supervised-finetuning

InternLM/InternLM-XComposer

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

GaryYufei/AlignLLMHumanSurvey

Aligning Large Language Models with Human: A Survey

Tebmer/Awesome-Knowledge-Distillation-of-LLMs

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.

magpie-align/magpie

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

chaoswork/sft_datasets

开源SFT数据集整理,随时补充

LIN-SHANG/InstructERC

The offical realization of InstructERC

sail-sg/sdft

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

yyDing1/ScaleQuest

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

NVlabs/catk

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

ZhengxiangShi/InstructionModelling

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

fanqiwan/KCA

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

inst-it/inst-it

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

BUAADreamer/MLLM-Finetuning-Demo

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

quanshr/AugCon

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

bhattbhavesh91/google-gemma-finetuning-n2sql

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

liziniu/GEM

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

BUAADreamer/Qwen2-VL-History

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

KwokHing/AI-Planet-LLM-Bootcamp-Challenge

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

sovit-123/lm_sft

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

nsrinidhibhat/fine-tune-llama-2

This project streamlines the fine-tuning process, enabling you to leverage Llama-2's capabilities for your own projects.

tien02/llm-math

Fine tune Large Language Model on Mathematic dataset

rasyosef/phi-2-sft-and-dpo

Notebooks to create an instruction following version of Microsoft's Phi 2 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

18907305772/KCA

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

asifhaider/LLM-Finetuning-Prompting-Project

Python Project Sample for Demonstration

ChryssaNab/ECG-Heartbeat-Classification

Binary classification of pathological heartbeats from ECG signals using 1D CNNs in PyTorch

codelion/ellora

Enhancing LLMs with LoRA

KindYAK/kaggle_20q

Solution for Kaggle 20 Questions competetion

rasyosef/phi-1_5-instruct

Notebooks to create an instruction following version of Microsoft's Phi 1.5 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

sunnynevarekar/LLM_Mistral_7b_SFT

Finetune Mistral 7b v1.0 on custom dataset

AliBakly/EPFLLaMA

EPFLLaMA: A lightweight language model fine-tuned on EPFL curriculum content. Specialized for STEM education and multiple-choice question answering. Implements advanced techniques like SFT, DPO, and quantization.

jmaczan/c-137

🦙 Llama 2 7B fine-tuned to revive Rick

quazirab/fine-tuning-llama-3.1-on-medical-questionnaires

Llama 3.1 Fine Tuning

eliashornberg/EPFLLaMA

EPFLLaMA: A lightweight language model fine-tuned on EPFL curriculum content. Specialized for STEM education and multiple-choice question answering. Implements advanced techniques like SFT, DPO, and quantization.

thisisHJLee/RLHF