Roadmap
We’re continuously expanding AITraining’s capabilities. Here’s what’s currently supported and what’s coming next.Currently Supported
LLM Training
- SFT - Supervised Fine-Tuning for instruction following
- DPO - Direct Preference Optimization
- ORPO - Odds Ratio Preference Optimization
- PPO - Proximal Policy Optimization (RL)
- Reward Modeling - Train reward models for RLHF
- Knowledge Distillation - Transfer knowledge from larger models
Text Tasks
- Text Classification - Sentiment, spam detection, categorization
- Token Classification - NER, POS tagging, entity extraction
- Sequence-to-Sequence - Translation, summarization
- Extractive QA - Answer questions from context
- Sentence Transformers - Semantic similarity embeddings
Vision Tasks
- Image Classification - Categorize images into labels
- Image Regression - Predict continuous values from images
- Object Detection - Locate and identify objects in images
- Vision-Language Models - Multimodal image+text tasks
Tabular Data
- XGBoost - Gradient boosting
- LightGBM - Fast gradient boosting
- Random Forest - Ensemble decision trees
- CatBoost - Categorical feature handling
- ExtraTrees - Extremely randomized trees
Reinforcement Learning
- PPO Trainer - Proximal Policy Optimization for LLMs
- DPO Trainer - Direct Preference Optimization
- Reward Models - Standard, pairwise, and multi-objective
- RL Environments - Text generation, math problems, code generation
- Async Forward-Backward Pipeline - Efficient training pipeline
Planned Training Tasks
Vision Tasks (Planned)
| Task | Description | Status |
|---|---|---|
| Image Segmentation | Pixel-level labeling for medical imaging, satellite analysis, background removal | Planned |
| Semantic Segmentation | Scene understanding with class labels per pixel | Planned |
| Instance Segmentation | Detect and segment individual object instances | Planned |
| Panoptic Segmentation | Combined semantic + instance segmentation | Planned |
Time Series & Forecasting (Planned)
| Task | Description | Status |
|---|---|---|
| Time Series Forecasting | Predict future values (stock prices, demand, weather) | Planned |
| Anomaly Detection | Identify outliers in sequential data | Planned |
| Time Series Classification | Classify sequences (ECG, sensor data, activity recognition) | Planned |
Additional ML Algorithms (Planned)
| Task | Description | Status |
|---|---|---|
| Support Vector Machines | SVMs for classification and regression | Planned |
| K-Nearest Neighbors | Instance-based learning | Planned |
| Gaussian Processes | Probabilistic predictions with uncertainty | Planned |
| Neural Networks (sklearn) | Simple MLPs for tabular data | Planned |
Specialized LLM Training (Planned)
| Task | Description | Status |
|---|---|---|
| Code LLM Fine-tuning | Specialized training for code generation models | Planned |
| Math Reasoning | Train models for mathematical problem solving | Planned |
| Multi-turn Dialogue | Enhanced conversation modeling | Planned |
| Tool Use / Function Calling | Train models to use external tools | Planned |
| Agentic Behaviors | Train models for autonomous task completion | Planned |
Audio & Speech (Planned)
| Task | Description | Status |
|---|---|---|
| Speech Recognition (ASR) | Automatic speech-to-text | Planned |
| Text-to-Speech (TTS) | Voice synthesis and cloning | Planned |
| Audio Classification | Sound event detection, music genre classification | Planned |
| Speaker Diarization | Identify who spoke when | Planned |
Multimodal (Planned)
| Task | Description | Status |
|---|---|---|
| Video Understanding | Action recognition, video captioning | Planned |
| Document AI | Layout analysis, form understanding | Planned |
| Chart/Graph Understanding | Extract data from visualizations | Planned |
| 3D Vision | Point cloud processing, depth estimation | Planned |
Specialized Domains (Planned)
| Task | Description | Status |
|---|---|---|
| Medical/Clinical NLP | HIPAA-aware training for healthcare | Planned |
| Legal Document Analysis | Contract review, case law search | Planned |
| Scientific Literature | Paper parsing, citation analysis | Planned |
| Financial Analysis | Sentiment, risk assessment, report generation | Planned |
Planned Features
Training Enhancements
- Ray Tune integration for distributed sweeps
- Curriculum learning support
- Continual learning / catastrophic forgetting prevention
- Mixture of Experts (MoE) fine-tuning
- Speculative decoding training
Infrastructure
- Full TUI (Terminal User Interface) wizard
- Web-based training UI
- Kubernetes deployment templates
- AWS/GCP/Azure marketplace images
Evaluation
- Automated red-teaming
- Bias and fairness benchmarks
- Domain-specific evaluation suites
- Human preference collection interface
Vote for Features
Want to influence our priorities? Let us know what matters most to you:GitHub Discussions
Vote on feature requests and propose new ideas
Discord Community
Join the discussion and share your use cases
Contributing
Interested in helping build these features? We welcome contributions:- Core Development: Python, PyTorch, Transformers
- Documentation: Help us document new features
- Testing: Test new trainers and report issues
- Examples: Share your training recipes