supervised-finetuning

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

Aligning Large Language Models with Human: A Survey

开源SFT数据集整理,随时补充

✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork

Enhancing LLMs with LoRA

[EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models

LogLLM: Log-based Anomaly Detection Using Large Language Models (system log anomaly detection)

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

The offical realization of InstructERC

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

[ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.

[ICML'26 Spotlight] What is the right loss function for LLM supervised finetuning?

使用LLaMA-Factory微调多模态大语言模型的示例代码 Demo of Finetuning Multimodal LLM with LLaMA-Factory

Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)

(NeurIPS 2025 🔥) Official implementation for "Efficient Multi-modal Large Language Models via Progressive Consistency Distillation"

The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":

[ICLR 2026] Official implementation of " 🦙 TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models"