That model was trained in part using their unreleased R1 "reasoning" model. Today they have actually released R1 itself, in addition to an entire household of brand-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 the majority of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters difficulties such as endless repetition, poor readability, and language mixing." ... so they also launched:

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

I do not have the capability to run designs larger 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 brand-new distilled designs are available in.

To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, utahsyardsale.com and six dense models distilled from DeepSeek-R1 based upon 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?

(I also just discovered the MIT license files state "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 remarkable beasts.

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

Quantized versions are already beginning to appear. So far I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really 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 design using Ollama itself:

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

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

I set up the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of idea used to help generate the response. 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 walrus running a tea room together. Hmm, that's an interesting mix. Let me think of how these two characters may communicate in a humorous circumstance.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, wolvesbaneuo.com often seen near the beach or water. Walruses have huge teeth, thick fur, and they're normally found in cooler environments, like icebergs or snowy locations. So, integrating these two into a tea space setting is currently a funny image.

[...]

It then thought for macphersonwiki.mywikis.wiki 20 paragraphs before outputting the joke! Here's the full transcript and here's the output at the end, kenpoguy.com after the tag:

The Joke:

A pelican and a walrus decide to open a quaint little tea space together. The walrus, with its big size, struggles to find comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to position dishes on the table, causing a couple of spills.

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

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes result in comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less ridiculous. 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 theme.

So yeah, asteroidsathome.net the joke is dreadful. But the process of getting there was such an interesting insight into how these new models work.

This was a fairly little 8B model. I'm anticipating trying the Llama 70B variation, 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 design that I have actually 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 design working like this-a 34GB download:

Can it draw a pelican?

I tried my traditional 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 wrong, so I followed up with:

the background ended up covering the remainder of the image

It believed some more and gave me this:

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

Other methods to attempt DeepSeek-R1

If you wish 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 (indication in with Google, use an email address or provide a Chinese +86 phone number) and classifieds.ocala-news.com after that pick the "DeepThink" alternative listed below the timely input box.

DeepSeek use the design via their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:

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

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 display them.