Alternatives and similar repositories for modelsmith

Users that are interested in modelsmith are comparing it to the libraries listed below

• ShanglunFengatETHZ / PrivacyBackdoor
  Privacy backdoors
  ☆52Updated last year
• google-parfait / dataset_grouper
  Libraries for efficient and scalable group-structured dataset pipelines.
  ☆25Updated 5 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆156Updated 6 months ago
• sail-sg / Cheating-LLM-Benchmarks
  [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)
  ☆85Updated last year
• arobey1 / advbench
  ☆44Updated 2 years ago
• RapidResponseBench / rapidresponsebench
  ☆35Updated last year
• andyzoujm / breaking-llama-guard
  Code to break Llama Guard
  ☆32Updated 2 years ago
• azshue / AutoPoison
  The official repository of the paper "On the Exploitability of Instruction Tuning".
  ☆66Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆248Updated last year
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆43Updated last year
• facebookresearch / SecAlign
  Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"
  ☆76Updated 4 months ago
• microsoft / DPSDA
  Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]
  ☆109Updated last month
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆122Updated last year
• technion-cs-nlp / LLMsKnow
  ☆84Updated 10 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆62Updated last week
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆70Updated last year
• tml-epfl / os-harm
  OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]
  ☆43Updated 2 months ago
• katiekang1998 / reasoning_generalization
  ☆33Updated 11 months ago
• i-gao / model-equality-testing
  Test equality between a black-box LLM API and a reference distribution
  ☆12Updated last year
• UCSB-NLP-Chang / ULD
  Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24…
  ☆26Updated last year
• oripress / AlgoTune
  AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each…
  ☆75Updated 3 weeks ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆41Updated last year
• vedantpalit / Towards-Vision-Language-Mechanistic-Interpretability
  This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…
  ☆24Updated last year
• mlcommons / modelbench
  Run safety benchmarks against AI models and view detailed reports showing how well they performed.
  ☆112Updated this week
• allenai / wildguard
  Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  ☆97Updated last year
• sail-sg / Agent-Smith
  [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
  ☆117Updated last year
• ethz-spylab / unlearning-vs-safety
  ☆25Updated last year
• poloclub / llm-landscape
  NeurIPS'24 - LLM Safety Landscape
  ☆34Updated last month
• SchwinnL / circuit-breakers-eval
  Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting
  ☆18Updated 8 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆24Updated last year