Luca Soldaini

Research Scientist at Ai2

Starred Projects (99)

verifiers by PrimeIntellect-ai

RL for LLMs in verifiable environments

karpathy:

rasbt:

jeffchuber:

hammer:

Created 8 months ago

Updated 2 days ago

ProX by GAIR-NLP

Data refinement framework for improving pre-training data quality

Created 1 year ago

Updated 3 months ago

system-prompts-and-models-of-ai-tools by x1xhlol

AI tool system prompts and models

tobi:

codekansas:

syrusakbary:

omarsar:

Created 7 months ago

Updated 3 days ago

cua by trycua

AI agent framework for computer OS control in virtual containers

tobi:

ValentaTomas:

chiphuyen:

gregpr07:

Created 8 months ago

Updated 2 days ago

OLMo-core by allenai

PyTorch building blocks for large language model training and inference

hammer:

Created 1 year ago

Updated 1 day ago

llm-datasets by mlabonne

Curated datasets/tools for LLM post-training

jph00:

shyamal-anadkat:

philschmid:

winglian:

Created 1 year ago

Updated 2 months ago

webdataset by webdataset

High-performance I/O system for large deep learning problems, strong PyTorch support

chiphuyen:

hammer:

theophilegervet:

Jiayi-Pan:

Created 6 years ago

Updated 3 months ago

olmocr by allenai

Toolkit for linearizing PDFs for LLM datasets/training

hammer:

dguido:

omarsar:

lantiga:

Created 1 year ago

Updated 1 day ago

LLM.swift by eastriverlee

Swift SDK for local LLM interaction on Apple platforms

ggerganov:

Created 1 year ago

Updated 1 week ago

SpeziLLM by StanfordSpezi

LLM integration for Swift applications

ggerganov:

Created 2 years ago

Updated 2 weeks ago

awesome-model-based-RL by opendilab

Curated list of model-based RL resources

Created 3 years ago

Updated 1 month ago

semchunk by isaacus-dev

Python library for splitting text into semantically meaningful chunks

Created 1 year ago

Updated 2 months ago

torchtitan by pytorch

PyTorch platform for generative AI model training research

karpathy:

pgarbacki:

lewtun:

zhuohan123:

Created 1 year ago

Updated 21 hours ago

chat_templates by chujiezheng

Chat templates for HuggingFace LLMs

natolambert:

shizhediao:

winglian:

osanseviero:

Created 1 year ago

Updated 10 months ago

DataDreamer by datadreamer-dev

Python library for synthetic data generation and training workflows

hammer:

omarsar:

JustinLin610:

natolambert:

Created 2 years ago

Updated 8 months ago

MAP-NEO by multimodal-art-projection

Open-source LLM with pretraining data, pipeline, scripts, and alignment code

hiyouga:

natolambert:

Created 1 year ago

Updated 8 months ago

sglang by sgl-project

Fast serving framework for LLMs and vision language models

samlambert:

ebursztein:

philschmid:

pankajroark:

Created 1 year ago

Updated 20 hours ago

cosmopedia by huggingface

Synthetic dataset for LLM training

shizhediao:

mlabonne:

osanseviero:

Created 1 year ago

Updated 10 months ago

distilabel by argilla-io

Framework for synthetic data and AI feedback pipelines

lvwerra:

jn2clark:

hiyouga:

pgarbacki:

Created 2 years ago

Updated 1 day ago

wtpsplit by segment-any-text

Text segmentation toolkit for robust sentence splitting

luiscape:

Created 5 years ago

Updated 6 days ago

outlines by dottxt-ai

SDK for structured LLM text generation

tobi:

kerollmops:

willingc:

jn2clark:

Created 2 years ago

Updated 4 days ago

domains by tb0hdan

Internet domains dataset for battling phishing attacks and research

Created 5 years ago

Updated 2 weeks ago

marker by datalab-to

CLI tool for converting PDFs and other documents to Markdown, JSON, and HTML

luiscape:

bfirsh:

joewalnes:

snowzurfer:

Created 1 year ago

Updated 2 days ago

OLMo-Eval by allenai

Evaluation suite for LLMs

Created 2 years ago

Updated 3 months ago

datatrove by huggingface

Data processing library for large-scale text data

lewtun:

shizhediao:

apsdehal:

mlabonne:

Created 2 years ago

Updated 6 days ago

reward-bench by allenai

Reward model evaluation tool

lewtun:

shizhediao:

natolambert:

Created 1 year ago

Updated 4 months ago

mlx by ml-explore

Array framework for machine learning on Apple silicon

geohot:

karpathy:

jmorganca:

chiphuyen:

