mnoukhov / async_rlhfLinks
Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models
☆54Updated last month
Alternatives and similar repositories for async_rlhf
Users that are interested in async_rlhf are comparing it to the libraries listed below
Sorting:
- Simple and efficient pytorch-native transformer training and inference (batched)☆75Updated last year
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆119Updated this week
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- A toolkit for scaling law research ⚖☆49Updated 4 months ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- ☆93Updated 8 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆55Updated 3 months ago
- ☆52Updated last year
- Long Context Extension and Generalization in LLMs☆56Updated 8 months ago
- Replicating O1 inference-time scaling laws☆87Updated 6 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated 11 months ago
- ☆49Updated 3 weeks ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆32Updated 2 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated 9 months ago
- Official implementation of TBA for async LLM post-training.☆15Updated last week
- NeurIPS 2024 tutorial on LLM Inference☆45Updated 5 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆73Updated 7 months ago
- Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆94Updated last month
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆50Updated last month
- Revisiting Mid-training in the Era of RL Scaling☆48Updated last month
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆159Updated last week
- RL algorithm: Advantage induced policy alignment☆65Updated last year
- [ICLR 2025] Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"☆60Updated 3 months ago
- ☆46Updated 3 months ago
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆29Updated last year
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆40Updated 3 weeks ago
- ☆48Updated 3 weeks ago
- ☆97Updated 11 months ago
- Minimal but scalable implementation of large language models in JAX☆34Updated 7 months ago