tlc4418 / llm_optimization
A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.
☆35Updated 2 weeks ago
Alternatives and similar repositories for llm_optimization:
Users that are interested in llm_optimization are comparing it to the libraries listed below
- Rewarded soups official implementation☆55Updated last year
- ☆34Updated 11 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆114Updated 2 months ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆24Updated last year
- Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Feedback (ICML 2024) by Alex J. Chan, Hao Sun, Samuel Holt…☆22Updated 5 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆40Updated last year
- ☆76Updated 6 months ago
- ☆20Updated 4 months ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆15Updated 3 weeks ago
- ☆28Updated last month
- Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"☆28Updated last year
- Codebase for "Uni[MASK]: Unified Inference in Sequential Decision Problems"☆53Updated 6 months ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆15Updated 2 months ago
- Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)☆41Updated 6 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆55Updated last month
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆49Updated 7 months ago
- Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients☆26Updated 4 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆95Updated 10 months ago
- ☆15Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆112Updated 4 months ago
- Directional Preference Alignment☆54Updated 4 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆62Updated 2 months ago
- ☆27Updated 3 months ago
- Dateset Reset Policy Optimization☆28Updated 9 months ago
- Implemention of the Decision-Pretrained Transformer (DPT) from the paper Supervised Pretraining Can Learn In-Context Reinforcement Learni…☆57Updated 8 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆30Updated 3 months ago
- Implements the Messenger environment and EMMA model.☆23Updated last year
- Direct preference optimization with f-divergences.☆13Updated 2 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆22Updated 4 months ago
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆20Updated last month