Simon Willison's Weblog

That design was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, in addition to a whole household of brand-new models obtained from that base.

There's an entire 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 the majority of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as endless repetition, poor readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance similar to OpenAI-o1 across math, code, and reasoning jobs". That a person is also MIT certified, christianpedia.com and is a comparable size.

I don't have the capability to run designs 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 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 a fascinating 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache licensed so maybe MIT is OK?

Licensing aside, these distilled models are fascinating beasts.

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

Quantized versions are already beginning 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 combination of Ollama, pipewiki.org LLM and the llm-ollama plugin.

First I brought and ran the design using Ollama itself:

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

Once the design has been fetched, LLM can talk with it as well. I choose utilizing LLM for experiments due to the fact that it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

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

Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an intriguing mix. Let me think about how these two characters might engage in a funny situation.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in cooler environments, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is currently a funny image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the full records and users.atw.hu 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 big size, has a hard time to find comfy chairs, so it sits on the table by accident, overturning 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 comical mishaps, the walrus searches for and trademarketclassifieds.com says with a smile, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes result in comedic mayhem.
- Punchline: "This isn't so fishy any longer" 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 horrible. But the procedure of arriving was such an intriguing insight into how these brand-new designs work.

This was a fairly little 8B model. I'm anticipating trying 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 favourite GPT-4 class design that I've worked 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 traditional Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing effectively:

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

the background wound up covering the remainder of the image

It believed some more and gave me this:

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

Other methods to attempt DeepSeek-R1

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

DeepSeek use the design through their API, utilizing 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 secret, then use llm -m deepseek-reasoner 'timely' to run prompts.

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