Simon Willison's Weblog

That model was trained in part using their unreleased R1 "reasoning" design. Today they have actually launched R1 itself, in addition to a whole family of brand-new models obtained from that base.

There's a whole 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 most of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters obstacles such as endless repeating, bad readability, and language mixing." ... so they likewise released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance similar to OpenAI-o1 across mathematics, code, and thinking tasks". That a person is likewise MIT accredited, and is a similar size.

I don't have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily play with myself. That's where the brand-new distilled models are available in.

To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?

(I likewise just observed 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 monsters.

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

Quantized variations are currently starting to appear. So far I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to have fun with.

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

First I brought and ran the model using Ollama itself:

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

Once the model has been fetched, LLM can speak with it too. I prefer using LLM for experiments because it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

Each response begins with a ... pseudo-XML tag containing the chain of idea used to assist generate 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 space together. Hmm, that's an interesting mix. Let me think of how these 2 characters may interact in a humorous situation.

First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're usually discovered in colder environments, like icebergs or snowy areas. So, combining these two into a tea room setting is already a funny 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 choose to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place saucers on the table, triggering a few spills.

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

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes result in comical chaos. - 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 funny while fitting the theme.

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

This was a fairly little 8B design. I'm looking forward to experimenting with the Llama 70B variation, 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 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 components incorrect, so I followed up with:

the background wound up covering the remainder of the image

It believed some more and offered me this:

As with the earlier joke, the chain of believed in the records was even more fascinating than completion outcome.

Other ways to try DeepSeek-R1

If you want to try the design out without installing anything you can do so using chat.deepseek.com-you'll require to develop an account (sign in with Google, use an email address or offer a Chinese +86 phone number) and then pick the "DeepThink" choice listed below the timely input box.

the design by means of 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 keys set deepseek and paste in your API secret, bybio.co then utilize llm -m deepseek-reasoner 'prompt' to run prompts.

This will not show you the reasoning tokens, unfortunately. Those are dished out by the API (example here) but LLM does not yet have a way to display them.