Simon Willison’s Weblog

That model was trained in part utilizing their unreleased R1 „thinking“ design. Today they have actually launched R1 itself, in addition to a whole household of brand-new models 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 many of their other releases, is under a clean MIT license. DeepSeek caution that „DeepSeek-R1-Zero encounters obstacles such as limitless repetition, poor readability, and language blending.“ … so they likewise launched:

DeepSeek-R1-which „includes cold-start information before RL“ and „attains performance similar to OpenAI-o1 across mathematics, code, and reasoning tasks“. That one is likewise MIT licensed, and wolvesbaneuo.com is a similar size.

I don’t have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can 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 actually models 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 designs have an MIT license connected, which I’m uncertain is compatible with the underlying Llama license. Qwen designs are Apache accredited 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 remarkable beasts.

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

Quantized versions are already starting to appear. Up until now I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it’s actually enjoyable to have fun with.

I’m running it using the combination of Ollama, 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 begins an interactive chat interface.

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

I set up the plugin and ran it like this:

Each action begins with a … pseudo-XML tag containing the chain of idea utilized to help create the reaction. For „a joke about a pelican and a walrus who run a tea space together“ that began like this:

Okay, so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that’s an intriguing combination. Let me think of how these 2 characters might connect in a funny circumstance.

First, let’s consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they’re typically found in colder climates, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is already an amusing image.

[…]

It then believed for 20 paragraphs before outputting the joke! Here’s the complete 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, has a hard time to find comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to position dishes on the table, triggering a few spills.

After a series of comical mishaps, the walrus looks up and states with a smile, „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 situation ending up being less ridiculous. The follow-up joke introduces „krill,“ a play on words that connects into both marine life („fish“) and tea, making it humorous while fitting the style.

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

This was a fairly little 8B design. I’m eagerly anticipating checking 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 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 traditional Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing extremely well:

It aimed to me like it got the order of the aspects wrong, 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 transcript was even more intriguing than the end outcome.

Other ways to try DeepSeek-R1

If you wish to try the model out without installing anything you can do so using chat.deepseek.com-you’ll require to create an account (check in with Google, utilize an email address or supply a Chinese +86 telephone number) and after that select the „DeepThink“ option listed below the timely input box.

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

Then run llm secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner ‘timely’ to run prompts.

This will not reveal you the reasoning tokens, unfortunately. Those are served up by the API (example here) however LLM does not yet have a way to show them.