rlhf · GitHub Topics | GitHub 中文社区

Open-Assistant

@LAION-AI

#大语言模型# 面向所有人的对话式 AI，我们相信我们即将创造一场革命，正如 Stable Diffusion 改变了现代艺术的创作过程, 我们将透过对话式 AI 来改变世界.

chatgpt language-model rlhf ai assistant discord-bot machine-learning nextjs python

Python37.08 k

3 个月前

LLaMA-Factory

@hiyouga

#大语言模型# Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

fine-tuning language-model llama llm peft transformers rlhf qlora quantization chatglm

Python34.73 k

1 天前

InternLM

@InternLM

#大语言模型# Official release of InternLM2.5 base and chat models. 1M context support

chatbot gpt large-language-model long-context rlhf fine-tuning-llm llm chinese flash-attention pretrained-models

Python6.5 k

1 天前

alignment-handbook

Hugging Face@huggingface

#大语言模型# Robust recipes to align language models with human and AI preferences

llm rlhf transformers

Python4.7 k

1 天前

awesome-RLHF

@opendilab

#计算机科学# A curated list of reinforcement learning with human feedback resources (continually updated)

deep-learning deep-reinforcement-learning human-feedback reinforcement-learning rlhf large-language-models

3.48 k

11 天前

docta

@Docta-ai

A Doctor for your data

data data-centric-ai data-centric-machine-learning data-curation data-diagnosis language-model rlhf

Python2.95 k

10 个月前

alpaca_eval

@tatsu-lab

#自然语言处理# An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

deep-learning evaluation foundation-models instruction-following large-language-models leaderboard nlp rlhf

Jupyter Notebook1.53 k

12 天前

WebGLM

THUDM@THUDM

#大语言模型# WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

chatgpt llm rlhf webglm

Python1.52 k

1 年前

SimPO

@princeton-nlp

SimPO: Simple Preference Optimization with a Reference-Free Reward

alignment large-language-models preference-alignment rlhf

Python274

6 个月前