openai / summarize-from-feedback
Code for "Learning to summarize from human feedback"
☆1,022Updated last year
Alternatives and similar repositories for summarize-from-feedback:
Users that are interested in summarize-from-feedback are comparing it to the libraries listed below
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,324Updated last year
- ☆1,563Updated 2 years ago
- Expanding natural instructions☆996Updated last year
- Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-…☆558Updated 11 months ago
- A modular RL library to fine-tune language models to human preferences☆2,305Updated last year
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆463Updated 2 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,733Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆820Updated 2 years ago
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆993Updated 9 months ago
- ☆1,513Updated last week
- A research project for natural language generation, containing the official implementations by MSRA NLC team.☆721Updated 9 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆864Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,386Updated last year
- Task-based datasets, preprocessing, and evaluation for sequence models.☆574Updated last week
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆807Updated 10 months ago
- ☆1,217Updated 2 years ago
- Tools to download and cleanup Common Crawl data☆1,002Updated 2 years ago
- Crosslingual Generalization through Multitask Finetuning☆532Updated 7 months ago
- BLEURT is a metric for Natural Language Generation based on transfer learning.☆726Updated last year
- Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.☆1,144Updated last year
- UnifiedQA: Crossing Format Boundaries With a Single QA System☆435Updated 2 years ago
- Original Implementation of Prompt Tuning from Lester, et al, 2021☆679Updated 2 months ago
- ☆1,208Updated 9 months ago
- Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03…☆535Updated last year
- Adversarial Natural Language Inference Benchmark☆393Updated 2 years ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆524Updated last year
- [NIPS2023] RRHF & Wombat☆807Updated last year
- Library for Knowledge Intensive Language Tasks☆939Updated 3 years ago
- Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpe…☆437Updated last year
- Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning☆732Updated 2 years ago