Simon Willison's Weblog

That design was trained in part using their unreleased R1 "reasoning" design. Today they have actually launched R1 itself, along with an entire family of brand-new designs obtained from that base.

There's an entire lot of things 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 warn that "DeepSeek-R1-Zero encounters challenges such as unlimited repetition, bad readability, and language mixing." ... so they likewise launched:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance similar to OpenAI-o1 across math, code, and thinking tasks". That a person is likewise MIT licensed, and is a similar 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 two designs are something I can easily play with myself. That's where the new distilled models are available in.

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

This is an interesting flex! They have designs based on Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and wiki.dulovic.tech Llama 3 (Llama-3.1 8B and Llama 3.3 70B Instruct).

Weirdly those Llama models have an MIT license attached, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?

Licensing aside, these distilled designs are remarkable beasts.

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

Quantized variations are already beginning to appear. So far I've tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to play with.

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

First I brought and ran the design utilizing Ollama itself:

This downloads around 8.5 GB of design data and starts an interactive chat interface.

Once the design has actually been brought, LLM can speak to it also. I prefer using LLM for experiments due to the fact that it logs everything 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 thought utilized to help generate the response. For "a joke about a pelican and a walrus who run a tea space 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 an intriguing combination. Let me think of how these 2 characters may engage in a humorous scenario.

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

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the full transcript and raovatonline.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 room together. The walrus, with its huge size, has a hard time to find comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, forum.batman.gainedge.org the pelican, trying to help, uses its beak to put saucers on the table, triggering a couple of spills.

After a series of comical mishaps, the walrus searches for and states with a grin, "This isn't so fishy any longer." 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 result in comical mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming 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 horrible. But the process of getting there was such an interesting insight into how these new designs work.

This was a fairly small 8B model. I'm anticipating trying out 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 preferred GPT-4 class design that I've run 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 timeless Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing really well:

It aimed to me like it got the order of the components wrong, drapia.org so I followed up with:

the background ended up covering the remainder of the image

It thought some more and provided me this:

Similar to the earlier joke, the chain of thought in the records was much more interesting than completion outcome.

Other methods 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 produce an account (check in with Google, utilize an email address or offer a Chinese +86 telephone number) and then choose the "DeepThink" option below the prompt input box.

DeepSeek use the design 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 keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.

This won't show you the reasoning tokens, unfortunately. Those are dished out by the API (example here) but LLM doesn't yet have a method to show them.