Fine-tune small open models with LoRA/QLoRA adapters for domain-specific workflows.
npx skills add https://github.com/47network/Sven --skill model-trainer-47network
Please help me install this Agent Skill. Skill: model-trainer Source: https://github.com/47network/Sven/tree/main/skills/ai-agency/model-trainer Command: npx skills add https://github.com/47network/Sven --skill model-trainer-47network
Fine-tuning domain-specific data for small open models using LoRA/QLoRA adapters to produce production-ready variants.
Provide data_sources or samples and start a training job.
High-intent search queries and answers about installing and using this skill.
To fine-tune small open models with LoRA or QLoRA adapters, provide data sources or samples to start a training job using pre-built recipes for domain-specific data. This produces production-ready adapter variants.
For QLoRA adapter training, you can fine-tune small open models such as Qwen3-4B and Gemma-2B. These models are targeted for domain-specific workflows across logs, codebases, and curated datasets.
You manage a LoRA fine-tuning job lifecycle using actions to create, get, list, and cancel jobs. This tracks training progress from initiation through adapter export.
Yes, you can export fine-tuned LoRA and QLoRA adapters directly to LiteLLM for immediate use. This enables production-ready variants to be deployed in enterprise knowledge and codebase-aware tools.
Available recipes for domain-specific model training include pre-built configurations for writing style, codebase conventions, and domain vocabulary. These recipes streamline adapting small open models to specialized data.
Rawgrowth-ConsultingFine-tune LLMs with YAML-config driven Axolotl workflows.
Marwan78888Configure LoRA/QLoRA fine-tuning workflows with JSONL datasets and hyperparameters.
JeffallanAutomate fine-tuning workflows for large language models using LoRA/QLoRA and PEFT methods.
eddieluengTrain low-rank LoRA/QLoRA adapters for parameter-efficient fine-tuning of large language models.
