jzhang38
Follow
Stars
[Findings of EMNLP 2024] AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models
reckoning, judgement, apocalypse
An open-source parameterizable NPU generator with full-stack multi-target compilation stack for intelligent workloads.
An evaluation suite for Retrieval-Augmented Generation (RAG).
Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
🔥🔥MLVU: Multi-task Long Video Understanding Benchmark
An open-source implementation for training LLaVA-NeXT.
[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.
[ICML 2024] CLLMs: Consistency Large Language Models
Training LLMs with QLoRA + FSDP
Accelerating the development of large multimodal models (LMMs) with lmms-eval
A high-throughput and memory-efficient inference and serving engine for LLMs
Some preliminary explorations of Mamba's context scaling.
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
SGLang is a fast serving framework for large language models and vision language models.
[ACL 2024] Progressive LLaMA with Block Expansion.
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
Robust recipes to align language models with human and AI preferences
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.