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

There's a lot of stuff in the new release.

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences difficulties such as endless repetition, poor readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency similar to OpenAI-o1 throughout math, code, and thinking tasks". That a person is likewise MIT accredited, and is a comparable size.

I do not have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily play with myself. That's where the models are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is a fascinating flex! They have actually designs based upon 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 licensed so maybe MIT is OK?

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

Licensing aside, these distilled models are fascinating beasts.

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

Quantized versions are currently starting to show up. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to have fun with.

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

First I fetched and ran the design using Ollama itself:

This downloads around 8.5 GB of model information and begins an interactive chat interface.

Once the design has been brought, LLM can speak with it too. I choose using LLM for experiments because it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

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

Okay, so I require 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 consider how these two characters might engage in a humorous situation.

First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, elearnportal.science and they're usually discovered in colder environments, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is currently an amusing image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full 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, has a hard time to discover comfortable chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, uses its beak to position saucers on the table, triggering a couple of spills.

After a series of comical mishaps, the walrus looks up and says with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes result in comical turmoil.

• Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less ridiculous. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.
  
  So yeah, the joke is horrible. But the process of getting there was such an interesting insight into how these new designs work.
  
  This was a fairly little 8B model. I'm looking forward to trying the Llama 70B variation, which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design that I've run 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 model working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted my timeless Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing effectively:
  
  It aimed to me like it got the order of the aspects incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and gave me this:
  
  Similar to the earlier joke, the chain of thought in the records was much more fascinating than completion result.
  
  Other ways to try DeepSeek-R1
  
  If you want to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or supply a Chinese +86 telephone number) and after that choose the "DeepThink" option below the timely input box.
  
  DeepSeek use the design via their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This won't show you the thinking tokens, unfortunately. Those are provided by the API (example here) however LLM doesn't yet have a way to display them.