That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, in addition to an entire household of 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 most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters obstacles such as endless repeating, poor readability, and language blending." ... so they also released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across math, code, and thinking tasks". That one is also MIT accredited, and is a similar size.

I don't have the ability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.

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

This is a fascinating flex! They have models 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 models are Apache accredited so perhaps MIT is OK?

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

Licensing aside, these distilled designs are fascinating monsters.

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

Quantized versions are currently beginning to appear. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to play with.

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

First I brought and ran the model utilizing Ollama itself:

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

Once the model 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 installed the plugin and ran it like this:

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

Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, macphersonwiki.mywikis.wiki that's a fascinating combination. Let me consider how these two characters might communicate in a humorous circumstance.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're usually discovered in chillier climates, like icebergs or snowy locations. So, combining these two into a tea space setting is currently a funny image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full records and garagesale.es 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 big size, struggles to discover comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to place saucers on the table, causing a few 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 mentions, "Maybe not, but we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes cause comedic mayhem.

• Punchline: "This isn't so fishy anymore" is a pun on the situation becoming 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 horrible. But the procedure of getting there was such a fascinating insight into how these brand-new models work.
  
  This was a fairly little 8B model. I'm looking forward to trying the Llama 70B version, 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 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 attempted my classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing very 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 thought some more and offered me this:
  
  Just like the earlier joke, the chain of believed in the transcript was far more fascinating than completion outcome.
  
  Other methods to try DeepSeek-R1
  
  If you wish to attempt the design out without installing anything at all you can do so using chat.deepseek.com-you'll need to develop an account (indication in with Google, use an email address or offer a +86 phone number) and then choose the "DeepThink" option below the prompt input box.
  
  DeepSeek offer the design through their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not show you the reasoning tokens, unfortunately. Those are served up by the API (example here) but LLM does not yet have a method to show them.