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.
Agent skill
Memory Estimation
by Red-Hat-AI-Innovation-Team in Red-Hat-AI-Innovation-Team/training_hub
A skill your agent uses when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training.
Install Memory Estimation
$ npx skills add Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Red-Hat-AI-Innovation-Team/training_hub memory-estimation --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/Red-Hat-AI-Innovation-Team/training_hub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/memory-estimation .claude/skills/memory-estimation && 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 "memory-estimation" agent skill from https://github.com/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimation into .claude/skills/memory-estimation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-estimation", 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/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimationType 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 Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Red-Hat-AI-Innovation-Team/training_hub memory-estimation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/memory-estimation .agents/skills/memory-estimation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "memory-estimation" agent skill from https://github.com/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimation into .agents/skills/memory-estimation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-estimation", 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 Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Red-Hat-AI-Innovation-Team/training_hub memory-estimation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/memory-estimation .cursor/skills/memory-estimation && 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 "memory-estimation" agent skill from https://github.com/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimation into .cursor/skills/memory-estimation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-estimation", 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/Red-Hat-AI-Innovation-Team/training_hub.git --path .claude/skills/memory-estimation--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 Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Red-Hat-AI-Innovation-Team/training_hub memory-estimation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/memory-estimation .gemini/skills/memory-estimation && 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 "memory-estimation" agent skill from https://github.com/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimation into .gemini/skills/memory-estimation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-estimation", 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 Red-Hat-AI-Innovation-Team/training_hub memory-estimationInstalls 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 Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hub.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/memory-estimation .github/skills/memory-estimation && 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 "memory-estimation" agent skill from https://github.com/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimation into .github/skills/memory-estimation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-estimation", 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 Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Red-Hat-AI-Innovation-Team/training_hub memory-estimation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/memory-estimation .opencode/skills/memory-estimation && 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 "memory-estimation" agent skill from https://github.com/Red-Hat-AI-Innovation-Team/training_hub/tree/main/.claude/skills/memory-estimation into .opencode/skills/memory-estimation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-estimation", 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
memory-estimation- GitHub stars
- 100
- Token cost
- ~393 tokens
- SKILL.md length
- 137 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training.
- Works in 3 steps: Check Environment → Run Estimation → Present Results
- The user wants to estimate GPU memory (VRAM) requirements for a training configuration
- SKILL.md covers Step 1: Check Environment, Step 2: Run Estimation, Step 3: Present Results and Estimation Methods
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Memory Estimation is an agent skill from Red-Hat-AI-Innovation-Team/training_hub. Use when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training.
Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Fine-tuning. The repository describes itself as: An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques. The licence is Apache-2.0.
When your agent uses it
- The user wants to estimate GPU memory (VRAM) requirements for a training configuration
- Check if a model will fit on their GPUs
- Plan GPU allocation for training
Example prompts
- “/memory-estimation”
Requirements
- Pre-approved tools (allowed-tools): Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_estimate.sh:*), Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh:*)
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 511a905. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_estimate.sh:*)Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh:*)
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
Memory Estimation loads about 393 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 137 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 Red-Hat-AI-Innovation-Team/training_hub at commit 511a905, republished under its Apache-2.0 licence (© Red-Hat-AI-Innovation-Team). 137 words, ~393 tokens.
Download SKILL.mdSave it as
.claude/skills/memory-estimation/SKILL.md (or your agent's skills folder).- name
- memory-estimation
- description
- Use when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training.
- allowed-tools
- Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_estimate.sh:*), Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh:*)
GPU Memory Estimation
Estimate GPU VRAM requirements before committing to a training run.
Step 1: Check Environment
"${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh"If library=missing, tell the user to install training_hub first via the setup-guide skill.