Created 1 year ago

Updated 1 day ago

InternLM by InternLM

LLM series (InternLM, InternLM2, InternLM2.5, InternLM3) official release

hammer:

simonw:

jph00:

omarsar:

Created 2 years ago

Updated 2 months ago

gpt_academic by binary-husky

LLM tool for paper reading/polishing/writing, optimized UI

yiranwu0:

JustinLin610:

osanseviero:

jiamings:

Created 2 years ago

Updated 3 weeks ago

gpt_paper_assistant by tatsu-lab

ArXiv scanner using GPT-4 for personalized paper recommendations

rodrigosnader:

hiyouga:

Edward-Sun:

Ying1123:

Created 1 year ago

Updated 1 year ago

dolma by allenai

Toolkit for curating datasets for language model pre-training

chiphuyen:

omarsar:

hammer:

shizhediao:

Created 2 years ago

Updated 2 weeks ago

MiniChain by srush

Tiny library for coding with large language models

hiyouga:

lysandrejik:

jph00:

ValentaTomas:

Created 2 years ago

Updated 1 year ago

falcontune by rmihaylov

CLI tool for finetuning Falcon LLMs

tobi:

pgarbacki:

Created 2 years ago

Updated 2 years ago

NeMo by NVIDIA-NeMo

Scalable generative AI framework for LLMs, multimodal, and speech AI research

alexchen4ai:

Ying1123:

shizhediao:

robinjhuang:

Created 6 years ago

Updated 1 day ago

guidance by guidance-ai

Guidance is a programming paradigm for steering LLMs

tobi:

ekzhu:

stas00:

Ying1123:

Created 2 years ago

Updated 6 days ago

hh-rlhf by anthropics

RLHF dataset for training safe AI assistants

chiphuyen:

vincentweisser:

transitive-bullshit:

Edward-Sun:

Created 3 years ago

Updated 3 months ago

self-instruct by yizhongw

Self-Instruct: Research paper for aligning language models with self-generated instructions

hiyouga:

pgarbacki:

transitive-bullshit:

lewtun:

Created 2 years ago

Updated 2 years ago

gpt4all by nomic-ai

Desktop app for local LLM inference, no GPU/API needed

willingc:

zhiyuan8:

osanseviero:

antirez:

Created 2 years ago

Updated 4 months ago

garak by NVIDIA

LLM vulnerability scanner for red-teaming and security assessments

ebursztein:

luiscape:

omarsar:

dguido:

Created 2 years ago

Updated 1 day ago

awesome-instruction-learning by RenzeLou

Curated list of instruction tuning/following papers and datasets

omarsar:

Created 2 years ago

Updated 1 year ago

docquery by impira

Document query engine for extracting information from documents

hammer:

sqs:

Created 3 years ago

Updated 2 years ago

pyllms by kagisearch

Python SDK for LLM access and benchmarking

shyamal-anadkat:

Sanger2000:

hammer:

torantulino:

Created 2 years ago

Updated 2 months ago

dspy by stanfordnlp

Framework for programming language models, not prompting

tobi:

mateiz:

vincentweisser:

pgarbacki:

Created 2 years ago

Updated 3 days ago

OLMo by allenai

Open language model code for training, evaluation, and inference

tjbck:

winglian:

john-b-yang:

transitive-bullshit:

Created 2 years ago

Updated 1 month ago

instruction-datasets by raunak-agarwal

Dataset list for instruction tuning of LLMs

huybery:

andreasjansson:

Created 2 years ago

Updated 1 year ago

GPTQ-for-LLaMa by qwopqwop200

4-bit quantization for LLaMA models using GPTQ

chiphuyen:

gakonst:

hiyouga:

jph00:

Created 2 years ago

Updated 1 year ago

openai-cookbook by openai

Examples for using the OpenAI API

deshraj:

0hq:

sb2nov:

nirga:

Created 3 years ago

Updated 3 days ago

transformers-bloom-inference by huggingface

Inference solutions for BLOOM models

Edward-Sun:

chuanli11:

philschmid:

stas00:

Created 3 years ago

Updated 1 year ago

llama by meta-llama

Inference code for Llama 2 models (deprecated)

froystig:

xiezhq-hermann:

fabhed:

borzunov:

Created 2 years ago

Updated 8 months ago

composer by mosaicml

DL framework for training at scale, optimized for large-scale clusters

aravindsrinivas:

eiso:

gakonst:

mlabonne:

Created 4 years ago

Updated 1 week ago

llama-hub by run-llama

Data loaders for LLMs (deprecated, now in LlamaIndex core)

chiphuyen:

rotemweiss57:

