That model was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, along with a whole household of brand-new models obtained from that base.

There's a whole lot of stuff in the brand-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 clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across challenges such as endless repetition, poor readability, and language mixing." ... so they also released:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance comparable to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT accredited, and is a similar size.

I don't have the ability 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 easily play with myself. That's where the new distilled designs are available in.

To support the research neighborhood, photorum.eclat-mauve.fr we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is a fascinating flex! They have models 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 works with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?

(I also simply noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a 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 versions are already beginning to show up. So far I've attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to play with.

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

First I fetched and ran the model utilizing Ollama itself:

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

Once the model has been brought, LLM can speak to it also. I prefer using LLM for experiments because it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of thought used to assist create 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 space together. Hmm, that's an interesting mix. Let me consider how these two characters may engage in an amusing scenario.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or drapia.org water. Walruses have huge teeth, thick fur, and they're normally found in colder environments, like icebergs or snowy areas. So, integrating these two into a tea room setting is already an amusing image.

[...]

It then thought for users.atw.hu 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 big size, struggles to discover comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put dishes on the table, causing a few spills.

After a series of funny accidents, wikitravel.org the walrus searches for and states with a smile, "This isn't so fishy any longer." The pelican smirks and mentions, "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 lead to comical turmoil.
- 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 style.

So yeah, the joke is dreadful. But the process of getting there was such a fascinating insight into how these new designs work.

This was a fairly small 8B model. I'm anticipating trying 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 run on my own machine-I have high expectations.

Update 21st January 2025: I got this quantized version of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:

Can it draw a pelican?

I attempted my traditional Generate an SVG of a pelican riding a bike 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 ended up covering the remainder of the image

It thought some more and offered me this:

As with the earlier joke, the chain of thought in the records was far more intriguing than the end outcome.

Other methods to attempt DeepSeek-R1

If you wish to try the design out without setting up anything at all you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or supply a Chinese +86 contact number) and then select the "DeepThink" option listed below the timely input box.

DeepSeek use the model via their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:

Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run triggers.

This won't show you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a way to display them.