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

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

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

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

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

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

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

An SDXL fine-tuned on Dalle3 underwater imagery

2B instruct version of Google’s Gemma model

7B instruct version of Google’s Gemma model

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

A fashion model

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

A Steerable Model for Bach Chorales Generation

Google's Gemma2 9b instruct model

Demucs is an audio source separator created by Facebook Research.

Google's Gemma2 27b instruct model

Demucs Music Source Separation

7B base version of Google’s Gemma model

Animating prompts with stable diffusion

SDXL using DeepCache