colbert.infra import ColBERTConfig, Run, RunConfig
with Run().context(RunConfig(nranks=1, experiment="my-training-run")):
config = ColBERTConfig(bsize=32, nway=2, accumsteps=1)
trainer = Trainer(triples="triples.train.jsonl", queries="queries.train.tsv", collection="collection.tsv", config=config)
trainer.train(checkpoint="bert-base-uncased")
checkpoint_path = trainer.best_checkpoint_path()Important behavior: Trainer.train(checkpoint=...) is the checkpoint source used by training. If ColBERTConfig(checkpoint=...) is also set, the explicit train(checkpoint=...) argument wins.
Bundled Helpers
scripts/validate_training_files.pychecks JSONL triples/examples plus query and collection TSV files for parseability, ID references, duplicate IDs, scored-example shape, and likelynwaymismatches before launching training.scripts/training_template.pyemits a safe argparse-based ColBERT training script template and warns about resource choices such asbsize % nranks, largenway, and GPU expectations.
Training Scope
Basic ColBERTv1-style training usually uses unscored [qid, positive_pid, negative_pid] JSONL examples with nway=2. Advanced ColBERTv2-style training often uses many-way examples such as 64-way scored JSONL, use_ib_negatives=True, distillation_alpha, doc_maxlen=180, dim=128, and a source checkpoint such as colbert-ir/colbertv1.9.
Practical training requires CUDA/GPU resources. CPU-only environments are useful for imports, file validation, and template generation, but real fine-tuning, distillation scoring, and distributed training are GPU-heavy.
© VectorSpaceLab, MIT. 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 5 other files (scripts, references) in skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/api-reference.md
- references/training-workflows.md
- references/troubleshooting.md
- scripts/training_template.py
- scripts/validate_training_files.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Training And Distillation 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 |
|---|---|---|---|---|---|---|
| Training And Distillation this skillVectorSpaceLab/AREX-Skill | 331 | — | ~850 | Automated safety check: Pass | MIT | |
| Sentence-Transformers Training Routerhuggingface/skills | 11k | 1 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Train RlOpenPipe/ART | 11k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~830 | Automated safety check: Pass | Apache-2.0 | |
| Dataset Evaluationawslabs/agent-plugins | 916 | 1 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Train SftOpenPipe/ART | 11k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
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.
- Official
Dataset Evaluation
awslabs/agent-plugins
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).
Train Sft
OpenPipe/ART
SFT training reference for the ART framework. An agent skill from OpenPipe/ART.
Fine Tuning With Trl
Orchestra-Research/AI-Research-SKILLs
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
More from VectorSpaceLab/AREX-Skill
All 157 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Categories
Questions about Training And Distillation
What does Training And Distillation do?
Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings. Training And Distillation is an agent skill from VectorSpaceLab/AREX-Skill. Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings.
When should I use Training And Distillation?
Training And Distillation fits situations like: tasks mention ColBERT Trainer; fine-tuning checkpoints; training triples; distillation scores.
How do I install Training And Distillation in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill training-and-distillation -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation in VectorSpaceLab/AREX-Skill) into .claude/skills/training-and-distillation in your project. Claude Code loads it when a task matches its description.
How do I install Training And Distillation in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill training-and-distillation -a codex`. Or copy the skill folder (skills/repositories/repo-skills/colbert/sub-skills/training-and-distillation in VectorSpaceLab/AREX-Skill) into .agents/skills/training-and-distillation in your project. Codex loads it when a task matches its description.
Can I use Training And Distillation 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 VectorSpaceLab/AREX-Skill --skill training-and-distillation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/training-and-distillation, .gemini/skills/training-and-distillation, .github/skills/training-and-distillation and .opencode/skills/training-and-distillation in your project.
What does Training And Distillation need to run?
Going by SKILL.md and its folder, Training And Distillation needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Training And Distillation 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 Training And Distillation 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Training And Distillation use?
Training And Distillation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Training And Distillation use?
About 850 tokens (SKILL.md is roughly 3.4k 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 3.8k tokens, read only when the agent opens those files.
What are the alternatives to Training And Distillation?
Skills that share tags, products or a category with Training And Distillation: Sentence-Transformers Training Router (huggingface/skills, 11k stars), Train Rl (OpenPipe/ART, 11k stars), Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Dataset Evaluation (awslabs/agent-plugins, 916 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Training And Distillation?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 331 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.