deepseek-ai

Mirrored from GitHub organization: deepseek-ai

Updated 2025-07-18 08:11:28 +00:00
Expert Specialized Fine-Tuning
Updated 2025-05-22 07:47:10 +00:00
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Updated 2025-05-15 02:00:11 +00:00
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Updated 2025-04-22 11:09:39 +00:00
Updated 2025-04-09 05:36:23 +00:00
Expert Parallelism Load Balancer
Updated 2025-03-24 09:17:10 +00:00
Analyze computation-communication overlap in V3/R1.
Updated 2025-03-21 02:23:50 +00:00
A lightweight data processing framework built on DuckDB and 3FS.
Updated 2025-03-05 18:23:52 +00:00
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Updated 2025-02-26 05:03:37 +00:00
Janus-Series: Unified Multimodal Understanding and Generation Models
Updated 2025-02-01 07:58:14 +00:00
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Updated 2024-09-25 10:23:55 +00:00
Updated 2024-08-16 03:33:21 +00:00
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Updated 2024-04-24 05:01:06 +00:00
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Updated 2024-04-15 07:55:36 +00:00
DeepSeek LLM: Let there be answers
Updated 2024-02-04 12:22:15 +00:00