AI

Chat & support: TheBloke's Discord server Want to contribute? TheBloke's Patreon p

RWKV v5 1.5B 16k微调模型 模型擅长角色扮演，建议参数temp 1, topp 0.3, presence penalty 0.1-0.3 frequency penalty 0.8-1

DistilBERT base model (uncased) This model is a distilled version of the BERT base model. It was int

Ziya2-13B-Base Main Page:Fengshenbang Github: Fengshenbang-LM 姜子牙系列模型 Ziya-LLaMA-13B-v1 Ziya-LLaM

RWKV v5 1.5B 16k微调模型 模型擅长小说写作，具备小说扩写，续写，定向续写等指令，欢迎测试反馈，QQ群：343127667 建议参数temp 1, topp 0.3, presence

Model Card for FLAN-T5 base Table of Contents TL;DR Model Details Usage Uses Bias, Risks, and Limi

Github • WeChat We opensource our Aquila2 series, now including Aquila2, the base language models,

Chat & support: my new Discord server Want to contribute? TheBloke's Patreon page

Github • WeChat We opensource our Aquila2 series, now including Aquila2, the base language models,

mPLUG-Owl2介绍 mPLUG-Owl2是一种面向多模态语言模型的模块化的训练范式。其能学习与语言空间相适应的视觉知识，并支持在多模态场景(支持图片、文本输入)下进行多轮对话。它涌现多图关系理解

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data GitHub Repo • Onli

MiniMA-3B ? arXiv | ? GitHub | ? HuggingFace-MiniMA | ? HuggingFace-MiniChat | ? ModelScope-MiniMA |

模型描述 (Model Description) IP-Adapter是一种有效且轻量级的适配器，可为预训练的文本到图像扩散模型实现图像提示功能。IP-Adapter还可以推广到使用现有可控工具的可控

Image drawn by GPT-4 DALL·E 3 TL;DR: Perhaps better than all existing models < 70B, in most quantita

Github • WeChat We opensource our Aquila2 series, now including Aquila2, the base language models,

Chat & support: my new Discord server Want to contribute? TheBloke's Patreon page

ERes2Net 语种识别模型 ERes2Net模型结合全局特征和局部特征，从而提高说话人识别性能。局部特征融合将一个单一残差块内的特征融合提取局部信号；全局特征融合使用不同层级输出的不同尺度声学特征

MiniChat-3B ? arXiv | ? GitHub | ? HuggingFace-MiniMA | ? HuggingFace-MiniChat | ? ModelScope-MiniMA

RoBERTa large model Pretrained model on English language using a masked language modeling (MLM) obje

ERes2Net 语种识别模型 ERes2Net模型结合全局特征和局部特征，从而提高说话人识别性能。局部特征融合将一个单一残差块内的特征融合提取局部信号；全局特征融合使用不同层级输出的不同尺度声学特征