schen149

schen149's Stars

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python31.2k2535.5k4.8k

• qdrant/qdrant

  Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

  Language:Rust20.8k1261.3k1.4k

• google-deepmind/pysc2

  StarCraft II Learning Environment

  Language:Python8k3472821.2k

• mit-han-lab/streaming-llm

  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

  Language:Python6.7k6583369

• allenai/OLMo

  Modeling, training, eval, and inference code for OLMo

  Language:Python4.8k48202492

• srush/Tensor-Puzzles

  Solve puzzles. Improve your pytorch.

  Language:Jupyter Notebook3.3k1320282

• google/BIG-bench

  Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

  Language:Python2.9k51151592

• castorini/pyserini

  Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

  Language:Python1.7k18549379

• allenai/natural-instructions

  Expanding natural instructions

  Language:Python96221161190

• jxmorris12/vec2text

  utilities for decoding deep representations (like sentence embeddings) back to text

  Language:Python750126285

• EdinburghNLP/awesome-hallucination-detection

  List of papers on hallucination detection in LLMs.

  69125457

• mlfoundations/task_vectors

  Editing Models with Task Arithmetic

  Language:Python43391836

• luyug/GradCache

  Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

  Language:Python36392924

• swj0419/detect-pretrain-code

  This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu , Terra Blevins , Danqi Chen , Luke Zettlemoyer.

  Language:Python20911623

• GFNOrg/gfn-lm-tuning

  Language:Jupyter Notebook15331020

• chentong0/factoid-wiki

  Dense X Retrieval: What Retrieval Granularity Should We Use?

  1369109

• chaitanyamalaviya/ExpertQA

  [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers

  Language:Python1226613

• ludwigwinkler/JaxLightning

  Running Jax in PyTorch Lightning

  Language:Python82411

• schen149/sub-sentence-encoder

  The official code repo for "Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations".

  Language:Python75130

• danieldeutsch/repro

  Repro is a library for easily running code from published papers via Docker.

  Language:Python401106

• ryokamoi/wice

  This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.

  Language:Python40241

• shadowkiller33/Contrast-Instruction

  Language:Python19303

• google-research-datasets/PropSegmEnt

  PropSegmEnt is an annotated dataset for segmenting English text into propositions, and recognizing proposition-level entailment relations - whether a different, related document entails each proposition, contradicts it, or neither. It consists of clusters of closely related documents from the news and Wikipedia domains.

  18312

• CogComp/MultiOpEd

  MULTIOPED: A Corpus of Multi-Perspective News Editorials.

  Language:Python10602

• naimenz/inverse-scaling-eval-pipeline

  Basic pipeline for running different sized GPT models and plotting the results

  Language:Python92016

• TRUMANCFY/MixGR

  Language:Jupyter Notebook5100

• JHU-CLSP/Cost-Effective-Experiment

  Scripts and docs that help us run cost effective experiment with OpenAI APIs

  Language:Python4602

• CogComp/transformer-lm-demo

  A simple demo of transformer language models, mostly for our internal use: http://dickens.seas.upenn.edu:4001

  Language:Python3112

• schen149/PropSegmEnt

  PropSegmEnt is an annotated dataset for segmenting English text into propositions, and recognizing proposition-level entailment relations - whether a different, related document entails each proposition, contradicts it, or neither. It consists of clusters of closely related documents from the news and Wikipedia domains.

  2000

• stevenysw/causal_gfl

  Language:R1100