Simon Willison's Weblog

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

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

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

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance comparable to OpenAI-o1 across mathematics, code, and reasoning tasks". That a person is also MIT licensed, and is a comparable size.

I do not have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.

To support the research study neighborhood, 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, 32B, Math 1.5 B and archmageriseswiki.com 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 works with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?

Licensing aside, these distilled designs are fascinating beasts.

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

Quantized variations are already starting to appear. Up until now I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really enjoyable to have fun 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 model data and begins an interactive chat interface.

Once the design has been brought, LLM can talk to it also. I prefer using LLM for experiments because it logs everything 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 help generate the action. 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 an interesting combination. Let me consider how these 2 characters may engage in an amusing 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 huge teeth, thick fur, and they're generally discovered in colder climates, like icebergs or snowy locations. So, combining these 2 into a tea space setting is currently a funny 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 room together. The walrus, with its huge size, struggles to find comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to put saucers on the table, triggering a few spills.

After a series of humorous incidents, the walrus looks up and states with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, however we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes result in comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario 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 theme.

So yeah, the joke is dreadful. But the procedure of getting there was such an intriguing insight into how these new models work.

This was a fairly small 8B design. I'm 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 design that I have actually worked 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 tried my classic Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing effectively:

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 thought some more and provided me this:

Just like the earlier joke, the chain of believed in the transcript was even more intriguing than the end result.

Other methods to attempt DeepSeek-R1

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