Ramsey's repositories
AlphaCLIP
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
Causal-Recommender-Systems
An index of causal inference based recommendation algorithms.
DiskANN
Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search
FlagEmbedding
Dense Retrieval and Retrieval-augmented LLMs
ForestDiffusion
Generating and Imputing Tabular Data via Diffusion and Flow XGBoost Models
gpt-4v-distribution-shift
Code for "How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation"
hiclass
A python library for hierarchical classification compatible with scikit-learn
hikyuu
Hikyuu Quant Framework 基于C++/Python的开源量化交易研究框架
imitater
Imitate OpenAI with Local Models
LaCLIP
[NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"
LLM-UM-Reading
A list of large language models for user modeling (LLM-UM) papers.
LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Long-Context-Data-Engineering
Implementation of paper Data Engineering for Scaling Language Models to 128K Context
LongContext_vs_RAG_NeedleInAHaystack
Comparing retrieval abilities from GPT4-Turbo and a RAG system on a toy example for various context lengths
LongLoRA
Code and documents of LongLoRA and LongAlpaca
metahuman-stream
Real time streaming digital human based on nerf
NeuralNLP-NeuralClassifier
An Open-source Neural Hierarchical Multi-label Text Classification Toolkit
OpenP5
OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems
operateGPT
🌟 Revolutionize Your Operations with One Sentence Automation: Utilizing large language models and Multi-Agents to generate operational copy, images, and videos with one-line requirements.
pgbm
Probabilistic Gradient Boosting Machines
pika
Pika is a NoSQL database compatible with redis which is developed by Qihoo's infrastructure team.
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
Selective_Context
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
sklearn-genetic
Genetic feature selection module for scikit-learn
TAG-Benchmark
Benchmark
TravelPlanner
Dataset and code for the paper "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"