Simon Willison's Weblog

That design was trained in part using their unreleased R1 "reasoning" design. 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 stuff in the brand-new release.

DeepSeek-R1-Zero seems the base design. 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 comes across challenges such as limitless repeating, bad readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance similar to OpenAI-o1 across mathematics, code, and thinking jobs". That one is also MIT accredited, and is a comparable 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 2 models are something I can easily play with myself. That's where the brand-new distilled models are available in.

To support the research neighborhood, classicrock.awardspace.biz we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is an interesting 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 models have an MIT license connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache accredited so perhaps MIT is OK?

Licensing aside, these distilled models are interesting beasts.

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

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

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

First I fetched and ran the design utilizing Ollama itself:

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

Once the model has been fetched, LLM can speak to it too. I choose utilizing LLM for experiments since it logs whatever to SQLite for later expedition.

I set up the plugin and forum.batman.gainedge.org ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of thought utilized to assist produce the response. 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 a fascinating combination. Let me think of how these 2 characters may connect in a funny circumstance.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, it-viking.ch typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally discovered in cooler climates, like icebergs or snowy areas. 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 full records and forum.batman.gainedge.org here's the output at the end, after the tag:

The Joke:

A pelican and a walrus choose to open a quaint little tea space together. The walrus, with its big size, has a hard time to discover comfortable 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, causing a couple of spills.

After a series of funny mishaps, the walrus looks up and oke.zone states with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "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 result in comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming less unreasonable. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the theme.

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

This was a fairly little 8B model. 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 preferred 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 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 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 completion outcome.

Other methods to attempt DeepSeek-R1

If you wish to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to produce an account (sign in with Google, utilize an email address or hb9lc.org provide a Chinese +86 phone number) and then choose the "DeepThink" option below the timely input box.

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

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

This won't show you the reasoning tokens, sadly. Those are dished out by the API (example here) however LLM does not yet have a way to display them.