That model was trained in part using their unreleased R1 "thinking" design. Today they have actually launched R1 itself, in addition to a whole family of brand-new models obtained from that base.

There's a whole lot of things in the brand-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 encounters difficulties such as unlimited repeating, bad readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 across math, code, and reasoning jobs". That one is also MIT certified, and 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 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 community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based upon 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 connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?

(I also simply noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may require to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled models are remarkable monsters.

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

Quantized versions are currently beginning to appear. So far I have actually attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to play with.

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

First I fetched and ran the model using Ollama itself:

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

Once the design has been brought, LLM can speak with it as well. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of idea used to help generate the reaction. 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 room together. Hmm, that's an interesting mix. Let me consider how these two characters might engage in a humorous situation.

First, wiki.whenparked.com let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, elearnportal.science thick fur, and they're usually discovered in cooler environments, like icebergs or snowy areas. 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 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, struggles to find comfortable chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, wiki.myamens.com trying to assist, uses its beak to put saucers on the table, causing a few spills.

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

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes result in comedic chaos.

• Punchline: "This isn't so fishy anymore" is a pun on the circumstance 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 amusing while fitting the theme.
  
  So yeah, the joke is dreadful. But the procedure of arriving was such an interesting insight into how these new models work.
  
  This was a fairly small 8B design. I'm anticipating checking out 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 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 attempted my 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 elements wrong, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It thought some more and offered me this:
  
  As with the earlier joke, the chain of believed in the records was even more intriguing than the end result.
  
  Other ways to attempt DeepSeek-R1
  
  If you want to attempt the model out without installing anything at all you can do so using chat.deepseek.com-you'll require to develop an account (indication in with Google, utilize an email address or setiathome.berkeley.edu offer a Chinese +86 telephone number) and then select the "DeepThink" choice below the prompt input box.
  
  DeepSeek offer the model through their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not reveal you the thinking tokens, unfortunately. Those are served up by the API (example here) but LLM does not yet have a way to display them.