Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
- fine-tuning
- llama
- llm
- peft
98,836 visible repositories in the index
1–24 of 38 · Most stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
AirLLM 2.8T LLM inference with single 4GB GPU
Code and documentation to train Stanford's Alpaca models, and generate the data.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Locally run an Instruction-Tuned Chat-Style LLM
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
TranslatedBELLE: Be Everyone's Large Language model Engine (open-source Chinese conversational large language model)
🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
A collection of prompts, system prompts and LLM instructions
Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
TranslatedRepo for BenCao [original name: HuaTuo (华驼)], Instruction-tuning Large Language Models with Chinese Medical Knowledge.
Aligning pretrained language models with instruction data generated by themselves.
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
🦦 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 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
My own Prompts for Custom instructions ChatGPT
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!
the holly uncodexify instructions - letting GPT create uncodexified UI
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
prompt2model - Generate Deployable Models from Natural Language Instructions