17 skills found
SkyWorkAIGC / SkyChat Chinese Chatbot GPT3SkyChat是一款基于中文GPT-3 api的聊天机器人项目。它可以像chatGPT一样,实现人机聊天、问答、中英文互译、对对联、写古诗等任务。| SkyChat is a Chatbot project based on Chinese GPT3 API. Like chatGPT, it can do human-machine chat, question and answer, and can also complete tasks such as Chinese-English or English-Chinese translation, content continuation, couplets, and Chinese ancient poems writing.
kevinamiri / Instructgpt PromptsInstruction-based prompts for generating and classifying text.
SkyWorkAIGC / SkyText Chinese GPT3SkyText是由奇点智源发布的中文GPT3预训练大模型,可以进行文章续写、对话、中英翻译、内容风格生成、推理、诗词对联等不同任务。| SkyText is a Chinese GPT3 pre-trained large model released by Singularity-AI, which can perform different tasks such as chatting, Q&A, and Chinese-English translation.
xrsrke / InstructGOOSEImplementation of Reinforcement Learning from Human Feedback (RLHF)
CarperAI / InstructGPTFor experiments involving instruct gpt. Currently used for documenting open research questions.
michaelnny / InstructLLaMAImplements pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), to train and fine-tune the LLaMA2 model to follow human instructions, similar to InstructGPT or ChatGPT, but on a much smaller scale.
flippe3 / Chat LtuOpen source implementation of InstructGPT (not finished)
joeljang / Negated Prompts For Llms[NeurIPS 2022 Workshop] A Case Study with Negated Prompts using T0 (3B, 11B), InstructGPT (350M-175B), GPT-3 (350M - 175B) & OPT (125M - 175B) LMs
Esmail-ibraheem / AxonAI research lab🔬: implementations of AI papers and theoretical research: InstructGPT, llama, transformers, diffusion models, RLHF, etc...
LanXiu0523 / RLHF InstructGPTReproduce instructGPT
cauyxy / CatGPTCatGPT is an open-source project aimed at replicating the PPO algorithm of InstructGPT and training it on a Chinese dataset.
hlp-ai / MiniChatGPTMini ChatGPT
Bhaavya / InstructGPT AnalogiesNo description available
Zayatsoff / InstructGPT3 SandboxThe goal is to use GPT-3 to answer high school discussion questions. A future version of this project will use a fine-tuned GPT2 model for this purpose.
HackWithSumit / ChatGPT OpenAIChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response
yusun-nlp / InstructforNERpaper: InstructGPT在命名实体识别任务中的表现和挑战
NJUxlj / InstructGPT Reproducereproduce the Instruct from the paper 《Training language models to follow instructions with human feedback》