That model was trained in part using their unreleased R1 "reasoning" model. Today they've launched R1 itself, together with an entire household of new models obtained from that base.

There's a whole lot of things in the brand-new release.

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most 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 launched:

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

I don't have the capability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly have fun with myself. That's where the brand-new distilled models are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based upon Llama and galgbtqhistoryproject.org Qwen.

This is an interesting 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 connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?

(I also simply observed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a little 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 currently starting to reveal up. So far I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to have fun with.

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

First I brought and ran the design utilizing Ollama itself:

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

Once the design has actually been brought, LLM can speak with it as well. I choose utilizing LLM for experiments because it logs whatever 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 idea utilized to assist produce 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 believe about how these 2 characters may interact in a funny circumstance.

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 big teeth, thick fur, and they're usually discovered in cooler climates, like icebergs or snowy areas. So, integrating 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 transcript 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 huge size, struggles to discover comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, causing a few spills.

After a series of humorous mishaps, forum.batman.gainedge.org the walrus searches for asteroidsathome.net and states with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comedic 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 connects into both marine life ("fish") and tea, making it funny while fitting the style.

So yeah, the joke is horrible. But the process of arriving was such a fascinating insight into how these brand-new models work.

This was a fairly small 8B design. I'm looking forward to trying the Llama 70B variation, oke.zone 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 model 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 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 elements wrong, so I followed up with:

the background wound up covering the remainder of the image

It thought some more and offered me this:

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

Other methods to try DeepSeek-R1

If you wish to attempt the design out without setting up anything at all you can do so utilizing 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 then pick the "DeepThink" choice below the timely input box.

DeepSeek use the model through 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 keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run triggers.

This will not reveal you the thinking tokens, sadly. Those are dished out by the API (example here) but LLM does not yet have a way to show them.