YerongLi

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

adaptive-retrieval

CatE

[WWW 2020] Discriminative Topic Mining via Category-Name Guided Text Embedding

ChunkLlama

Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

DAC

[CVPR 2024] Official implementation of CVPR 2024 paper: "Doubly Abductive Counterfactual Inference for Text-based Image Editing"

diffusion-re

dive

GLM-iprompt

Apply Iprompt on GLM with innovative new methods. Currently support Chinese QA, English QA and Chinese poem generation.

GPT2-fine-tuning-in-a-GAN-setting

InstructDiffusion

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

InternLM-XComposer2d5-7b

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

iPrompt1

Code, Data and Demo for Paper: Controllable Generation from Pre-trained Language Models via Inverse Prompting

LLaMA-Efficient-Tuning

Fine-tuning LLaMA with PEFT (PT+SFT+RLHF with QLoRA)

LLaMA-Factory-police

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

LLaVA-NeXT

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

LongLM

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

LOTClass

[EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach

MathVerse

Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

MathVision

MATH-Vision dataset and code to measure Multimodal Mathematical Reasoning capabilities.

MathVista

MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts

MetaGPT

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

middle-llm-attack

blackbox attack

pythontextnow

pythontextnow

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

SmartEdit

Official code of SmartEdit [CVPR-2024 Highlight]

TaxoComplete

his is the repositotry of TaxoComplete: Self-Supervised Taxonomy Completion Leveraging Position-Enhanced Semantic Matching

video-subtitle-remover

video-subtitle-remover with crop