EasyRLHF

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

The official GitHub page for the survey paper "A Survey of Large Language Models".

Aligning pretrained language models with instruction data generated by themselves.

Instruction Tuning with GPT-4

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

Align Anything: Training All-modality Model with Feedback

? Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

【EMNLP 2024?】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection