Simon Willison's Weblog

That design was trained in part using their unreleased R1 "reasoning" design. Today they've launched R1 itself, together with a whole household of brand-new models obtained from that base.

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

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as limitless repetition, bad readability, and language mixing." ... so they also released:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across math, code, and reasoning tasks". That a person is likewise MIT certified, and is a similar size.

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

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

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

Licensing aside, these distilled designs are remarkable beasts.

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

Quantized versions are currently starting to appear. Up until now I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and annunciogratis.net it's truly fun to play with.

I'm running it utilizing the mix of Ollama, 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 too. I prefer using LLM for experiments since it logs whatever to SQLite for later expedition.

I installed the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to assist create the action. For "a joke about a pelican and a walrus who run a tea space together" that began like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an intriguing combination. Let me believe about how these two characters may communicate in an amusing situation.

First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and bytes-the-dust.com they're typically discovered in chillier climates, like icebergs or snowy areas. So, integrating these two into a tea space setting is already an amusing 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 decide to open a quaint little tea space together. The walrus, with its huge size, struggles to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to position saucers on the table, a couple of spills.

After a series of comical incidents, the walrus looks up and states with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes result in comedic mayhem. - Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less ridiculous. The follow-up joke presents "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 awful. But the process of arriving was such an intriguing insight into how these brand-new designs work.

This was a fairly little 8B model. I'm looking forward to 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've operated 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 classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing effectively:

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:

Just like the earlier joke, the chain of believed in the records was much more interesting than completion outcome.

Other methods to try DeepSeek-R1

If you desire to attempt the model out without installing anything at all you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or macphersonwiki.mywikis.wiki offer a Chinese +86 contact number) and then choose the "DeepThink" option listed below the prompt input box.

DeepSeek offer 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 utilize llm -m deepseek-reasoner 'timely' to run prompts.

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