yuan2.0-2b-mars是源2.0-2B模型的2024年3月版本，源2.0 是浪潮信息发布的新一代基础语言大模型。我们开源了全部的3个模型源2.0-102B，源2.0-51B和源2.0-2B。并且我们提供了预训练，微调，推理服务的相关脚本，以供研发人员做进一步的开发。源2.0是在源1.0的基础上，利用更多样的高质量预训练数据和指令微调数据集，令模型在语义、数学、推理、代码、知识等不同方面具备更强的理解能力。

Idefics2 is an open multimodal model that accepts arbitrary sequences of image and text inputs and produces text outputs

IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

FlashFace: Human Image Personalization with High-fidelity Identity Preservation

Trained on VV instagram posts.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Qwen1.5 32B Chat variant. A transformer-based decoder-only language model. Good with Chinese and English.

full body version

Real-ESRGAN with optional face correction and adjustable upscale

text2img model trained on LAION HighRes and fine-tuned on internal datasets

snowflake-arctic-embed is a suite of text embedding models that focuses on creating high-quality retrieval models optimized for performance

Change eye (iris) color

Transfer the style of one image to another

input your name, and this model will print the most handsome man

pitch correction on your voice

ControlNet Line Art Anime

Mixtral 8x22b Instruct v0.1

hello world

Base version of Llama 3, a 70 billion parameter language model from Meta.

A 70 billion parameter language model from Meta, fine tuned for chat completions

Base version of Llama 3, an 8 billion parameter language model from Meta.

OpenBMB MiniCPM-V 2.8B is a strong multimodal large language model for efficient end-side deployment

A tiny model for testing out Cog

a powerful and competitive model like Midjourney v6 and DALL-E 3 but Open and Decentralized

HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach

An example of a rudimentary Q&A assistant for ACME SL

ZeST: Zero-Shot Material Transfer from a Single Image

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

WizardLM 2 8x22B

lightweight text-to-speech (TTS) model, trained on 10.5K hours of audio data

Accelerated transcription, word-level timestamps and diarization with whisperX large-v3

Mixtral-8x22b-v0.1-Instruct-Open-Hermes

Mixtral 8x22b v0.1 Zephyr Orpo 141b A35b v0.1

Midjourney v6 text-to-image quality model but Open and Decentralized

GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

A large, stereo MusicGen that acts as a useful tool for music producers

Nous Hermes 2 Mixtral 8x7B DPO is a Nous Research model trained over the Mixtral 8x7B MoE LLM

Mixtral-8x22b-v0.1-4bit

Image generation, Added: inpaint_strength loras_custom_urls

Use a subset of https://github.com/barun-saha/slide-deck-ai to create powerpoint slides from a json description - using python-pptx (https://github.com/scanny/python-pptx)