Disiok:

jerryjliu:

Created 2 years ago

Updated 1 year ago

Instruction-Tuning-Papers by SinclairCoder

Reading list for instruction tuning papers

codekansas:

huybery:

Created 2 years ago

Updated 2 years ago

parallelformers by tunib-ai

Toolkit for easy model parallelization

Edward-Sun:

parasj:

patrickvonplaten:

julien-c:

Created 4 years ago

Updated 2 years ago

alpa by alpa-projects

Auto-parallelization framework for large-scale neural network training and serving

chiphuyen:

Jiayi-Pan:

transitive-bullshit:

hammer:

Created 4 years ago

Updated 1 year ago

GLM-130B by zai-org

Bilingual model for research and evaluation

wassemgtk:

jiamings:

mckaywrigley:

bryanhelmig:

Created 3 years ago

Updated 2 years ago

FasterTransformer by NVIDIA

Optimized transformer library for inference

nat:

chiphuyen:

JustinLin610:

mfuntowicz:

Created 4 years ago

Updated 1 year ago

orama by oramasearch

Browser-based search engine and RAG pipeline

osanseviero:

jaredpalmer:

omarsar:

transitive-bullshit:

Created 3 years ago

Updated 2 days ago

bitsandbytes by bitsandbytes-foundation

PyTorch library for k-bit quantization, enabling accessible LLMs

tjbck:

alexchen4ai:

danielhanchen:

shimmyshimmer:

Created 4 years ago

Updated 1 week ago

examples by mosaicml

Reference benchmarks for training and deploying ML models at scale

jph00:

hammer:

jfrankle:

hanlint:

Created 3 years ago

Updated 3 months ago

metaseq by facebookresearch

Codebase for large-scale transformer model development and deployment

chiphuyen:

gakonst:

xiezhq-hermann:

Ying1123:

Created 3 years ago

Updated 1 year ago

tevatron by texttron

Unified toolkit for document retrieval across modalities, languages, and scale

jn2clark:

Created 4 years ago

Updated 1 week ago

trlx by CarperAI

Distributed RLHF for LLMs

nat:

chiphuyen:

eugeneyan:

huybery:

Created 3 years ago

Updated 1 year ago

tiktoken by openai

Fast BPE tokenizer for OpenAI models

nat:

gregpr07:

chuanli11:

hammer:

Created 2 years ago

Updated 1 week ago

whisper by openai

Speech recognition model for multilingual transcription/translation

bcherny:

karpathy:

ogabrielluiz:

zhyncs:

Created 3 years ago

Updated 1 month ago

speechbrain by speechbrain

PyTorch toolkit for speech and text processing research

soumith:

transitive-bullshit:

spahl:

tridao:

Created 5 years ago

Updated 5 days ago

galai by paperswithcode

Scientific language model API

shizhediao:

vincentweisser:

amix:

RJT1990:

Created 2 years ago

Updated 2 years ago

faiss by facebookresearch

Similarity search library for dense vectors

lilianweng:

aravindsrinivas:

hsbt:

khou22:

Created 8 years ago

Updated 3 days ago

tinygrad by tinygrad

Minimalist deep learning framework for education and exploration

geohot:

k06a:

ekzhang:

amin3141:

Created 5 years ago

Updated 20 hours ago

pytorch-lightning by Lightning-AI

Deep learning framework for pretraining, finetuning, and deploying AI models

albertfgu:

omarsar:

zhangce:

JohannesHa:

Created 6 years ago

Updated 22 hours ago

RL4LMs by allenai

RL library to fine-tune language models to human preferences

vincentweisser:

chiphuyen:

winglian:

shizhediao:

Created 3 years ago

Updated 1 year ago

t-few by r-three

Code for parameter-efficient fine-tuning research paper

Created 3 years ago

Updated 2 years ago

manifest by HazyResearch

SDK for prompt programming with foundation models

ishaan-jaff:

aangelopoulos:

albertfgu:

shizhediao:

Created 3 years ago

Updated 1 year ago

AITemplate by facebookincubator

Generate high-performance inference engines

nat:

hammer:

transitive-bullshit:

jrk:

Created 3 years ago

Updated 3 weeks ago

lm-evaluation-harness by EleutherAI

Framework for few-shot language model evaluation

aravindsrinivas:

zjasper666:

zhuohan123:

shizhediao:

Created 5 years ago

Updated 3 days ago

s2orc by allenai

Corpus for NLP/text mining research on scientific papers

shizhediao:

hammer:

