Skip to content
repository radar
Other

💻DeepSeek-R1

FAINT SIGNAL COOLING

deepseek-ai/DeepSeek-R1

Open-Source Reasoning, at GPT-o1 Level

⭐ Hugely popular: 92k stars, gaining about 37 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
language n/a
license MIT

momentum

total stars 92k
stars added last week +37
HN peak 2k pts 1y 6mo ago
used by 1 repos & packages
commits / week 0 steady
issues closed 93% ~45d to close, median
contributors 12
release cadence n/a
last activity 1y 1mo ago

durability

backing company-owned DeepSeek
openness permissive

since we covered it

monthly average + 2k/mo (+3%/mo) · + 35k total since PR#1

why it's a big deal

  • Provides open reasoning model weights under an MIT license, so teams can run and build on GPT-o1-level reasoning commercially rather than only calling a closed API.
  • Ships six distilled variants from 1.5B to 70B built on Qwen2.5 and Llama, letting users pick a size that fits their own hardware instead of only the 671B full model.
  • Documents concrete usage settings, including temperature 0.5 to 0.7, no system prompt, and a forced think prefix, giving operators a known-good starting configuration.

under the hood

  • Written in Python around a mixture-of-experts model with 671B total parameters, 37B activated per token, and a 128K context window, derived from DeepSeek-V3-Base.
  • DeepSeek-R1-Zero is trained with large-scale reinforcement learning and no supervised fine-tuning, while DeepSeek-R1 adds cold-start data and two further SFT stages to cut repetition, poor readability, and language mixing.
  • Full models run through the DeepSeek-V3 setup rather than Hugging Face Transformers, while the distilled models are served with vLLM or SGLang.

Radar summary, generated from the project's public sources

star history

PR#1 · 57k92k now Jan 2025Aug 2026
  1. PR#1 57k 2025-02-05
  2. now 92k + 35k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-65 understory score output 0 · clout 65
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#1 2025-02-05 above the radar

    Open-Source Reasoning, at GPT-o1 Level

similar projects

compare these →
  • ☸️ EXO

    Python · leaner, 47k stars

    Run frontier AI locally.

    47k ACTIVE
  • 🔗 Fabric

    Go · leaner, 43k stars

    Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

    43k ACTIVE
  • 🖥️ openscreen

    TypeScript · leaner, 40k stars

    Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

    40k OFF THE RADAR

comments

Sign in with GitHub to add your blip on DeepSeek-R1.

loading comments…