That model was trained in part using their unreleased R1 "reasoning" model. Today they have actually released R1 itself, together with a whole household of new models obtained from that base.

There's a great deal of things in the brand-new release.

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences difficulties such as limitless repeating, poor readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and thinking jobs". That one is also MIT certified, and townshipmarket.co.za is a comparable size.

I don't 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 have fun with myself. That's where the brand-new distilled designs are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, bio.rogstecnologia.com.br and 6 thick models distilled from DeepSeek-R1 based on Llama and Qwen.

This is an interesting flex! They have 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 attached, wiki.philo.at which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache licensed so maybe MIT is OK?

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

Licensing aside, these distilled models are interesting beasts.

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

Quantized versions are currently starting to show up. So far I've attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to play with.

I'm running it utilizing the combination of Ollama, wiki.eqoarevival.com LLM and the llm-ollama plugin.

First I fetched and ran the model utilizing Ollama itself:

This downloads around 8.5 GB of model data and it-viking.ch starts an interactive chat interface.

Once the design has been fetched, higgledy-piggledy.xyz LLM can speak with it too. I prefer utilizing LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

Each action starts with a ... pseudo-XML tag containing the chain of idea utilized to help create the reaction. For "a joke about a pelican and a walrus who run a tea space 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 mix. Let me consider how these two characters may connect in an amusing scenario.

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 found in cooler climates, like icebergs or snowy locations. So, integrating these 2 into a tea space setting is currently a funny 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 choose to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfortable chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place dishes on the table, causing a couple of spills.

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

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes result in comical mayhem.

• Punchline: "This isn't so fishy anymore" is a pun on the situation becoming less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it funny while fitting the style.
  
  So yeah, wiki.eqoarevival.com the joke is awful. But the process of getting there was such an interesting insight into how these new models work.
  
  This was a fairly small 8B design. I'm looking forward to trying 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 operated on my own machine-I have high expectations.
  
  Update 21st January 2025: I got this quantized version 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 bicycle timely too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the aspects incorrect, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It thought some more and provided me this:
  
  Just like the earlier joke, the chain of thought in the transcript was much more interesting than completion result.
  
  Other methods to attempt DeepSeek-R1
  
  If you wish to attempt the model out without setting up anything you can do so utilizing chat.deepseek.com-you'll need to develop an account (check in with Google, use an email address or offer a Chinese +86 phone number) and then choose the "DeepThink" alternative listed below the prompt input box.
  
  DeepSeek use the model via their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run triggers.
  
  This won't reveal you the reasoning tokens, unfortunately. Those are dished out by the API (example here) however LLM does not yet have a way to display them.