기록 - 2025-01-29

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

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

Use your locally running AI models to assist you in your web browsing

LLM inference in C/C++

Qwen2.5-VL is the multimodal large language model series developed by the Qwen team at Alibaba Cloud.

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

The open-source repo for docs.github.com

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Expert Specialized Fine-Tuning

Ink Documentation

Ink Documentation