That design was trained in part using their unreleased R1 "thinking" design. Today they've launched R1 itself, along with an entire family of new models obtained from that base.

There's a whole lot of things in the new release.

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences challenges such as endless repeating, bad readability, and language mixing." ... so they also released:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT licensed, and is a comparable size.

I don't have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily have fun with myself. That's where the new distilled designs are available in.

To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and oke.zone six thick models distilled from DeepSeek-R1 based on Llama and Qwen.

This is a fascinating flex! They have models based on Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and Llama 3 (Llama-3.1 8B and Llama 3.3 70B Instruct).

Weirdly those Llama models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache accredited so perhaps MIT is OK?

(I likewise just noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled designs are interesting monsters.

Running DeepSeek-R1-Distill-Llama-8B-GGUF

Quantized variations are already starting to appear. So far I have actually attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to play with.

I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.

First I brought and classifieds.ocala-news.com ran the model using Ollama itself:

This downloads around 8.5 GB of design data and begins an interactive chat user interface.

Once the design has actually been fetched, LLM can talk to it also. I prefer using LLM for experiments because it logs whatever to SQLite for later exploration.

I installed the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of idea utilized to assist create the reaction. For "a joke about a pelican and a walrus who run a tea room together" that began like this:

Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating combination. Let me think of how these two characters may engage in a humorous situation.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, wiki.vst.hs-furtwangen.de and they're typically discovered in colder climates, king-wifi.win like icebergs or snowy locations. So, integrating these two into a tea space setting is currently a funny image.

[...]
It then thought for koha-community.cz 20 paragraphs before outputting the joke! Here's the complete transcript and here's the output at the end, after the tag:

The Joke:

A pelican and a walrus decide to open a quaint little tea room together. The walrus, with its huge size, struggles to find comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, online-learning-initiative.org the pelican, attempting to assist, utilizes its beak to put saucers on the table, triggering a few spills.

After a series of funny incidents, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, however we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes lead to comical turmoil.

• Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less absurd. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the style.
  
  So yeah, the joke is terrible. But the process of arriving was such an interesting insight into how these new models work.
  
  This was a fairly small 8B design. I'm looking forward to checking out the Llama 70B variation, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design that I've worked on my own machine-I have high expectations.
  
  Update 21st January 2025: I got this quantized variation of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I tried my classic Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing very well:
  
  It aimed to me like it got the order of the elements incorrect, so I followed up with:
  
  the background ended up covering the of the image
  
  It thought some more and gave me this:
  
  Just like the earlier joke, the chain of thought in the records was far more fascinating than the end outcome.
  
  Other methods to attempt DeepSeek-R1
  
  If you desire to attempt the design out without installing anything you can do so utilizing chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or supply a Chinese +86 contact number) and then pick the "DeepThink" alternative listed below the prompt input box.
  
  DeepSeek provide the design by means of their API, utilizing an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and valetinowiki.racing paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
  
  This won't show you the reasoning tokens, unfortunately. Those are provided by the API (example here) but LLM doesn't yet have a method to show them.