Select and configure Unsloth-supported LLM architectures for efficient fine-tuning.
npx skills add https://github.com/cuba6112/skillfactory --skill unsloth-models
Please help me install this Agent Skill. Skill: unsloth-models Source: https://github.com/cuba6112/skillfactory/tree/main/skills/unsloth-models Command: npx skills add https://github.com/cuba6112/skillfactory --skill unsloth-models
This Skill helps users select and configure optimal Unsloth-supported model architectures for fine-tuning, addressing the challenge of choosing the right base model and variant for specific tasks and hardware constraints.
Use the unsloth-models skill to find the best model for reasoning tasks.
High-intent search queries and answers about installing and using this skill.
Choose Instruct models for conversational AI or instruction-following tasks, and Base models for open-ended text completion. This Skill provides decision-making criteria to match model variants with your specific task requirements.
Yes, you can fine-tune large models like DeepSeek-R1 on consumer hardware by leveraging Unsloth's pre-quantized Hub variants and optimized kernels. This Skill guides you to specialized distilled versions that fit limited GPU VRAM.
The best way to configure Llama 4 and Qwen3 is by selecting the appropriate pre-quantized variants and applying Unsloth's optimized kernels. This Skill facilitates informed decisions on model architecture selection for efficient fine-tuning.
Yes, Unsloth works with Hugging Face Hub to provide pre-quantized model variants. This Skill helps you leverage these Hub variants with optimized kernels to achieve efficient fine-tuning on consumer hardware.
You need a distilled version of a large reasoning model when working under strict hardware constraints like limited GPU VRAM. This Skill addresses the need for specialized distilled versions of models like DeepSeek-R1 for consumer hardware.
JeffallanAutomate fine-tuning workflows for large language models using LoRA/QLoRA and PEFT methods.
ScientiaCapitalExport fine-tuned models to GGUF and deploy with vLLM or Ollama.
Mesh-LLMAutomate Windows deployment of Mesh LLM via PowerShell install.ps1.
blueskies1818Fine-tune large language models with reduced VRAM usage and faster training.
