Stars
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
A high-throughput and memory-efficient inference and serving engine for LLMs
O1 Replication Journey: A Strategic Progress Report – Part I
This resposity maintains a collection of important papers on conditional image synthesis with diffusion models
Offical code repository of “BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training”
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
Reference implementation for DPO (Direct Preference Optimization)
🎉 The code repository for "Parrot: Multilingual Visual Instruction Tuning" in PyTorch.
Open-source evaluation toolkit of large vision-language models (LVLMs), support 160+ VLMs, 50+ benchmarks
Official implement for "SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion"(NeurIPS'24) in PyTorch.
A comprehensive toolkit and benchmark for tabular data learning, featuring 30 deep methods, more than 10 classical methods, and 300 diverse tabular datasets.
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
llama3 implementation one matrix multiplication at a time
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列
The code repository for "Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration" (NeurIPS'23) in PyTorch
The code repository for "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning"(CVPR24) in PyTorch.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
✨✨Latest Advances on Multimodal Large Language Models