Pinned Repositories
annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
Bert-Chinese-Text-Classification-Pytorch
使用Bert，ERNIE，进行中文文本分类
BERT-chinese-text-classification-pytorch-1
This repo contains a PyTorch implementation of a pretrained BERT model for text classification.
blog
Public repo for HF blog posts
caffe
Caffe: a fast open framework for deep learning.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
CV
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
NLPer-Interview
该仓库主要记录 NLP 算法工程师相关的面试题
video-question-answering
Video Question Answering via Gradually Refined Attention over Appearance and Motion
lucas0214's Repositories
lucas0214/CV
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
lucas0214/annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
lucas0214/Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
lucas0214/Bert-Chinese-Text-Classification-Pytorch
使用Bert，ERNIE，进行中文文本分类
lucas0214/blog
Public repo for HF blog posts
lucas0214/CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
lucas0214/Clip4caption
A Simple Baseline Based on CLIP and Transformer for Video Captioning
lucas0214/CVPR2024-Papers-with-Code
CVPR 2024 论文和开源项目合集
lucas0214/d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
lucas0214/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
lucas0214/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
lucas0214/doing_the_PhD
lucas0214/LLM-quickstart
Quick Start for Large Language Models (Theoretical Learning and Practical Fine-tuning) 大语言模型快速入门（理论学习与微调实战）
lucas0214/llm-viz
3D Visualization of an GPT-style LLM
lucas0214/LLMBind
LLMBind: A Unified Modality-Task Integration Framework
lucas0214/MA-LMM
(2024CVPR) MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
lucas0214/MoE-LLaVA
Mixture-of-Experts for Large Vision-Language Models
lucas0214/MPIKGC
[LREC-COLING 2024] Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models
lucas0214/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
lucas0214/openai-quickstart
A comprehensive guide to understanding and implementing large language models with hands-on examples using LangChain for GenAI applications.
lucas0214/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
lucas0214/ProLLaMA
A Protein Large Language Model for Multi-Task Protein Language Processing
lucas0214/ProST
Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval --ICCV2023 Oral
lucas0214/SceneGraphParser
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
lucas0214/Transformer-from-scratch
lucas0214/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
lucas0214/UniBind
The source code for "UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All"
lucas0214/unsloth
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
lucas0214/Video-LLaVA
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
lucas0214/vit-imagenet21k-p
Preprocessing ImageNet-21K into an indexed directory, with a Vision Transformer (ViT) trained on it, inspired by 'Pretraining for the Masses'.