Simon Willison's Weblog

That model was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, niaskywalk.com in addition to an entire family of new designs obtained from that base.

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

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

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That a person is likewise MIT licensed, and is a similar size.

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

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

This is an interesting flex! They have actually designs based upon 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 connected, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache accredited so maybe MIT is OK?

Licensing aside, these distilled designs are fascinating beasts.

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

Quantized versions are currently starting to appear. Up until now I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to play with.

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

First I fetched and ran the model using Ollama itself:

This downloads around 8.5 GB of model data and wavedream.wiki begins an interactive chat interface.

Once the model has been brought, LLM can talk with it too. I choose utilizing LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I installed the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to help produce the reaction. For "a joke about a pelican and a walrus who run a tea room together" that started like this:

Okay, oke.zone so I need 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 2 characters might communicate in a funny circumstance.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and wavedream.wiki they're usually discovered in colder climates, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is already a funny image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the complete transcript and here's the output at the end, king-wifi.win after the tag:

The Joke:

A pelican and a walrus choose to open a quaint little tea space together. The walrus, with its huge size, has a hard time to find comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, uses its beak to position saucers on the table, triggering 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 says, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comical turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being 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 theme.

So yeah, the joke is awful. But the process of arriving was such an interesting insight into how these new designs work.

This was a fairly little 8B model. I'm anticipating attempting out 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 favourite GPT-4 class design 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 classic 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 thought some more and wavedream.wiki gave me this:

As with the earlier joke, the chain of thought in the transcript was far more intriguing than the end outcome.

Other ways to attempt DeepSeek-R1

If you wish to attempt the model out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll need to produce an account (sign in with Google, use an email address or provide a Chinese +86 contact number) and after that pick the "DeepThink" alternative listed below the timely input box.