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