That design was trained in part utilizing their unreleased R1 “thinking” model. Today they’ve launched R1 itself, along with an entire household of brand-new models obtained from that base.

There’s a great deal 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 tidy MIT license. DeepSeek caution that “DeepSeek-R1-Zero comes across difficulties such as endless repeating, bad readability, and language blending.” … so they likewise released:

DeepSeek-R1-which “incorporates cold-start information before RL” and “attains performance comparable to OpenAI-o1 across mathematics, code, and reasoning jobs”. That one is also MIT certified, and is a similar 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 quickly play with myself. That’s where the brand-new distilled models are available in.

To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based on Llama and Qwen.

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

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

(I likewise simply saw the MIT license files state “Copyright © 2023 DeepSeek” so they may need to pay a bit more attention to how they copied those in.)

Licensing aside, these distilled models are monsters.

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

Quantized variations are already starting to show up. Up until now I have actually attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it’s actually fun to have fun with.

I’m running it using the combination of Ollama, LLM and the llm-ollama plugin.

First I brought and ran the design using Ollama itself:

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

Once the model has been brought, LLM can talk with it as well. I prefer using LLM for experiments because it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

Each reaction begins with a … pseudo-XML tag containing the chain of thought used to assist generate the action. 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 an interesting combination. Let me think of how these two characters may engage in an amusing 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 big teeth, thick fur, and they’re generally discovered in cooler climates, like icebergs or snowy areas. So, combining these 2 into a tea room setting is currently a funny image.

[…]
It then thought for 20 paragraphs before outputting the joke! Here’s the full records 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 sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to place dishes on the table, causing a few spills.

After a series of comical incidents, the walrus looks up and says with a smile, “This isn’t so fishy any longer.” The pelican smirks and says, “Maybe not, but we do have a lot of krill in our tea!”

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comical turmoil.

• Punchline: “This isn’t so fishy anymore” is a pun on the situation 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 funny while fitting the style.
  
  So yeah, the joke is awful. But the process of getting there was such a fascinating insight into how these brand-new designs work.
  
  This was a fairly small 8B model. I’m looking forward to checking out 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 model 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 bike timely too. It did refrain from doing extremely 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 remainder of the image
  
  It believed some more and provided me this:
  
  As with the earlier joke, the chain of believed in the transcript was far more fascinating than the end outcome.
  
  Other ways to attempt DeepSeek-R1
  
  If you wish to try the design out without setting up anything you can do so using chat.deepseek.com-you’ll require to create an account (sign in with Google, use an email address or offer a Chinese +86 phone number) and after that select the “DeepThink” choice below the prompt input box.
  
  DeepSeek provide the model 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 configuration file:
  
  Then run llm secrets set deepseek and paste in your API key, then use llm -m deepseek-reasoner ‘prompt’ to run prompts.
  
  This will not show you the thinking tokens, unfortunately. Those are provided by the API (example here) however LLM does not yet have a way to display them.