Phi-4 Bug Fixes(unsloth.ai)

171 points by danielhanchen 1 year ago | 50 comments

Unsloth Studio(unsloth.ai)

364 points by brainless 7 months ago | 67 comments

Announcement page for Unsloth Studio (Beta), an open-source no-code web UI for training, running, and exporting open AI models locally.

Mini-R1: Reproduce DeepSeek R1 "Aha Moment"(philschmid.de)

155 points by jonbaer 1 year ago | 11 comments

Official DeepSeek R1 Now on Ollama(ollama.com)

204 points by excerionsforte 1 year ago | 72 comments

Long-Context GRPO(unsloth.ai)

48 points by veryluckyxyz 1 year ago | 15 comments

Berkeley Researchers Replicate DeepSeek R1's Core Tech for Just $30: A Small Mod(xyzlabs.substack.com)

136 points by semking 1 year ago | 47 comments

DeepSeek-v3.1(api-docs.deepseek.com)

733 points by wertyk 1 year ago | 253 comments

DeepSeek API docs news post announcing the DeepSeek-V3.1 release, featuring hybrid think/non-think inference, faster reasoning, and stronger agent skills.

Deep Learning Is Not So Mysterious or Different(arxiv.org)

445 points by wuubuu 1 year ago | 112 comments

arXiv paper by Andrew Gordon Wilson arguing deep learning generalization phenomena like benign overfitting and double descent are explainable by soft inductive biases.

DeepSeek-Prover-V2(github.com)

359 points by meetpateltech 1 year ago | 74 comments

GitHub repository for DeepSeek-Prover-V2, DeepSeek's model for formal theorem proving, containing a paper PDF, README, model license, and miniF2F solutions.

DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis(artificialanalysis.ai)

530 points by theanonymousone 2 months ago | 289 comments

An Artificial Analysis page meant to benchmark DeepSeek V4 Flash's intelligence, performance and price, which returned a 404 Page not found error.

DeepSeek-V4-Flash Update(api-docs.deepseek.com)

657 points by dnhkng 2 months ago | 313 comments

DeepSeek API docs changelog entry announcing the DeepSeek-V4-Flash API public beta with improved agent benchmark results.

DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost(esengine.github.io)

706 points by Alifatisk 5 months ago | 273 comments

Project homepage for Reasonix, an open-source DeepSeek-native terminal coding agent built around DeepSeek's prefix cache for low-cost long sessions.