Wizard Commands Reference

The AITraining wizard supports various commands to help you navigate, search, and configure your training job. These commands work at any prompt:

Command	Shortcut	Description
`:back`		Go back to the previous step
`:help`	`?`, `:h`	Show detailed help for the current prompt
`:exit`	`:quit`	Cancel the wizard and exit

Using :back

You can go back at any point to change previous answers:

Model (number, HF ID, or command): :back
↩️ Going back to dataset selection...

Dataset (number, HF ID, or command):

Using :help

Every prompt has contextual help:

Training split name [train]: :help

ℹ️  Help
  Dataset splits are named subsets of your data.

  Common split names:
    • 'train' - Training data (most common)
    • 'test' - Test/evaluation data
    • 'validation' or 'valid' - Validation data

  Note: This is NOT asking for a percentage split (like 80/20).
  It's asking for the exact name of the split in your dataset.

Training split name [train]:

Catalog Commands

These commands work when browsing models or datasets:

Command	Description
`/search <query>`	Search for models/datasets by name
`/sort`	Change sorting (trending, downloads, likes, recent)
`/filter`	Filter models by size (models only)
`/refresh`	Clear cache and reload the list

/search

Find specific models or datasets:

Model (number, HF ID, or command): /search llama

Popular models (trending):
  1. meta-llama/Llama-3.2-1B (1B)
  2. meta-llama/Llama-3.2-3B (3B)
  3. meta-llama/Llama-3.1-8B (8B)
  4. meta-llama/Llama-3.1-70B (70B)
  ...

Search examples:

/search gemma - Find Gemma models
/search code - Find code-focused models
/search alpaca - Find Alpaca-style datasets
/search conversation - Find conversation datasets

/sort

Change how results are ordered:

Model (number, HF ID, or command): /sort
Sort options: [T]rending [D]ownloads [L]ikes [R]ecent
Sort by [T]: D

Sort Option	Key	Description
Trending	T	What’s popular right now
Downloads	D	Most downloaded all-time
Likes	L	Most liked by the community
Recent	R	Newest additions

/filter

Filter models by parameter count (only works for models, not datasets):

Model (number, HF ID, or command): /filter
Filter size: [A]ll [S]mall(<3B) [M]edium(3-10B) [L]arge(>10B)
Filter size [A]: S

Filter	Key	Size Range	Typical Hardware
All	A	No filter	Any
Small	S	< 3B parameters	MacBook, consumer GPU
Medium	M	3B - 10B parameters	Gaming GPU, workstation
Large	L	> 10B parameters	Cloud GPU, multi-GPU

/refresh

Clear the cache and fetch fresh data:

Model (number, HF ID, or command): /refresh
Cache cleared.

Popular models (trending):
  ...

Selection Methods

When choosing a model or dataset, you have several options:

By Number

Select from the displayed list:

Popular models (trending):
  1. google/gemma-3-270m (270M)
  2. google/gemma-2-2b (2B)
  3. meta-llama/Llama-3.2-1B (1B)

Model (number, HF ID, or command): 2
✓ Model: google/gemma-2-2b

By HuggingFace ID

Type the full model/dataset ID:

Model (number, HF ID, or command): mistralai/Mistral-7B-v0.3
✓ Model: mistralai/Mistral-7B-v0.3

By Local Path

Point to a local directory:

Dataset (number, HF ID, or command): ./my_training_data
✓ Dataset: ./my_training_data

Input Conventions

Defaults

Values in [brackets] are defaults. Press Enter to accept:

Project name [my-llm-project]: ↵
✓ Project: my-llm-project

Required Fields

Fields marked [REQUIRED] must be filled:

Prompt column name [REQUIRED] [prompt]: ↵
❌ This field is required for DPO/ORPO training.
Prompt column name [REQUIRED] [prompt]: instruction
✓

Yes/No Questions

Answer with y/yes or n/no:

Configure advanced parameters? [y/N]: y

Enable LoRA? [Y/n]: ↵
✓ LoRA enabled (default)

Capitalized letter indicates the default:

[Y/n] - Default is Yes
[y/N] - Default is No

Keyboard Shortcuts

Key	Action
Enter	Accept default or confirm input
Ctrl+C	Cancel wizard (same as `:exit`)
Arrow Up/Down	Scroll through numbered options (if supported)

Advanced Parameters

When configuring advanced parameters, the wizard groups them:

⚙️  Training Hyperparameters

Configure Training Hyperparameters parameters? [y/N]: y

epochs [1]:
batch_size [2]:
lr [3e-5]:

Each group can be configured independently:

Group	Contains
Training Hyperparameters	epochs, batch_size, lr, warmup_ratio
PEFT/LoRA	peft, lora_r, lora_alpha, quantization
DPO/ORPO	dpo_beta, max_prompt_length
Hub Integration	push_to_hub, username, token
Knowledge Distillation	teacher_model, distill_temperature
Hyperparameter Sweep	use_sweep, sweep_n_trials
Enhanced Evaluation	use_enhanced_eval, eval_metrics
Reinforcement Learning	rl_reward_model_path (PPO only)

Tips

Use :help liberally

Every single prompt has detailed help. If you’re unsure what something means, type :help.

Go back to fix mistakes

Made a wrong choice? Use :back to return to previous steps. Your other answers are preserved.

Search before scrolling

Instead of scrolling through hundreds of models, use /search llama or /search 7b to narrow down.

Filter by your hardware

Not sure which models will work? Use /filter → S (small) to see only models that fit consumer hardware.

Accept defaults for first run

On your first training, accept most defaults. Get something working, then customize.

Command Quick Reference

# Navigation
:back          Go to previous step
:help          Show help for current prompt
:exit          Cancel and exit

# Catalog (models/datasets)
/search query  Search by name
/sort          Change sort order
/filter        Filter by size (models only)
/refresh       Reload list

# Selection
1, 2, 3...     Select by number
google/gemma   Type HuggingFace ID
./my_data      Type local path

# Input
Enter          Accept default
y/n            Yes/No answers
Ctrl+C         Cancel

Getting Started

Understanding Choices

Wizard Commands

Wizard Commands Reference

Navigation Commands

Using :back

Using :help

Catalog Commands

/search

/sort

/filter

/refresh

Selection Methods

By Number

By HuggingFace ID

By Local Path

Input Conventions

Defaults

Required Fields

Yes/No Questions

Keyboard Shortcuts

Advanced Parameters

Tips

Command Quick Reference

​Wizard Commands Reference

​Navigation Commands

​Using :back

​Using :help

​Catalog Commands

​/search

​/sort

​/filter

​/refresh

​Selection Methods

​By Number

​By HuggingFace ID

​By Local Path

​Input Conventions

​Defaults

​Required Fields

​Yes/No Questions

​Keyboard Shortcuts

​Advanced Parameters

​Tips

​Command Quick Reference

Wizard Commands Reference

Navigation Commands

Using :back

Using :help

Catalog Commands

/search

/sort

/filter

/refresh

Selection Methods

By Number

By HuggingFace ID

By Local Path

Input Conventions

Defaults

Required Fields

Yes/No Questions

Keyboard Shortcuts

Advanced Parameters

Tips

Command Quick Reference