danielmamay

danielmamay's Stars

• tml-epfl/llm-adaptive-attacks

  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

  Language:Shell22822

• rmcelreath/stat_rethinking_2024

  Language:R1.3k133

• openai/sparse_autoencoder

  Language:Python35938

• callummcdougall/sae_vis

  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

  Language:HTML16834

• jbloomAus/SAELens

  Training Sparse Autoencoders on Language Models

  Language:Jupyter Notebook507129

• microsoft/Samba

  Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

  Language:Python80949

• ridgerchu/matmulfreellm

  Implementation for MatMul-free LM.

  Language:Python2.9k184

• google-research/arco-era5

  Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.

  Language:Python33223

• google-research/weatherbench2

  A benchmark for the next generation of data-driven global weather models.

  Language:Python45648

• iterative/dvc

  🦉 Data Versioning and ML Experiments

  Language:Python14k1.2k

• avehtari/ROS-Examples

  Regression and other stories R examples

  Language:HTML325256

• eric-mitchell/direct-preference-optimization

  Reference implementation for DPO (Direct Preference Optimization)

  Language:Python2.2k185

• tatsu-lab/alpaca_eval

  An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

  Language:Jupyter Notebook1.6k245

• artidoro/qlora

  QLoRA: Efficient Finetuning of Quantized LLMs

  Language:Jupyter Notebook10.1k824

• ndif-team/nnsight

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

  Language:Jupyter Notebook41740

• thestephencasper/latent_adversarial_training

  Language:Python195

• openai/simple-evals

  Language:Python2k173

• UKGovernmentBEIS/inspect_ai

  Inspect: A framework for large language model evaluations

  Language:Python647128

• andyzoujm/representation-engineering

  Representation Engineering: A Top-Down Approach to AI Transparency

  Language:Jupyter Notebook73688

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python27.4k3.1k

• centerforaisafety/HarmBench

  HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

  Language:Jupyter Notebook35359

• METR/task-standard

  METR Task Standard

  Language:TypeScript12731

• google-deepmind/graphcast

  Language:Python4.8k596

• carlini/yet-another-applied-llm-benchmark

  A benchmark to evaluate language models on questions I've previously asked them to solve.

  Language:Python91866

• karpathy/minbpe

  Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

  Language:Python9.2k870

• dalibo/pev2

  Postgres Explain Visualizer 2

  Language:TypeScript2.7k131

• jepsen-io/jepsen

  A framework for distributed systems verification, with fault injection

  Language:Clojure6.9k719

• nerfstudio-project/nerfstudio

  A collaboration friendly studio for NeRFs

  Language:Python9.6k1.3k

• pyro-ppl/pyro

  Deep universal probabilistic programming with Python and PyTorch

  Language:Python8.6k988

• openai/weak-to-strong

  Language:Python2.5k308