Created 6 years ago

Updated 1 year ago

stable-diffusion by CompVis

Latent text-to-image diffusion model

gaearon:

patrickvonplaten:

codekansas:

ValentaTomas:

Created 3 years ago

Updated 1 year ago

primeqa by primeqa

Open-source repo for multilingual question answering research

hammer:

jn2clark:

omarsar:

osanseviero:

Created 3 years ago

Updated 3 weeks ago

flax by google

NN library for JAX, designed for flexibility in neural network research

charliermarsh:

codekansas:

Jiayi-Pan:

jaredpalmer:

Created 5 years ago

Updated 1 day ago

optimum by huggingface

Hardware optimization tools for Transformers, Diffusers, etc

clmnt:

PiotrDabkowski:

ankane:

julien-c:

Created 4 years ago

Updated 5 days ago

sentence-transformers by UKPLab

Framework for text embeddings, retrieval, and reranking

chiphuyen:

luiscape:

didierrlopes:

pgarbacki:

Created 6 years ago

Updated 5 days ago

annotated_deep_learning_paper_implementations by labmlai

PyTorch implementations/tutorials of deep learning papers with side-by-side notes

pgarbacki:

JohannesHa:

sb2nov:

hammer:

Created 5 years ago

Updated 3 weeks ago

datasets by huggingface

Access and process large AI datasets efficiently

clmnt:

chiphuyen:

transitive-bullshit:

gakonst:

Created 5 years ago

Updated 1 day ago

lightning-transformers by Lightning-Universe

Archived library for training Transformers with PyTorch Lightning

CodeCreator:

luiscape:

lantiga:

Created 4 years ago

Updated 2 years ago

netron by lutzroeder

Model visualizer for neural networks, deep learning, and ML

casper-hansen:

hammer:

guberti:

wesm:

Created 15 years ago

Updated 1 day ago

unilm by microsoft

Foundation models for language, vision, speech, and multimodal tasks

jph00:

AlexCheema:

chiphuyen:

osanseviero:

Created 6 years ago

Updated 3 months ago

text-to-text-transfer-transformer by google-research

Unified text-to-text transformer for NLP research

aravindsrinivas:

chiphuyen:

pgarbacki:

patrickvonplaten:

Created 6 years ago

Updated 5 months ago

DeBERTa by microsoft

BERT enhancement via disentangled attention, enhanced mask decoder

huybery:

hammer:

omarsar:

evhub:

Created 5 years ago

Updated 2 years ago

nlp-recipes by microsoft

NLP examples and best practices as Jupyter notebooks

luiscape:

rstojnic:

omarsar:

lysandrejik:

Created 6 years ago

Updated 3 years ago

oie-resources by gkiril

Extensive resources for Open Information Extraction (OIE) research

Created 6 years ago

Updated 3 years ago

fairseq by facebookresearch

Sequence modeling toolkit for translation, language modeling, and text generation research

lilianweng:

aravindsrinivas:

tjbck:

pathak22:

Created 8 years ago

Updated 2 weeks ago

tokenizers by huggingface

Fast tokenizer library optimized for research and production

clmnt:

syrusakbary:

transitive-bullshit:

JohannesHa:

Created 6 years ago

Updated 6 days ago

transformers by huggingface

ML library for pretrained model inference and training

clmnt:

lilianweng:

karpathy:

tjbck:

Created 7 years ago

Updated 20 hours ago

BlingFire by microsoft

Fast text tokenization library

jph00:

ankane:

ekzhu:

hammer:

Created 6 years ago

Updated 10 months ago

anserini by castorini

Lucene toolkit for reproducible information retrieval research

parasj:

tholor:

hammer:

Created 10 years ago

Updated 1 day ago

awesome-information-retrieval by harpribot

Curated list of information retrieval resources

omarsar:

taranjeet:

Created 9 years ago

Updated 2 years ago

bert by google-research

TensorFlow code and pre-trained models for BERT

aravindsrinivas:

pgarbacki:

jn2clark:

evhub:

Created 7 years ago

Updated 1 year ago

tsv-utils by eBay

CLI tools for large tabular data files: filtering, statistics, sampling, joins, and more

hammer:

joewalnes:

spartee:

simonw:

Created 9 years ago

Updated 3 years ago

tensorflow by tensorflow

Open-source ML framework

norvig:

aravindsrinivas:

karpathy:

bcherny:

Created 10 years ago

Updated 20 hours ago

spaCy by explosion

NLP library for production applications

aravindsrinivas:

fchollet:

nirga:

jn2clark:

Created 11 years ago

Updated 4 months ago

Feedback? Help us improve.