leonardtang

leonardtang's Stars

• josh-ashkinaze/plurals

  Plurals: A System for Guiding LLMs Via Simulated Social Ensembles

  Language:Python152

• BCHSI/philter-ucsf

  Open source clinical text de-identification

  Language:Python11650

• argilla-io/distilabel

  Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

  Language:Python1.8k144

• voxel51/zcore

  Language:Shell555

• cvs-health/langfair

  LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

  Language:Python8914

• microsoft/Trace

  End-to-end Generative Optimization for AI Agents

  Language:Python40426

• datadreamer-dev/DataDreamer

  DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

  Language:Python87246

• wasiahmad/Awesome-LLM-Synthetic-Data

  A reading list on LLM based Synthetic Data Generation 🔥

  88949

• madaan/minimal-text-diffusion

  A minimal implementation of diffusion models for text generation

  Language:Python32230

• refuel-ai/autolabel

  Label, clean and enrich text datasets with LLMs.

  Language:Python2.1k149

• spcl/graph-of-thoughts

  Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

  Language:Python2.2k165

• amudide/switch_sae

  Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)

  Language:Jupyter Notebook141

• google/oss-fuzz-gen

  LLM powered fuzzing via OSS-Fuzz.

  Language:Python1k124

• zeno-ml/zeno-build

  Build, evaluate, understand, and fix LLM-based apps

  Language:Jupyter Notebook48533

• Mihaiii/backtrack_sampler

  An easy-to-understand framework for LLM samplers that rewind and revise generated tokens

  Language:Python1158

• sam-paech/antislop-sampler

  Language:Python24323

• turboderp/exllamav2

  A fast inference library for running LLMs locally on modern consumer-class GPUs

  Language:Python3.8k289

• holistic-ai/holisticai

  This is an open-source tool to assess and improve the trustworthiness of AI systems.

  Language:Jupyter Notebook8319

• honeyhiveai/realign

  Realign is a testing and simulation framework for AI applications.

  Language:Python141

• ndif-team/nnsight

  The nnsight package enables interpreting and manipulating the internals of deep learned models.

  Language:Jupyter Notebook44041

• stanfordnlp/pyreft

  ReFT: Representation Finetuning for Language Models

  Language:Python1.3k111

• chujiezheng/chat_templates

  Chat Templates for 🤗 HuggingFace Large Language Models

  Language:Jinja56753

• Aleph-Alpha/scaling

  Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for training large language models.

  Language:Python532

• Libr-AI/do-not-answer

  Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

  Language:Jupyter Notebook19925

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda24.8k2.8k

• prometheus-eval/prometheus-eval

  Evaluate your LLM's response with Prometheus and GPT4 💯

  Language:Python82949

• aiverify-foundation/moonshot

  Moonshot - A simple and modular tool to evaluate and red-team any LLM application.

  Language:Python19140

• Repello-AI/whistleblower

  Whistleblower is a tool for leaking system prompts and capability discovery of any API accessible LLM App. Built for developers, security red-teams and folks who want to know what's going on inside the LLM App they use daily

  Language:Python1145

• ridgerchu/matmulfreellm

  Implementation for MatMul-free LM.

  Language:Python2.9k187

• black-forest-labs/flux

  Official inference repo for FLUX.1 models

  Language:Python18.7k1.3k