openai / lm-human-preferences
Code for the paper Fine-Tuning Language Models from Human Preferences
☆1,282Updated last year
Alternatives and similar repositories for lm-human-preferences:
Users that are interested in lm-human-preferences are comparing it to the libraries listed below
- A modular RL library to fine-tune language models to human preferences☆2,276Updated 11 months ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,682Updated last year
- Code for "Learning to summarize from human feedback"☆1,006Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆794Updated 7 months ago
- Expanding natural instructions☆975Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,587Updated last year
- Reference implementation for DPO (Direct Preference Optimization)☆2,386Updated 6 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,318Updated 11 months ago
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,416Updated 8 months ago
- ☆1,497Updated last week
- Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-…☆551Updated 9 months ago
- [NIPS2023] RRHF & Wombat☆799Updated last year
- Measuring Massive Multitask Language Understanding | ICLR 2021☆1,305Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,364Updated 11 months ago
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆760Updated last year
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆1,907Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆804Updated last week
- Prefix-Tuning: Optimizing Continuous Prompts for Generation☆910Updated 9 months ago
- Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Langu…☆348Updated last year
- Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"☆1,127Updated 11 months ago
- Original Implementation of Prompt Tuning from Lester, et al, 2021☆667Updated 2 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆857Updated last year
- ☆1,192Updated last year
- ☆728Updated 8 months ago
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆984Updated 6 months ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆3,729Updated this week
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,379Updated 2 months ago
- Toolkit for creating, sharing and using natural language prompts.☆2,773Updated last year
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆459Updated 7 months ago
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,668Updated 6 months ago