allenai / RL4LMsLinks
A modular RL library to fine-tune language models to human preferences
☆2,308Updated last year
Alternatives and similar repositories for RL4LMs
Users that are interested in RL4LMs are comparing it to the libraries listed below
Sorting:
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,652Updated last year
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,335Updated last year
- Reference implementation for DPO (Direct Preference Optimization)☆2,583Updated 9 months ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,743Updated last year
- ☆1,520Updated last month
- Toolkit for creating, sharing and using natural language prompts.☆2,864Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,500Updated last week
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,478Updated 11 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,391Updated last year
- Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"☆1,171Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆809Updated 10 months ago
- Expanding natural instructions☆995Updated last year
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆770Updated last year
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,729Updated 9 months ago
- [NIPS2023] RRHF & Wombat☆809Updated last year
- Secrets of RLHF in Large Language Models Part I: PPO☆1,364Updated last year
- Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI☆2,033Updated 10 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆865Updated last year
- Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-…☆559Updated last year
- Aligning pretrained language models with instruction data generated by themselves.☆4,377Updated 2 years ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆3,949Updated last month
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,107Updated last year
- Original Implementation of Prompt Tuning from Lester, et al, 2021☆681Updated 2 months ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆1,999Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆849Updated last week
- ☆2,819Updated this week
- Aligning Large Language Models with Human: A Survey☆730Updated last year
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆4,002Updated this week
- ☆1,218Updated 10 months ago
- A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)☆1,118Updated last year