That model was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, together with a whole household of new models obtained from that base.

There's an entire lot of things in the new release.

DeepSeek-R1-Zero seems the base design. 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 comes across obstacles such as endless repetition, bad readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That a person is likewise MIT licensed, and asteroidsathome.net is a similar size.

I do not have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly have fun with myself. That's where the new distilled models are available in.

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

This is a remarkable flex! They have actually 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache accredited so perhaps MIT is OK?

(I also simply noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need 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 already starting to appear. Up until now I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to have fun with.

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

First I brought and ran the design utilizing Ollama itself:

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

Once the design has actually been brought, LLM can speak to it also. I choose utilizing LLM for experiments because it logs whatever to SQLite for later expedition.

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 action. For "a joke about a pelican and a walrus who run a tea space together" that started like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, online-learning-initiative.org that's an interesting mix. Let me think of how these 2 characters may communicate in a funny circumstance.

First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're usually discovered in cooler climates, like icebergs or snowy locations. So, these 2 into a tea room setting is already an amusing image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete records 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, overturning the teapot. Meanwhile, surgiteams.com the pelican, attempting to help, utilizes its beak to put saucers on the table, causing a couple of spills.

After a series of humorous accidents, the walrus searches for and says with a smile, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, but we do have a great deal of krill in our tea!"

Explanation:

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

• Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less absurd. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, making it funny while fitting the style.
  
  So yeah, the joke is awful. But the process of arriving was such an intriguing insight into how these new models work.
  
  This was a fairly little 8B model. I'm looking forward to checking out the Llama 70B version, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class design that I have actually 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 tried my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the aspects wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It thought some more and provided me this:
  
  Similar to the earlier joke, the chain of believed in the transcript was far more interesting than completion result.
  
  Other ways to try DeepSeek-R1
  
  If you desire to try the model out without setting up anything you can do so using chat.deepseek.com-you'll need to create an account (sign in with Google, use an email address or supply a Chinese +86 contact number) and pipewiki.org then pick the "DeepThink" alternative listed below the timely input box.
  
  DeepSeek provide the design via their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm secrets set deepseek and lovewiki.faith paste in your API key, then use llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This won't show you the reasoning tokens, regretfully. Those are served up by the API (example here) however LLM doesn't yet have a method to show them.