Simon Willison’s Weblog

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

There’s a great deal of stuff in the brand-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 difficulties such as unlimited repeating, bad readability, and language mixing.” … so they likewise launched:

DeepSeek-R1-which “includes cold-start information before RL” and “attains efficiency comparable to OpenAI-o1 across mathematics, code, and reasoning jobs”. That one is likewise MIT certified, and is a similar size.

I do not have the capability to run designs larger 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 new distilled models are available in.

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

This is a fascinating 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 designs have an MIT license connected, which I’m uncertain works with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?

(I also simply discovered the MIT license files state “Copyright (c) 2023 DeepSeek” so they may need 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 currently starting to reveal up. So far I’ve tried just 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 combination of Ollama, LLM and the llm-ollama plugin.

First I fetched and ran the model utilizing Ollama itself:

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

Once the model has actually been fetched, LLM can speak to it too. I prefer utilizing LLM for experiments because it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each response begins with a … pseudo-XML tag containing the chain of thought used to assist produce the reaction. For “a joke about a pelican and a walrus who run a tea room together” that started like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, hb9lc.org that’s a fascinating combination. Let me think of how these two characters might interact in a humorous 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, thick fur, and they’re generally discovered in chillier climates, like icebergs or snowy locations. So, combining these two into a tea space setting is already a funny image.

[…]

It then thought for 20 paragraphs before outputting the joke! Here’s the complete records 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 big size, struggles to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, photorum.eclat-mauve.fr trying to help, uses its beak to put saucers on the table, causing a couple of spills.

After a series of humorous mishaps, the walrus searches for and states with a grin, “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 lead to comedic turmoil.
– Punchline: “This isn’t so fishy anymore” is a pun on the circumstance ending up being 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 theme.

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

This was a fairly small 8B model. I’m anticipating experimenting with 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 bike 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 believed some more and offered me this:

Just like the earlier joke, the chain of believed in the transcript was far more fascinating than the end outcome.

Other methods to try DeepSeek-R1

If you desire to try the model out without setting up anything you can do so using chat.deepseek.com-you’ll require to create an account ( in with Google, use an email address or supply a Chinese +86 phone number) and after that choose the “DeepThink” option below the prompt input box.

DeepSeek use the design by means of their API, using an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml configuration file:

Then run llm keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner ‘prompt’ to run prompts.

This won’t show you the reasoning tokens, regretfully. Those are dished out by the API (example here) however LLM doesn’t yet have a method to display them.