Notes and commented code for RLHF (PPO)
☆138Feb 27, 2024Updated 2 years ago
Alternatives and similar repositories for rlhf-ppo
Users that are interested in rlhf-ppo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Notes on Direct Preference Optimization☆28Apr 14, 2024Updated 2 years ago
- Distributed training (multi-node) of a Transformer model☆105Apr 10, 2024Updated 2 years ago
- LLaMA 2 implemented from scratch in PyTorch☆381Sep 25, 2023Updated 3 years ago
- ☆27Aug 27, 2026Updated last month
- Notes on the Mistral AI model☆22Dec 27, 2023Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Because it's there.☆16Sep 22, 2024Updated 2 years ago
- Notes on quantization in neural networks☆136Dec 14, 2023Updated 2 years ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆20Nov 19, 2024Updated last year
- Training codebase for K2-V2☆22Dec 17, 2025Updated 10 months ago
- ☆11Mar 7, 2024Updated 2 years ago
- Pytorch code for experiments on Linear Transformers☆24Jan 12, 2024Updated 2 years ago
- ☆14Nov 15, 2022Updated 3 years ago
- This repo contains all the codes for SEScore implementation☆15Mar 3, 2025Updated last year
- Library for training process reward models☆29Jun 3, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models (LLMs + MCTS + Self-Improvement)☆51Dec 15, 2023Updated 2 years ago
- Synthetic Data Generation for Evaluation☆16Feb 21, 2025Updated last year
- Training Coder Models with Critique Reinforcement Learning [ICLR26]☆13Apr 11, 2026Updated 6 months ago
- JMLR Cover Letter Template☆10Dec 15, 2021Updated 4 years ago
- ☆21Sep 14, 2026Updated last month
- ☆13Feb 14, 2022Updated 4 years ago
- Filter dialog data with a simple entropy-based method (see ACL paper)☆14Oct 4, 2019Updated 7 years ago
- ☆19Dec 16, 2024Updated last year
- [COLM 2026] MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning☆131Jul 9, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- solution for cs336-assignment1,2,5 , including colab code link and blog link.☆17Feb 20, 2026Updated 7 months ago
- LORA: Low-Rank Adaptation of Large Language Models implemented using PyTorch☆129Jul 24, 2023Updated 3 years ago
- ☆17Mar 14, 2024Updated 2 years ago
- ☆11Sep 25, 2025Updated last year
- ☆14Jul 13, 2025Updated last year
- 测试 https://huggingface.co/OFA-Sys/gsm8k-rft-llama7b-u13b 的 GSM8K 分数☆15Aug 10, 2023Updated 3 years ago
- Clustered Compositional Embeddings☆13Oct 25, 2023Updated 2 years ago
- ☆450Apr 10, 2025Updated last year
- NeurIPS 2024 tutorial on LLM Inference☆50Dec 10, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 3 years ago
- [SOML'21] Reference material, tutorial notebooks and other resources for Summer of ML, organised by AIMLC IITD.☆10Jul 4, 2021Updated 5 years ago
- Safe Python Code Execution Environment for Language Models☆17Oct 9, 2026Updated last week
- Ἀνατομή is a PyTorch library to analyze representation of neural networks☆13Jan 31, 2024Updated 2 years ago
- Full stack LLM (Pre-training/finetuning, PPO(RLHF), Inference, Quant, etc.)☆45Feb 21, 2025Updated last year
- [ICLR 2026] PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, co…☆40Sep 9, 2025Updated last year
- ☆13Sep 16, 2024Updated 2 years ago