DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source

A reasoning model trained with reinforcement learning, on par with OpenAI o1

DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL

Janus-Pro is a novel autoregressive framework for multimodal understanding

Janus-Pro is a novel autoregressive framework for multimodal understanding

DeepSeek-VL: An open-source Vision-Language Model designed for real-world vision and language understanding applications

Pushing the Limits of Mathematical Reasoning in Open Language Models - Base model

Pushing the Limits of Mathematical Reasoning in Open Language Models - Instruct model

A quantized 33B parameter language model from Deepseek for SOTA repository level code completion

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1

DeepSeek-VL2-small, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL

Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

DeepSeek LLM, an advanced language model comprising 67 billion parameters. Trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese

A ~7B parameter language model from Deepseek for SOTA repository level code completion

The DeepFloyd IF model has been initially released as a non-commercial research-only model. Please make sure you read and abide to the license before using it.

DeepFake AI

A fashion model

An SDXL fine-tuned on Dalle3 underwater imagery

2B instruct version of Google’s Gemma model

7B instruct version of Google’s Gemma model

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

Deep Flexible Structure-preserving Image Smoothing

Deep3D: Real-Time end-to-end 2D-to-3D Video Conversion, based on deep learning

Gemma2 2b by Google