openai / summarize-from-feedbackLinks
Code for "Learning to summarize from human feedback"
☆1,032Updated 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
Sorting:
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,344Updated last year
- Expanding natural instructions☆1,007Updated last year
- ☆1,229Updated 2 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆823Updated 2 years ago
- A modular RL library to fine-tune language models to human preferences☆2,329Updated last year
- ☆1,529Updated last week
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆869Updated last year
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,762Updated last month
- Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-…☆560Updated last year
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆1,003Updated 11 months ago
- Original Implementation of Prompt Tuning from Lester, et al, 2021☆687Updated 4 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆816Updated last year
- A research project for natural language generation, containing the official implementations by MSRA NLC team.☆729Updated 11 months ago
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆463Updated 2 years ago
- ☆1,581Updated 2 years ago
- Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.☆471Updated last year
- Tools to download and cleanup Common Crawl data☆1,017Updated 2 years ago
- Crosslingual Generalization through Multitask Finetuning☆538Updated 9 months ago
- Few-shot Learning of GPT-3☆352Updated last year
- Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.☆1,147Updated last year
- BLEURT is a metric for Natural Language Generation based on transfer learning.☆740Updated last year
- Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03…☆543Updated last year
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆769Updated last year
- Ask Me Anything language model prompting☆547Updated 2 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 2 years ago
- A prize for finding tasks that cause large language models to show inverse scaling☆613Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,402Updated last year
- Prefix-Tuning: Optimizing Continuous Prompts for Generation☆937Updated last year
- Task-based datasets, preprocessing, and evaluation for sequence models.☆583Updated 2 months ago
- Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.☆737Updated 2 years ago