Stars
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
List of papers about Proteins Design using Deep Learning
LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
[ACL 2024 Oral] This is the code repo for our ACL‘24 paper "MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin".
A simple, easy-to-hack GraphRAG implementation
VLDB 2024 paper repo. RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search
VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama
Example models using DeepSpeed
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Python implementation of an N-gram language model with Laplace smoothing and sentence generation.
This is an implementation of the paper: Searching for Best Practices in Retrieval-Augmented Generation (EMNLP2024)
[ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.acl-long.572/)
《动手学大模型Dive into LLMs》系列编程实践教程
Algebraic value editing in pretrained language models
Retrieval and Retrieval-augmented LLMs
Basic Machine Learning and Deep Learning
⚡机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归