Step 2: Run Estimation
Execute the estimation script with user-provided parameters or config defaults:
"${CLAUDE_PLUGIN_ROOT}/scripts/th_estimate.sh" $ARGUMENTSStep 3: Present Results
Parse the JSON output and present clearly:
- Memory estimates — Show low/mid/high VRAM estimates in GB
- GPU fit — Report whether the configuration fits on the available GPU(s)
- Recommendations — If memory is tight, suggest:
- Reduce
max_seq_len(e.g., 4096 -> 2048) - Reduce
effective_batch_size - Switch to LoRA or QLoRA for lower memory
- Add more GPUs for data parallelism
- Reduce
Estimation Methods
| Method | For | Estimator |
|---|---|---|
basic | SFT, GRPO | BasicEstimator |
osft | OSFT | OSFTEstimator |
lora | LoRA-SFT, LoRA-GRPO | LoRAEstimator |
qlora | Quantized LoRA | QLoRAEstimator |
If no method is specified, the script infers it from the configured algorithm.
© Red-Hat-AI-Innovation-Team, 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
Files
Just SKILL.md in .claude/skills/memory-estimation of Red-Hat-AI-Innovation-Team/training_hub.
Open the folder on GitHubat commit 511a905
Compare with similar skills
Memory Estimation 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 |
|---|---|---|---|---|---|---|
| Memory Estimation this skillRed-Hat-AI-Innovation-Team/training_hub | 100 | — | ~393 | Automated safety check: Pass | Apache-2.0 | |
| 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 Red-Hat-AI-Innovation-Team/training_hub
Setup Guide
Red-Hat-AI-Innovation-Team/training_hub
A skill your agent uses when the user wants to set up LLM training for the first time, or when traininghub is not yet installed/configured in the current environment.
Training Hub Guide
Red-Hat-AI-Innovation-Team/training_hub
Guides users through LLM post-training with Training Hub, including installation, algorithm selection (SFT, OSFT, LoRA), hyperparameter tuning, troubleshooting OOM errors, interpreting loss curves…
Training Guide
Red-Hat-AI-Innovation-Team/training_hub
A skill your agent uses when the user wants to run a training job using a saved configuration.
Related
Categories
Questions about Memory Estimation
What does Memory Estimation do?
A skill your agent uses when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training. Memory Estimation is an agent skill from Red-Hat-AI-Innovation-Team/training_hub. Use when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training.
When should I use Memory Estimation?
Memory Estimation fits situations like: the user wants to estimate GPU memory (VRAM) requirements for a training configuration; check if a model will fit on their GPUs; plan GPU allocation for training.
How do I install Memory Estimation in Claude Code?
Run `npx skills add Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a claude-code`. Or copy the skill folder (.claude/skills/memory-estimation in Red-Hat-AI-Innovation-Team/training_hub) into .claude/skills/memory-estimation in your project. Claude Code loads it when a task matches its description.
How do I install Memory Estimation in Codex?
Run `npx skills add Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a codex`. Or copy the skill folder (.claude/skills/memory-estimation in Red-Hat-AI-Innovation-Team/training_hub) into .agents/skills/memory-estimation in your project. Codex loads it when a task matches its description.
Can I use Memory Estimation 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 Red-Hat-AI-Innovation-Team/training_hub --skill memory-estimation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-estimation, .gemini/skills/memory-estimation, .github/skills/memory-estimation and .opencode/skills/memory-estimation in your project.
What does Memory Estimation need to run?
SKILL.md names no scripts, command-line tools or credentials: Memory Estimation is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_estimate.sh:*), Bash(${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh:*).
Does Memory Estimation 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 Memory Estimation 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 Memory Estimation use?
Memory Estimation 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.
How many tokens does Memory Estimation use?
About 393 tokens (SKILL.md is roughly 1.6k 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 Memory Estimation?
Skills that share tags, products or a category with Memory Estimation: 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 Memory Estimation?
Red-Hat-AI-Innovation-Team (a GitHub organization) maintains it in Red-Hat-AI-Innovation-Team/training_hub, which has 100 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.
Source: Red-Hat-AI-Innovation-Team/training_hub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.