Simon Willison's Weblog

That design was trained in part using their unreleased R1 "thinking" design. Today they have actually launched R1 itself, in addition to an entire household of new designs obtained from that base.

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

DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as unlimited repetition, bad readability, and language blending." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance comparable to OpenAI-o1 across mathematics, code, and thinking tasks". That one is likewise MIT certified, and is a similar size.

I do not have the ability to run models bigger 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 new distilled models are available in.

To support the research study neighborhood, higgledy-piggledy.xyz we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based on Llama and Qwen.

This is a remarkable 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 certified so perhaps MIT is OK?

Licensing aside, these distilled models are interesting beasts.

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

Quantized variations are currently beginning to appear. So far I've tried just among 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 combination of Ollama, LLM and the llm-ollama plugin.

First I fetched and ran the design utilizing Ollama itself:

This downloads around 8.5 GB of model information and begins an interactive chat interface.

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

I set up the plugin and ran it like this:

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

Okay, so I need to come up with a joke about a pelican and archmageriseswiki.com a walrus running a tea space together. Hmm, that's an interesting combination. Let me think about how these 2 characters might communicate in an amusing scenario.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, wiki.lafabriquedelalogistique.fr thick fur, and smfsimple.com they're generally discovered in colder environments, like icebergs or snowy locations. So, integrating these two into a tea room setting is currently an amusing image.

[...]

It then thought 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 a walrus choose to open a quaint little tea room together. The walrus, with its big size, has a hard time to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place dishes on the table, causing a few 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 says, "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 comedic turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less unreasonable. 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 horrible. But the procedure of getting there was such a fascinating insight into how these brand-new designs work.

This was a fairly small 8B model. I'm eagerly anticipating attempting out 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 preferred GPT-4 class design that I've worked on my own machine-I have high expectations.

Update 21st January 2025: bbarlock.com 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 tried my traditional 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:

As with the earlier joke, the chain of thought in the transcript was even more fascinating than the end result.

Other methods to try DeepSeek-R1

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

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

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