Alternatives and similar repositories for DPO

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

• Asap7772 / understanding-rlhf
  Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…
  ☆32Updated last year
• likenneth / q_probe
  Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
  ☆41Updated last year
• mnoukhov / async_rlhf
  Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models
  ☆67Updated 6 months ago
• cmu-l3 / neurips2024-inference-tutorial-code
  NeurIPS 2024 tutorial on LLM Inference
  ☆47Updated 11 months ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆100Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• samuelarnesen / nyu-debate-modeling
  ☆23Updated last year
• katiekang1998 / reasoning_generalization
  ☆33Updated 10 months ago
• yidingjiang / ado
  The repository contains code for Adaptive Data Optimization
  ☆28Updated 11 months ago
• mcleish7 / gemstone-scaling-laws
  Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)
  ☆29Updated last month
• hamishivi / EasyLM
  Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…
  ☆75Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆85Updated last year
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆40Updated last month
• gregorbachmann / Next-Token-Failures
  ☆104Updated last year
• allenai / easy-to-hard-generalization
  Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"
  ☆48Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆47Updated last year
• facebookresearch / oni
  Learn online intrinsic rewards from LLM feedback
  ☆45Updated 11 months ago
• formll / resolving-scaling-law-discrepancies
  ☆20Updated 2 weeks ago
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 9 months ago
• upiterbarg / lintseq
  [ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)
  ☆19Updated 9 months ago
• abaheti95 / LoL-RL
  Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients
  ☆26Updated last year
• shenao-zhang / BARL
  Bayes-Adaptive RL for LLM Reasoning
  ☆41Updated 5 months ago
• abdulhaim / LMRL-Gym
  ☆105Updated last year
• RobertCsordas / moeut
  ☆88Updated last year
• hughbzhang / o1_inference_scaling_laws
  Replicating O1 inference-time scaling laws
  ☆90Updated 11 months ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated 2 years ago
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆78Updated last year
• sustcsonglin / mamba-triton
  ☆49Updated last year
• kyo-takano / chinchilla
  A toolkit for scaling law research ⚖
  ☆53Updated 9 months ago