That design was trained in part using their unreleased R1 "thinking" model. Today they have actually released R1 itself, in addition to an entire family of new models obtained from that base.

There's a lot of things in the 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 tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as unlimited repeating, poor readability, and language mixing." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and thinking jobs". That one is likewise MIT licensed, and is a similar 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 2 models are something I can easily have fun with myself. That's where the new distilled designs are available in.

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

This is a remarkable flex! They have 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 is compatible with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?

(I likewise just discovered 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 remarkable monsters.

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

Quantized variations are already beginning to reveal up. Up until now I have actually tried simply one of 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 using the combination of Ollama, LLM and the llm-ollama plugin.

First I brought and ran the model using Ollama itself:

This downloads around 8.5 GB of model information and begins an interactive chat user interface.

Once the model has been brought, townshipmarket.co.za LLM can speak to it too. I prefer utilizing LLM for experiments because it logs everything to SQLite for later exploration.

I installed the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to assist create the reaction. For "a joke about a pelican and a walrus who run a tea room together" that began like this:

Okay, so I need to come up with a joke about a pelican and a a tea space together. Hmm, that's an intriguing mix. Let me consider how these 2 characters may engage in a funny situation.

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

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full 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 big size, struggles to find comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, uses its beak to position saucers on the table, causing a few spills.

After a series of comical mishaps, the walrus searches for and states with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, however we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes result in comical turmoil.

• Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.
  
  So yeah, the joke is terrible. But the process of arriving was such an intriguing insight into how these brand-new models work.
  
  This was a fairly little 8B model. I'm anticipating checking 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 variation of that Llama 3.3 70B R1 distilled model working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I tried my traditional Generate an SVG of a pelican riding a bicycle prompt 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 provided me this:
  
  Just like the earlier joke, the chain of believed in the records was much more intriguing than the end outcome.
  
  Other methods to attempt DeepSeek-R1
  
  If you desire to attempt the model out without installing anything you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or provide a Chinese +86 phone number) and then pick the "DeepThink" option below the timely input box.
  
  DeepSeek offer the design via their API, utilizing an OpenAI-imitating endpoint. You can access that through 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 'prompt' to run triggers.
  
  This will not reveal you the reasoning tokens, regretfully. Those are served up by the API (example here) but LLM doesn't yet have a way to display them.