A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.
☆47Jan 16, 2025Updated last year
Alternatives and similar repositories for llm_optimization
Users that are interested in llm_optimization are comparing it to the libraries listed below
Sorting:
- ☆13Jul 3, 2022Updated 3 years ago
- This is work done by the Oxen.ai Community, trying to reproduce the Self-Rewarding Language Model paper from MetaAI.☆133Nov 16, 2024Updated last year
- Rewarded soups official implementation☆62Sep 27, 2023Updated 2 years ago
- ☆11Aug 10, 2020Updated 5 years ago
- a benchmark suite for testing logical reasoning abilities of prompt-based models☆32Nov 20, 2023Updated 2 years ago
- The official implementation of InfoRM [NeurIPS 2024].☆15Oct 25, 2025Updated 4 months ago
- ☆14Sep 11, 2022Updated 3 years ago
- Repository for paper: "SnAKe: Bayesian Optimization with Pathwise Exploration".☆17Feb 9, 2024Updated 2 years ago
- an unofficial implementation of BaRT Defense☆11Jan 6, 2021Updated 5 years ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆29Feb 17, 2025Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆842Jul 1, 2024Updated last year
- Official Code Repository for [AutoScale📈: Scale-Aware Data Mixing for Pre-Training LLMs] Published as a conference paper at **COLM 2025*…☆13Aug 8, 2025Updated 7 months ago
- ☆21Dec 17, 2020Updated 5 years ago
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆14Jun 21, 2024Updated last year
- ☆20Jun 3, 2023Updated 2 years ago
- ☆12Mar 7, 2024Updated 2 years ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆78Oct 9, 2025Updated 5 months ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Feb 27, 2023Updated 3 years ago
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆22Dec 30, 2021Updated 4 years ago
- Computational statistics and machine learning reading group at Imperial College London (2019-2020)☆25Jan 9, 2026Updated 2 months ago
- [ICML 2024] "Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection"☆15Feb 15, 2025Updated last year
- Source code of our EMNLP 2024 paper "FactAlign: Long-form Factuality Alignment of Large Language Models"☆19Oct 3, 2024Updated last year
- Implementing FastSent in theano☆12May 2, 2016Updated 9 years ago
- SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models☆15Jun 24, 2024Updated last year
- The official code of Multi-player Nash Preference Optimization [ICLR 2026]☆33Feb 4, 2026Updated last month
- The Multitask Long Document Benchmark☆42Nov 2, 2022Updated 3 years ago
- ☆21Jun 27, 2024Updated last year
- An official implementation of "Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective" (KDD 2024)☆12Sep 16, 2024Updated last year
- [ICLR 2025 Spotlight] Weak-to-strong preference optimization: stealing reward from weak aligned model☆17Feb 24, 2025Updated last year
- Yet another dynamic batch sampler for variable sequence data in PyTorch.☆13Dec 9, 2021Updated 4 years ago
- ☆10Aug 10, 2024Updated last year
- Public repository for Machine Learning II course☆17May 23, 2025Updated 9 months ago
- Code for ICLR 2025 Paper "GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment"☆20Feb 10, 2025Updated last year
- An implementation of DecorrelatedBN by tensorflow☆13Jun 30, 2022Updated 3 years ago
- ☆13Jul 2, 2025Updated 8 months ago
- Code and data for the paper "Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?"☆26Jun 3, 2025Updated 9 months ago
- Learning from Indirect Observations☆11Jul 16, 2021Updated 4 years ago
- Adversarial Augmentation Against Adversarial Attacks☆32May 23, 2023Updated 2 years ago
- This is AlpaGasus2-QLoRA based on LLaMA2 with AlpaGasus mechanism using QLoRA!☆15Nov 22, 2023Updated 2 years ago