An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

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

Aligning Large Language Models with Human: A Survey

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.

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

开源SFT数据集整理,随时补充

The offical realization of InstructERC

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

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

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

[NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"

EMNLP'2024: Knowledge Verification to Nip Hallucination in the Bud

Official repository of "Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning"

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

[AAAI 2025]Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity

Finetuning Google's Gemma Model for Translating Natural Language into SQL

Code for Paper (Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity)

Qwen2-VL在文旅领域的LLaMA-Factory微调案例 The case for fine-tuning Qwen2-VL in the field of historical literature and museums

Various LMs/LLMs below 3B parameters (for now) trained using SFT (Supervised Fine Tuning) for several downstream tasks

An LLM challenge to (i) fine-tune pre-trained HuggingFace transformer model to build a Code Generation language model, and (ii) build a retrieval-augmented generation (RAG) application using LangChain