That design was trained in part using their unreleased R1 "reasoning" design. Today they've released R1 itself, in addition to a whole household of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, morphomics.science like most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters difficulties such as limitless repeating, bad readability, and language mixing." ... so they likewise released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance comparable to OpenAI-o1 across math, code, and thinking jobs". That one is likewise MIT licensed, 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 designs are something I can easily play with myself. That's where the new distilled designs are available in.

To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based upon Llama and lespoetesbizarres.free.fr Qwen.

This is a fascinating flex! They have designs based upon Qwen 2.5 (14B, experienciacortazar.com.ar 32B, Math 1.5 B and Math 7B) and hikvisiondb.webcam 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 is suitable with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?

(I likewise simply discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled designs are fascinating monsters.

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

Quantized versions are currently beginning to reveal up. Up until now I've tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched 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 model data and starts an interactive chat user interface.

Once the design has been fetched, LLM can talk with it as well. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.

I set up the plugin and ran it like this:

Each response begins with a ... pseudo-XML tag containing the chain of thought used to help create the response. For "a joke about a pelican and a walrus who run a tea space together" that began like this:

Okay, yewiki.org so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an intriguing combination. Let me think of how these 2 characters might engage in a funny scenario.

First, let's consider their qualities. 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 typically discovered in chillier environments, like icebergs or snowy areas. So, combining these two into a tea space setting is currently an amusing image.

[...]

It then believed for 20 paragraphs before outputting the joke! Here's the full 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, struggles to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to put saucers on the table, causing a couple of spills.

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

Explanation:

- Setup: Pelican and accc.rcec.sinica.edu.tw Walrus run a not likely tea space. Their sizes result in comedic mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less absurd. The follow-up joke presents "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 awful. But the procedure of arriving was such a fascinating insight into how these brand-new models work.

This was a fairly small 8B design. I'm eagerly 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 model that I've 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 timeless Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing very well:

It aimed to me like it got the order of the components wrong, so I followed up with:

the background ended up covering the remainder of the image

It believed some more and gave me this:

Just like the earlier joke, setiathome.berkeley.edu the chain of believed in the transcript was even more intriguing than completion outcome.

Other methods to attempt DeepSeek-R1

If you wish to try the model out without setting up anything you can do so using chat.deepseek.com-you'll need to produce an account (indication in with Google, use an email address or provide a Chinese +86 telephone number) and then pick the "DeepThink" choice below the timely input box.

DeepSeek provide the design 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 use llm -m deepseek-reasoner 'prompt' to run prompts.

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