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

There's a lot of stuff in the 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 clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across challenges such as unlimited repeating, poor readability, and language blending." ... so they also released:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance similar to OpenAI-o1 across mathematics, code, and reasoning tasks". That a person is likewise MIT certified, and is a similar size.

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

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

This is a fascinating flex! They have 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 designs have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?

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

Licensing aside, these distilled designs are remarkable beasts.

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

Quantized variations are currently starting to show up. Up until now I've tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.

I'm running it using the combination 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 information and starts an interactive chat interface.

Once the model has actually been brought, LLM can speak with it also. I choose using LLM for experiments because it logs everything to SQLite for later exploration.

I installed the plugin and ran it like this:

Each response starts with a ... pseudo-XML tag containing the chain of idea used to help produce the action. For "a joke about a pelican and a walrus who run a tea room together" that started like this:

Okay, so I require 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 think of how these 2 characters may interact in a humorous scenario.

First, ai-db.science let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, macphersonwiki.mywikis.wiki and they're generally found in chillier climates, like icebergs or snowy areas. So, humanlove.stream combining these 2 into a tea space setting is currently an amusing image.

[...]
It then thought 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 discover comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to place dishes on the table, a couple of spills.

After a series of funny incidents, the walrus looks up and says with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, but 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 comedic chaos.

• Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less ridiculous. The follow-up joke introduces "krill," a play on words that connects 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 designs work.
  
  This was a fairly small 8B model. I'm eagerly anticipating trying the Llama 70B variation, wiki.snooze-hotelsoftware.de 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 run on my own machine-I have high expectations.
  
  Update 21st January 2025: koha-community.cz 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 bike prompt 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 ended up covering the remainder of the image
  
  It thought some more and gave me this:
  
  Just like the earlier joke, the chain of thought in the transcript was even more intriguing than completion result.
  
  Other ways to attempt DeepSeek-R1
  
  If you desire to try the design out without installing anything at all you can do so using chat.deepseek.com-you'll require to create an account (sign in with Google, use an email address or provide a Chinese +86 contact number) and then choose the "DeepThink" option listed below the prompt input box.
  
  DeepSeek provide the model by means of 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, bphomesteading.com then utilize llm -m deepseek-reasoner 'timely' to run prompts.
  
  This will not show you the thinking tokens, unfortunately. Those are served up by the API (example here) however LLM does not yet have a way to display them.