Llama-3 8B Gradient Instruct 262k LoRA Adapter 这是从语言模型中提取的 LoRA 适配器。它是使用mergekit提取的。 LoRA 详情 这个 LoRA

Llama-3 8B Gradient Instruct 262k Join our custom agent and long context (262k-1M+) waitlist: https:

InternLM2-WQX-VL-20B InternLM2-WQX HOT [![li

InternLM2-WQX-20B InternLM2-WQX HOT [![licen

EasyAnimate | 高分辨率长视频生成的端到端解决方案 ? EasyAnimate是一个用于生成高分辨率和长视频的端到端解决方案。我们可以训练基于转换器的扩散生成器，训练用于处理长视频的VAE

EasyAnimate | 高分辨率长视频生成的端到端解决方案 ? EasyAnimate是一个用于生成高分辨率和长视频的端到端解决方案。我们可以训练基于转换器的扩散生成器，训练用于处理长视频的VAE

diffuser port of https://huggingface.co/osunlp/InstructPix2Pix-MagicBrush. diffuser version of Magic

Mengzi3-8B 以创新为引擎，驱动 AI 生态的可持续发展！ 在 Mengzi3-13B 大模型 3 月底开源后不久，澜舟科技全新推出的又一款轻量化大模型——Mengzi3-8B，现已正式开源！

NDLSLM1.5_0.8B-Chat 介绍 NDLSLM1.50.8B-Chat：此模型是基于NDLSLM0.8B-base模型，在大约为236万条SFT中文数据进行全参数微调的Chat模型，其框架

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,