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

There's a great deal of things in the new release.

DeepSeek-R1-Zero appears to be 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 difficulties such as unlimited repetition, poor readability, and language blending." ... so they also released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency similar to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That a person is likewise MIT certified, and is a comparable size.

I do not have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly 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 models distilled from DeepSeek-R1 based on Llama and Qwen.

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

(I also just noticed 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 models are fascinating beasts.

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

Quantized versions are already starting to appear. So far I have actually tried just 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 using the mix of Ollama, ratemywifey.com 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 starts an interactive chat interface.

Once the model has been brought, LLM can speak with it as well. I choose using LLM for experiments since 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 thought utilized to help generate the response. 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 intriguing combination. Let me think about how these two characters may engage in a humorous 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 usually found in cooler environments, like icebergs or snowy locations. So, integrating these two into a tea room setting is already an amusing image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the complete transcript 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 space together. The walrus, with its huge size, struggles to find comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place dishes on the table, causing a few spills.

After a series of humorous incidents, the walrus looks up and says with a smile, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

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

• Punchline: "This isn't so fishy any longer" is a pun on the situation becoming less unreasonable. 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 style.
  
  So yeah, the joke is terrible. But the process of getting there was such an intriguing insight into how these new designs work.
  
  This was a fairly little 8B design. I'm anticipating experimenting with 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 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 bicycle timely too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the aspects wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It thought some more and gave me this:
  
  As with the earlier joke, the chain of believed in the records was far more interesting than completion outcome.
  
  Other ways to try DeepSeek-R1
  
  If you wish to attempt the model out without setting up anything you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or provide a Chinese +86 contact number) and after that choose the "DeepThink" option below the prompt input box.
  
  DeepSeek offer the design through 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 keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
  
  This won't reveal you the thinking tokens, regretfully. Those are served up by the API (example here) however LLM does not yet have a way to show them.