Swallow-MS-7b-v0.1 Our Swallow-MS-7b-v0.1 model has undergone continual pre-training from the Mistra

Introduction An experimental version of IP-Adapter-FaceID: we use face ID embedding from a face reco

Mantis: Interleaved Multi-Image Instruction Tuning (Deprecated) Mantis is a multimodal conversationa

Mantis: Interleaved Multi-Image Instruction Tuning (Deprecated) Mantis is a multimodal conversationa

? MAmmoTH2: Scaling Instructions from the Web Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

? MAmmoTH2: Scaling Instructions from the Web Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

? MAmmoTH2: Scaling Instructions from the Web Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

? MAmmoTH2: Scaling Instructions from the Web Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

? MAmmoTH2: Scaling Instructions from the Web Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

? MAmmoTH2: Scaling Instructions from the Web Project Page: https://tiger-ai-lab.github.io/MAmmoTH2/

ConsistI2V Model Card ? Homepage | ? arXiv | ?️ Code | ? I2V-Bench | ? Space We propose ConsistI2V,

Llama-3-Chinese-8B-Instruct-v3-GGUF 这个仓库包含了Llama-3-Chinese-8B-Instruct-v3-GGUF（兼容llama.cpp/ol

模型描述 M2-Encoder是强大的中英双语多模态模型，它在我们构建的包含60亿图文对(30亿中文+30亿英文)的BM-6B上训练得到，支持zero-shot 图文跨模态检索(文搜图、图搜文) 以及

模型描述 M2-Encoder是强大的中英双语多模态模型，它在我们构建的包含60亿图文对(30亿中文+30亿英文)的BM-6B上训练得到，支持zero-shot 图文跨模态检索(文搜图、图搜文) 以及

模型描述 M2-Encoder是强大的中英双语多模态模型，它在我们构建的包含60亿图文对(30亿中文+30亿英文)的BM-6B上训练得到，支持zero-shot 图文跨模态检索(文搜图、图搜文) 以及

Model Card for CodeFuse-StarCoder2-15B [中文] [English] Clone with HTTP git clone https://w

Advancing Open-source Language Models with Mixed-Quality Data Online Demo |

SDXL Flash in collaboration with Project Fluently Introducing the new fast model SDXL Flash, we lea

引领中医智能化新篇章——“五行心智”智能中医问诊大模型 在人工智能技术飞速发展的今天，为了传承和发扬中医药的精髓，腾讯烟台新工科研究院团队经过深入调研和与中医药学院合作，成功研发出一款基于QWEN的

ComfyUI The most powerful and modular stable diffusion GUI and backend. This ui will let you design