Simon Willison's Weblog

That design was trained in part utilizing their unreleased R1 "thinking" model. Today they have actually launched R1 itself, together with a whole household of brand-new models obtained from that base.

There's a lot of things 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 caution that "DeepSeek-R1-Zero comes across challenges such as limitless repetition, poor readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT certified, and is a comparable size.

I do not 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 brand-new distilled models are available in.

To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is a fascinating flex! They have models 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 is suitable with the underlying Llama license. Qwen designs are Apache accredited so possibly MIT is OK?

Licensing aside, these distilled models are remarkable beasts.

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

Quantized variations are currently starting to reveal up. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly enjoyable to play with.

I'm running it using the mix 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 user interface.

Once the design has been fetched, LLM can talk with it too. I choose using LLM for experiments because it logs whatever to SQLite for later exploration.

I set up the plugin and ran it like this:

Each response starts with a ... pseudo-XML tag containing the chain of idea utilized to help produce the response. 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 room together. Hmm, that's a fascinating mix. Let me consider how these two characters may connect in a humorous situation.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're usually discovered in colder climates, like icebergs or yewiki.org snowy areas. So, combining these two into a tea space setting is currently 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 big size, struggles to find comfy chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place saucers on the table, causing a few spills.

After a series of humorous mishaps, the walrus searches for and says with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes cause comical mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less unreasonable. The follow-up joke introduces "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 an intriguing insight into how these new models work.

This was a fairly small 8B design. I'm anticipating 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 model that I've operated 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 design 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 really well:

It aimed to me like it got the order of the components incorrect, so I followed up with:

the background ended up covering the remainder of the image

It believed some more and gave me this:

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

Other methods to try DeepSeek-R1

If you want to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or offer a Chinese +86 telephone number) and after that choose the "DeepThink" option listed below the timely input box.

DeepSeek use the model via their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:

Then run llm secrets set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run prompts.

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