peft-fine-tuning

21.8k

davila7

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train less than 1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

quantizing-models-bitsandbytes

21.8k

davila7

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

llama-factory

21.8k

davila7

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

gptq

21.8k

davila7

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

unsloth

21.8k

davila7

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

implementing-llms-litgpt

21.8k

davila7

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when needing clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

axolotl

21.8k

davila7

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

LLM fine-tuning

29

omer-metin

Use when adapting large language models to specific tasks, domains, or behaviors — covers LoRA, QLoRA, PEFT, instruction tuning, and full fine-tuning strategies. Use when ", " mentioned.

qlora

14

itsmostafa

Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.

mlx

14

itsmostafa

Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.

llm-fine-tuning

10

BagelHole

Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP. Covers dataset prep, training runs, and model export.

peft-fine-tuning

9

TerminalSkills

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when a user asks to fine-tune a language model, train a custom LLM, adapt a model to their data, use LoRA or QLoRA, fine-tune Llama or Mistral, or train a model on consumer GPUs. Covers PEFT methods for 7B-70B parameter models.

optimizing-models

4

gitwalter

LoRA/QLoRA/PEFT fine-tuning workflows with Hugging Face transformers

local-llm-fine-tuning

2

organvm-iv-taxis

Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.

unsloth

AXGZ21

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

axolotl

AXGZ21

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Language Model Fine-Tuner

Eli-yu-first

Fine-tunes language models with LoRA, QLoRA, and full fine-tuning with dataset preparation and evaluation