Topic: rlhf Goto Github

👇 Here are 79 public repositories matching this topic...

alexrame / rewardedsoups
rlhf,Rewarded soups official implementation
User: alexrame
deeplearning rlhf

argilla-io / argilla
rlhf,✨Argilla: the open-source feedback platform for LLMs
Organization: argilla-io
Home Page: https://docs.argilla.io
human-in-the-loop natural-language-processing mlops developer-tools text-labeling annotation-tool nlp machine-learning active-learning weak-supervision

argilla-io / distilabel
rlhf,⚗️ AI Feedback framework for scalable LLM alignment
Organization: argilla-io
Home Page: https://distilabel.argilla.io
ai huggingface llms openai python rlaif rlhf

cambioml / pykoi
rlhf,pykoi: Active learning in one unified interface
User: cambioml
Home Page: https://www.cambioml.com
ai chatbot feedback language-model llm machine-learning rlhf

cogment / cogment-verse
rlhf,Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)
Organization: cogment
Home Page: https://cogment.ai/cogment_verse
reinforcement-learning human-in-the-loop-learning cogment rlhf

csmile-1006 / preferencetransformer
rlhf,Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)
User: csmile-1006
Home Page: https://sites.google.com/view/preference-transformer
rl rlhf robotics

docta-ai / docta
rlhf,A Doctor for your data
Organization: docta-ai
data data-centric-ai data-centric-machine-learning data-curation data-diagnosis language-model rlhf

g-u-n / t2i-humanfeedback
rlhf,Implementations of Baseline Methods for Aligning Text2Img Diffusion Models with Human FeedBack
User: g-u-n
human-feedback rlhf stable-diffusion text2img

garyyufei / alignllmhumansurvey
rlhf,Aligning Large Language Models with Human: A Survey
User: garyyufei
Home Page: https://arxiv.org/abs/2307.12966
chatgpt gpt-4 large-language-models llms rlhf supervised-finetuning survey awesome chinese-llama llama

glgh / awesome-llm-human-preference-datasets
rlhf,A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.
User: glgh
awesome-list datasets eval human-preferences llm machine-learning nlp rlhf

hiyouga / chatglm-efficient-tuning
rlhf,Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
User: hiyouga
chatglm chatgpt fine-tuning lora alpaca peft huggingface language-model transformers pytorch

hiyouga / llama-factory
rlhf,Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
User: hiyouga
fine-tuning language-model llama llm peft transformers rlhf pre-training qlora quantization

huggingface / alignment-handbook
rlhf,Robust recipes for to align language models with human and AI preferences
Organization: huggingface
Home Page: https://huggingface.co/HuggingFaceH4
llm rlhf transformers

jackaduma / alpaca-lora-rlhf-pytorch
rlhf,A full pipeline to finetune Alpaca LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Alpaca architecture. Basically ChatGPT but with Alpaca
User: jackaduma
alpaca chatgpt llama llm lora pytorch rlhf gpt finetune deepspeed

jackaduma / chatglm-lora-rlhf-pytorch
rlhf,A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM
User: jackaduma
lora chatglm chatglm-6b chatgpt finetune gpt llm pytorch rlhf llama

jackaduma / vicuna-lora-rlhf-pytorch
rlhf,A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically ChatGPT but with Vicuna
User: jackaduma
chatgpt finetune gpt llama llm lora peft ppo pytorch reward-models

jasonvanf / llama-trl
rlhf,LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA
User: jasonvanf
adapter gpt llama lora peft ppo rlhf trl chatgpt transformer

jerry1993-tech / cornucopia-llama-fin-chinese
rlhf,聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效的金融垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
User: jerry1993-tech
Home Page: https://zhuanlan.zhihu.com/p/633736418
llama nlp chinese finance rlhf sft qa text-generation large-language-models transformers

jianzhnie / open-chatgpt
rlhf,The open source implementation of ChatGPT, Alpaca, Vicuna and RLHF Pipeline. 从0开始实现一个ChatGPT.
User: jianzhnie
Home Page: https://jianzhnie.github.io/machine-learning-wiki/#/deep-rl/papers/RLHF
chatgpt gpt llm rlhf ppo llama stanford-alpaca lora peft

joyce94 / llm-rlhf-tuning
rlhf,LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)
User: joyce94
fine-tuning language-model llama llm lora peft ppo reinforcement-learning rlhf

l294265421 / alpaca-rlhf
rlhf,Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat
User: l294265421
Home Page: https://88aeeb3aef5040507e.gradio.live/
chatgpt rlhf llama alpaca reinforcement-learning language-model llm large-language-models

l294265421 / my-alpaca
rlhf,Reproduce alpaca
User: l294265421
Home Page: https://88aeeb3aef5040507e.gradio.live/
alpaca chatgpt alpaca-lora colab autodl multi-turn rlhf

laion-ai / open-assistant
rlhf,OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Organization: laion-ai
Home Page: https://open-assistant.io
chatgpt language-model rlhf ai assistant discord-bot machine-learning nextjs python

lhao499 / chain-of-hindsight
rlhf,Chain-of-Hindsight, a simpler and more effective alternative to RLHF
User: lhao499
large-language-models rlhf learning-from-human-feedback

liziniu / remax
rlhf,
User: liziniu
large-language-models reinforcement-learning rlhf

log10-io / log10
rlhf,Python client library for managing your LLM data in one place
Organization: log10-io
Home Page: https://log10.io
agents ai artificial-intelligence autonomous-agents debugging langchain langchain-python llmops logging monitoring

mengdi-li / awesome-rlaif
rlhf,A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)
User: mengdi-li
rlaif alignment rlhf llms rl

