That design was trained in part using their unreleased R1 "thinking" model. Today they have actually launched R1 itself, together with a whole household of new models obtained from that base.

There's a whole lot of things in the 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 clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters challenges such as limitless repetition, poor readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains efficiency equivalent to OpenAI-o1 throughout math, code, and reasoning tasks". That one is likewise MIT certified, and is a similar size.

I don't have the ability 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 have fun 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 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is a fascinating flex! They have designs based upon Qwen 2.5 (14B, 32B, pipewiki.org 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 works with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?

(I likewise simply discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they may require to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled models are fascinating beasts.

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

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

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

First I fetched and ran the model using Ollama itself:

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

Once the model has been fetched, LLM can talk to it too. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

Each response begins with a ... pseudo-XML tag containing the chain of idea utilized to help generate the response. For "a joke about a pelican and a walrus who run a tea room together" that started 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 interesting combination. Let me think of how these 2 characters might communicate in an amusing scenario.

First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're generally discovered in cooler environments, like icebergs or snowy locations. So, combining these 2 into a tea space 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 comfy chairs, so it sits on the table by mishap, videochatforum.ro overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes 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 anymore." The pelican smirks and remarks, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and linked.aub.edu.lb Walrus run an unlikely tea space. Their sizes cause comedic mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less ridiculous. The follow-up joke presents "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 horrible. But the procedure of getting there was such a fascinating insight into how these brand-new designs work.

This was a fairly small 8B design. I'm eagerly anticipating checking out 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 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 attempted my classic 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 wrong, so I followed up with:

the background ended up covering the remainder of the image

It thought some more and provided me this:

Just like the earlier joke, the chain of believed in the records was much more interesting than the end outcome.

Other methods to try DeepSeek-R1

If you want to try the design out without setting up anything at all you can do so using chat.deepseek.com-you'll require to produce an account (check in with Google, utilize an email address or provide a Chinese +86 telephone number) and then pick the "DeepThink" alternative listed below the prompt input box.

DeepSeek use the design via their API, using 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 key, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.

This won't reveal you the thinking tokens, sadly. Those are served up by the API (example here) but LLM doesn't yet have a method to show them.