47network/model-trainer

Model Trainer Skill

Fine-tunes small open models (Qwen3-4B, Gemma-2B, etc.) on domain-specific data using LoRA/QLoRA adapters.

Architecture

Training Data Sources → Data Prep → LoRA Fine-Tune → Evaluation → Export to LiteLLM
     ↓                                    ↓                          ↓
Conversation Logs            HuggingFace PEFT             LiteLLM Model Registry
RAG Documents                bitsandbytes QLoRA            Local Model Fleet
File Uploads                 Transformers Trainer
Inline Samples

Pre-Built Recipes

| Recipe | Base Model | Purpose | Epochs | |-----------------------|-----------------|--------------------------------------------|--------| | writing_style | Qwen2.5-4B | Match user's tone, vocabulary, structure | 3 | | codebase_conventions | Qwen2.5-4B | Learn project patterns and naming | 2 | | domain_vocabulary | Qwen2.5-4B | Domain-specific terms and knowledge | 5 |

Data Formats

• conversation: Chat messages [{role, content}]
• instruction: Alpaca-style {instruction, output}
• completion: Raw text continuation
• preference: DPO-style {prompt, chosen, rejected}