mindspore-courses / step_into_llm
rlhf,MindSpore online courses: Step into LLM
Organization: mindspore-courses
llm natural-language-processing nlp large-language-models mindspore bert chatgpt codegeex gpt gpt2

miraclemarvel55 / chatglm-rlhf
rlhf,对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF
User: miraclemarvel55
chatglm custom nickname rlhf ppo reward similarity

miraclemarvel55 / llama-moss-rlhf-lora
rlhf,用RLHF可选LoRA对LLaMA和MOSS进行训练|Training LLaMA or MOSS with RLHF [LoRA]
User: miraclemarvel55
llama moss chinese lora ppo rl rlhf reward similarity

nlp-uoregon / okapi
rlhf,Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
User: nlp-uoregon
bloom chatbot dataset instruction-tuning language-model large-language-models multilingual nlp question-answering reinforcement-learning

opendilab / awesome-rlhf
rlhf,A curated list of reinforcement learning with human feedback resources (continually updated)
Organization: opendilab
deep-learning deep-reinforcement-learning human-feedback reinforcement-learning rlhf large-language-models

opening-up-chatgpt / opening-up-chatgpt.github.io
rlhf,Tracking instruction-tuned LLM openness. Paper: Liesenfeld, Andreas, Alianda Lopez, and Mark Dingemanse. 2023. “Opening up ChatGPT: Tracking Openness, Transparency, and Accountability in Instruction-Tuned Text Generators.” In Proceedings of the 5th International Conference on Conversational User Interfaces. doi:10.1145/3571884.3604316.
Organization: opening-up-chatgpt
Home Page: https://opening-up-chatgpt.github.io/
chatgpt llm open-source rlhf transparency chatgpt-free

openllmai / openrlhf
rlhf,A Ray-based High-performance RLHF framework (for 7B on RTX4090 and 34B on A100)
Organization: openllmai
llm ray rlhf deepspeed transformers

patrick-tssn / llm4academic
rlhf,Theory and Practice about LLMs
User: patrick-tssn
accelerate api-wrapper instruction-tuning large-language-models multi-modal pretraining rlhf llm open-source

pku-alignment / beavertails
rlhf,BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
Organization: pku-alignment
Home Page: https://sites.google.com/view/pku-beavertails
ai-safety human-feedback human-feedback-data language-model large-language-model llm llms rlhf safe-rlhf safety

pku-alignment / safe-rlhf
rlhf,Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Organization: pku-alignment
Home Page: https://pku-beaver.github.io
ai-safety alpaca datasets deepspeed large-language-models llama llm llms reinforcement-learning reinforcement-learning-from-human-feedback

rucaibox / llmsurvey
rlhf,The official GitHub page for the survey paper "A Survey of Large Language Models".
Organization: rucaibox
Home Page: https://arxiv.org/abs/2303.18223
chain-of-thought chatgpt in-context-learning instruction-tuning large-language-models llm llms natural-language-processing pre-trained-language-models pre-training

sanjibnarzary / awesome-llm
rlhf,Curated list of open source and openly accessible large language models
User: sanjibnarzary
Home Page: https://github.com/sanjibnarzary/awesome-llm
alpaca bloom gpt llama llm llms nlp opt transformer transformers

ssbuild / chatglm_rlhf
rlhf,chatglm_rlhf_finetuning
User: ssbuild
chatglm finetuning lora reward rlhf chat qlora

ssbuild / llm_rlhf
rlhf,realize the reinforcement learning training for gpt2 llama bloom and so on llm model
User: ssbuild
llm lora reward rlhf trlx trl llm-rlhf

tatsu-lab / alpaca_eval
rlhf,An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Organization: tatsu-lab
Home Page: https://tatsu-lab.github.io/alpaca_eval/
deep-learning evaluation foundation-models instruction-following large-language-models leaderboard nlp rlhf

thudm / imagereward
rlhf,[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Organization: thudm
diffusion-models generative-model rlhf human-preferences

thudm / webglm
rlhf,WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)
Organization: thudm
chatgpt llm rlhf webglm

tomekkorbak / pretraining-with-human-feedback
rlhf,Code accompanying the paper Pretraining Language Models with Human Preferences
User: tomekkorbak
Home Page: https://arxiv.org/abs/2302.08582
ai-alignment ai-safety decision-transformers gpt language-models pretraining reinforcement-learning rlhf

vicgalle / zero-shot-reward-models
rlhf,ZYN: Zero-Shot Reward Models with Yes-No Questions
User: vicgalle
llm reinforcement-learning rlhf zero-shot reward-models trlx rlaif

voidful / textrl
rlhf,Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
User: voidful
nlp reinforcement-learning language-model nlg controlled-nlg gpt-3 gpt-2 pytorch rlhf chatgpt

wangrongsheng / medqa-chatglm
rlhf,🛰️ 基于真实医疗对话数据在ChatGLM上进行LoRA、P-Tuning V2、Freeze、RLHF等微调，我们的眼光不止于医疗问答
User: wangrongsheng
Home Page: https://www.wangrs.co/MedQA-ChatGLM/
chatglm-6b chatgpt dataset fine-tuning freeze huggingface large-language-models llms lora medical

xrsrke / instructgoose
rlhf,Implementation of Reinforcement Learning from Human Feedback (RLHF)
User: xrsrke
Home Page: https://xrsrke.github.io/instructGOOSE/
instructgpt reinforcement-learning rlhf chatgpt human-feedback

xtreme1-io / xtreme1
rlhf,Xtreme1 - The Next GEN Platform for Multimodal Training Data. #3D annotation, 3D segmentation, lidar-camera fusion annotation, image annotation and RLHF tools are supported!
Organization: xtreme1-io
Home Page: https://www.basic.ai
3d-annotation annotation-tool lidar-camera-fusion machine-learning rlhf