Instruction Tuning Collection

◆

◆

◆

◆

📦Normal

★★★★★

“Implement a ChatGPT-like LLM in PyTorch from scratch, step by step”

◆

◆

◆

◆

🔮Psychic

★★★★

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

◆

◆

◆

◆

🔮Psychic

★★★★

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

◆

◆

◆

◆

📦Normal

★★★

“:sparkles::sparkles:Latest Advances on Multimodal Large Language Models”

◆

◆

◆

◆

🔮Psychic

★★★

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

◆

◆

◆

◆

🔮Psychic

★★★

“Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷”

◆

◆

◆

◆

🔮Psychic

★★

“Aligning pretrained language models with instruction data generated by themselves.”

◆

◆

◆

◆

🔥Flame

★★

“Instruction Tuning with GPT-4”

◆

◆

◆

◆

🔮Psychic

★★

“Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model”

◆

◆

◆

◆

🔮Psychic

★★

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

◆

◆

◆

◆

📦Normal

★★

“总结Prompt&LLM论文，开源数据&模型，AIGC应用”

◆

◆

◆

◆

🔮Psychic

★★

“🦦 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.”

◆

◆

◆

◆

🔮Psychic

★★

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

◆

◆

◆

◆

📦Normal

★★

“We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！”

◆

◆

◆

◆

🔮Psychic

★★

“mPLUG-Owl: The Powerful Multi-modal Large Language Model Family”

◆

◆

◆

◆

🔮Psychic

★★

“[ECCV2024] Video Foundation Models & Data for Multimodal Understanding”

◆

◆

◆

◆

🔮Psychic

★★

“Cambrian-1 is a family of multimodal LLMs with a vision-centric design.”

◆

◆

◆

◆

🔮Psychic

★★

“Synthetic data curation for post-training and structured data extraction”