Method
QLoRA
LoRA on a 4-bit quantized base model.
7 cases from 7 companies apply QLoRA. 1 was checked in an online A/B test; 2 report results in production.
Typical tasks: Rank search results, Reduce ML cost, Label data with LLMs, Build an assistant over internal docs and 1 more. Companies: Sber, VTB, Pinterest, Mercari, CFT and 2 more. Often combined with: RAG, Supervised fine-tuning, Knowledge distillation, BM25, Reinforcement learning and 16 more.
| The Search of the Future | general | 2026-05 | |
| Distilling Qwen for Meeting Minutes | banking | 2025-05 | |
Building RAG-Like Systems for Few-Shot Intent Classification in Narrow Domains![]() | ![]() | banking | 2025-05 |
| Improving Pinterest Search Relevance Using Large Language Models | social | 2025-04 | |
How Can OpenAI Help If You Use Open-Source LLMs?![]() | ![]() | edtech | 2024-11 |
Fine-Tuning an LLM to Extract Dynamically Specified Attributes![]() | ![]() | marketplace | 2024-09 |
| LLM Practice Without ChristofariCF | CF | general | 2024-05 |


