That model was trained in part using their unreleased R1 "thinking" design. Today they've launched R1 itself, along with a whole household of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters challenges such as limitless repeating, bad readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance similar to OpenAI-o1 across mathematics, code, and thinking jobs". That a person is likewise MIT accredited, and 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 2 models are something I can quickly have fun with myself. That's where the brand-new distilled designs are available in.

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

This is a fascinating 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 designs have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache certified so perhaps MIT is OK?

(I likewise simply discovered 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 designs are interesting monsters.

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

Quantized variations are already beginning to appear. So far I have actually tried just one of 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 fetched and ran the design utilizing 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 too. I prefer utilizing LLM for experiments since 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 help generate the response. 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 room together. Hmm, that's a fascinating combination. Let me think of how these two characters might communicate in a humorous circumstance.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, higgledy-piggledy.xyz and they're typically discovered in cooler environments, like icebergs or snowy locations. So, integrating these two into a tea room setting is currently 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 space together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, to assist, uses its beak to put saucers on the table, causing a few spills.

After a series of humorous mishaps, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "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 cause comical chaos.

• Punchline: "This isn't so fishy any longer" is a pun on the circumstance 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 amusing while fitting the style.
  
  So yeah, the joke is awful. But the procedure of getting there was such a fascinating insight into how these brand-new designs work.
  
  This was a fairly little 8B design. I'm looking forward to attempting 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've worked 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 traditional Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing really well:
  
  It aimed to me like it got the order of the components wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It believed some more and offered me this:
  
  Just like the earlier joke, the chain of believed in the transcript was far more fascinating than the end result.
  
  Other methods to attempt DeepSeek-R1
  
  If you want to attempt the model out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (sign in with Google, use an email address or supply a Chinese +86 telephone number) and after that pick the "DeepThink" option below the prompt input box.
  
  DeepSeek use 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 setup file:
  
  Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This won't reveal you the thinking tokens, regretfully. Those are dished out by the API (example here) but LLM doesn't yet have a method to display them.