JulianJuaner

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

test

Measuring Massive Multitask Language Understanding | ICLR 2021

VideoCrafter

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

alphageometry

flash-attention

Fast and memory-efficient exact attention

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

PnPInversion

[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

tesseract

Tesseract Open Source OCR Engine (main repository)

ReplaceAnything

MotionDirector

MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

AlphaCLIP

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

webvid

Large-scale text-video dataset. 10 million captioned short videos.

MR-GSM8K

Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs

visualblocks

Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-and-drop ML components, including models, user inputs, processors, and visualizations.

MoTCoder

This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks.

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

Emu

Emu Series: Generative Multimodal Models from BAAI

OpenLRM

An open-source impl. of Large Reconstruction Models

StyleCrafter

StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

PointTransformerV3

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

adaptively_sparse_attention

tesseract

Tesseract Open Source OCR Engine (main repository)

anomaly_diff

DemoFusion

Let us democratise high-resolution generation! (CVPR 2024)

Prompt-Highlighter

[CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs

DynamiCrafter

[ECCV 2024] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

ComfyUI_UltimateSDUpscale

ComfyUI nodes for the Ultimate Stable Diffusion Upscale script by Coyote-A.