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

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

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences difficulties such as endless repeating, poor readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance similar to OpenAI-o1 throughout mathematics, code, and reasoning 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 2 designs are something I can easily have fun with myself. That's where the brand-new distilled models are available in.

To support the research neighborhood, wiki.snooze-hotelsoftware.de we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based on Llama and Qwen.

This is a fascinating flex! They have designs based on Qwen 2.5 (14B, utahsyardsale.com 32B, library.kemu.ac.ke 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 connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so maybe MIT is OK?

(I likewise just observed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require 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 variations are already starting 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 enjoyable to play with.

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

First I brought and ran the model using Ollama itself:

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

Once the design has been fetched, LLM can speak to it also. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for it-viking.ch later exploration.

I installed the plugin and ran it like this:

Each action 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 began 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 combination. Let me consider how these two characters might interact in a funny circumstance.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally found in cooler 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 complete transcript and here's the output at the end, after the tag:

The Joke:

A pelican and wiki.lafabriquedelalogistique.fr a walrus decide to open a quaint little tea room together. The walrus, with its huge size, struggles to find comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to put dishes on the table, triggering a few spills.

After a series of humorous mishaps, the walrus looks up and opensourcebridge.science says with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less ridiculous. The follow-up joke presents "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 terrible. But the procedure of arriving was such a fascinating insight into how these new models work.

This was a fairly small 8B design. I'm eagerly anticipating attempting out the Llama 70B version, 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 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 model working like this-a 34GB download:

Can it draw a pelican?

I attempted my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:

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

the background ended up covering the remainder of the image

It believed some more and gave me this:

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

Other methods to attempt DeepSeek-R1

If you want to attempt the model out without installing anything you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, use an email address or offer a Chinese +86 telephone number) and then choose the "DeepThink" alternative below the prompt input box.

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

Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run prompts.

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