Alternatives and similar repositories for automated-interpretability:

Users that are interested in automated-interpretability are comparing it to the libraries listed below

• anthropics / hh-rlhf
  Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
  ☆1,679Updated last year
• openai / prm800k
  800,000 step-level correctness labels on LLM solutions to MATH problems
  ☆1,884Updated last year
• princeton-nlp / MeZO
  [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
  ☆1,081Updated last year
• reasoning-machines / pal
  PaL: Program-Aided Language Models (ICML 2023)
  ☆481Updated last year
• EleutherAI / pythia
  The hub for EleutherAI's work on interpretability and learning dynamics
  ☆2,368Updated 2 months ago
• sylinrl / TruthfulQA
  TruthfulQA: Measuring How Models Imitate Human Falsehoods
  ☆669Updated last month
• tatsu-lab / alpaca_farm
  A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.
  ☆793Updated 7 months ago
• yuchenlin / LLM-Blender
  [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…
  ☆911Updated 3 months ago
• bigcode-project / bigcode-evaluation-harness
  A framework for the evaluation of autoregressive code generation language models.
  ☆884Updated 3 months ago
• lupantech / chameleon-llm
  Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".
  ☆1,109Updated last year
• likenneth / honest_llama
  Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  ☆496Updated 2 weeks ago
• ctlllll / LLM-ToolMaker
  ☆1,025Updated last year
• salesforce / xgen
  Salesforce open-source LLMs with 8k sequence length.
  ☆717Updated 2 weeks ago
• kmeng01 / rome
  Locating and editing factual associations in GPT (NeurIPS 2022)
  ☆605Updated 9 months ago
• IBM / Dromedary
  Dromedary: towards helpful, ethical and reliable LLMs.
  ☆1,136Updated last year
• lupantech / ScienceQA
  Data and code for NeurIPS 2022 Paper "Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering".
  ☆629Updated 4 months ago
• kmeng01 / memit
  Mass-editing thousands of facts into a transformer memory (ICLR 2023)
  ☆462Updated last year
• tatsu-lab / alpaca_eval
  An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
  ☆1,646Updated last month
• SinclairCoder / Instruction-Tuning-Papers
  Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).
  ☆760Updated last year
• andyzoujm / representation-engineering
  Representation Engineering: A Top-Down Approach to AI Transparency
  ☆787Updated 6 months ago
• arielnlee / Platypus
  Code for fine-tuning Platypus fam LLMs using LoRA
  ☆626Updated last year
• google-research / FLAN
  ☆1,497Updated this week
• allenai / natural-instructions
  Expanding natural instructions
  ☆973Updated last year
• hendrycks / test
  Measuring Massive Multitask Language Understanding | ICLR 2021
  ☆1,302Updated last year
• persimmon-ai-labs / adept-inference
  Inference code for Persimmon-8B
  ☆416Updated last year
• declare-lab / instruct-eval
  This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
  ☆541Updated 11 months ago
• ContextualAI / HALOs
  A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
  ☆798Updated this week
• lucidrains / MEGABYTE-pytorch
  Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
  ☆636Updated last month
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆472Updated 8 months ago
• madaan / self-refine
  LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
  ☆666Updated 4 months ago