That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they've launched R1 itself, along with an entire family of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters challenges such as unlimited repeating, poor readability, and language mixing." ... so they likewise launched:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance comparable to OpenAI-o1 throughout math, code, and thinking tasks". That one is also MIT licensed, and is a similar size.

I don't have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily play 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 designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is an interesting flex! They have models 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?

(I also just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)

Licensing aside, these distilled models are interesting beasts.

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

Quantized variations are currently starting to show up. Up until now I have actually tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.

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

First I fetched and ran the design using Ollama itself:

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

Once the design has actually been fetched, LLM can speak with it as well. I prefer utilizing LLM for experiments since it logs whatever to SQLite for later exploration.

I installed the plugin and ran it like this:

Each response begins with a ... pseudo-XML tag containing the chain of thought utilized to help produce the action. For "a joke about a pelican and a walrus who run a tea space 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 an intriguing mix. Let me think about how these 2 characters might connect in a humorous situation.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're normally found in chillier climates, like icebergs or snowy areas. So, combining these 2 into a tea room setting is already an amusing image.

[...]

It then thought for 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 decide to open a quaint little tea room together. The walrus, with its big size, has a hard time to discover comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, uses its beak to position dishes on the table, wikitravel.org triggering a few spills.

After a series of comical incidents, the walrus searches for 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 chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being 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 style.

So yeah, the joke is dreadful. But the process of arriving was such an intriguing insight into how these brand-new models work.

This was a fairly small 8B model. I'm eagerly 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 favourite GPT-4 class design that I have actually 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 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:

Similar to the earlier joke, the chain of believed in the transcript was even more fascinating than the end outcome.

Other ways to attempt DeepSeek-R1

If you desire to try the model out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or supply a Chinese +86 contact number) and then choose the "DeepThink" choice listed below the timely input box.

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

Then run llm secrets set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run triggers.

This will not reveal you the thinking tokens, sadly. Those are provided by the API (example here) however LLM doesn't yet have a method to display them.