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

There's a lot of things in the brand-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 clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters obstacles such as endless repetition, bad readability, and language blending." ... so they also launched:

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

I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs 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 thick models distilled from DeepSeek-R1 based upon Llama and wiki.vst.hs-furtwangen.de Qwen.

This is an interesting flex! They have actually designs 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 connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so possibly MIT is OK?

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

Licensing aside, these distilled designs are remarkable monsters.

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

Quantized versions are currently starting to reveal up. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to have fun with.

I'm running it using the combination 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 model data and begins an interactive chat interface.

Once the design has actually been brought, LLM can speak with it also. I prefer using LLM for experiments since it logs whatever to SQLite for later expedition.

I installed the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of idea utilized to help 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 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 about how these two characters may engage in a funny situation.

First, 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, and they're found in cooler environments, like icebergs or snowy locations. So, combining these two into a tea space 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 decide to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to put dishes on the table, triggering a couple of spills.

After a series of comical accidents, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

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

• 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 humorous while fitting the style.
  
  So yeah, the joke is horrible. But the process of getting there was such a fascinating insight into how these brand-new designs work.
  
  This was a fairly little 8B model. I'm eagerly anticipating experimenting with the Llama 70B variation, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design that I have actually operated on my own machine-I have high expectations.
  
  Update 21st January 2025: wiki.snooze-hotelsoftware.de 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 classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing effectively:
  
  It aimed to me like it got the order of the components incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and provided me this:
  
  As with the earlier joke, wiki.insidertoday.org the chain of thought in the records was even more fascinating than the end result.
  
  Other methods to try DeepSeek-R1
  
  If you want to try the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to produce an account (indication in with Google, utilize an email address or supply a Chinese +86 telephone number) and after that select the "DeepThink" alternative listed below the timely input box.
  
  DeepSeek offer 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 secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
  
  This won't show you the reasoning tokens, regretfully. Those are provided by the API (example here) but LLM does not yet have a way to show them.