voidful / TextRL
Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
☆539Updated 4 months ago
Related projects: ⓘ
- Implementation of Reinforcement Learning from Human Feedback (RLHF)☆168Updated last year
- Expanding natural instructions☆944Updated 9 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆758Updated 2 months ago
- Accompanying repo for the RLPrompt paper☆293Updated 3 months ago
- A modular RL library to fine-tune language models to human preferences☆2,173Updated 6 months ago
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆748Updated last year
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆456Updated last year
- This repository contains a collection of papers and resources on Reasoning in Large Language Models.☆523Updated 10 months ago
- Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03…☆508Updated 9 months ago
- [NIPS2023] RRHF & Wombat☆789Updated 11 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆300Updated 11 months ago
- [NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation☆461Updated 6 months ago
- Fusion-in-Decoder☆548Updated 11 months ago
- A research project for natural language generation, containing the official implementations by MSRA NLC team.☆683Updated last month
- ☆246Updated 9 months ago
- LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA☆177Updated last year
- Crosslingual Generalization through Multitask Finetuning☆510Updated last year
- Code for "Learning to summarize from human feedback"☆975Updated last year
- Original Implementation of Prompt Tuning from Lester, et al, 2021☆642Updated 3 months ago
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,204Updated last year
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆411Updated 2 months ago
- DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI☆468Updated 4 months ago
- Chain-of-Hindsight, A Scalable RLHF Method☆213Updated 11 months ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆499Updated 10 months ago
- Papers and Datasets on Instruction Tuning and Following. ✨✨✨☆449Updated 5 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆695Updated last week
- Prod Env☆375Updated 11 months ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,561Updated last year
- A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human…☆206Updated 3 months ago
- All available datasets for Instruction Tuning of Large Language Models☆231Updated 9 months ago