That model was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, together with an entire family of brand-new designs obtained from that base.

There's a lot of stuff in the new release.

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across obstacles such as unlimited repeating, poor readability, and language blending." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and reasoning tasks". That a person is also MIT certified, 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), morphomics.science so neither of these two models are something I can easily have fun with myself. That's where the new distilled designs are available in.

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

This is a remarkable flex! They have designs based upon Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and surgiteams.com 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 models are Apache certified so perhaps MIT is OK?

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

Licensing aside, these distilled designs are interesting monsters.

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

Quantized variations are already starting to reveal up. So far I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly enjoyable to have fun with.

I'm running it utilizing the combination 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 garagesale.es begins an interactive chat user interface.

Once the design has actually been brought, LLM can speak to it also. I prefer utilizing LLM for experiments since it logs whatever to SQLite for later exploration.

I installed the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of idea used to help produce the action. 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 interesting mix. Let me consider how these two characters may engage in an amusing situation.

First, let's consider their characteristics. Pelicans are known for loft.awardspace.info their long beaks and users.atw.hu Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally discovered in colder environments, like icebergs or snowy areas. So, combining these two into a tea room setting is already an amusing image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the full records 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 big size, has a hard time to find comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position saucers on the table, causing a couple of spills.

After a series of comical mishaps, utahsyardsale.com the walrus looks up and says with a grin, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes cause comedic turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less absurd. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.

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

This was a fairly small 8B model. I'm eagerly anticipating experimenting with the Llama 70B version, 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 have actually 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 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 elements wrong, so I followed up with:

the background ended up covering the remainder of the image

It believed some more and provided me this:

Just like the earlier joke, the chain of thought in the transcript was far more intriguing than the end outcome.

Other methods to try DeepSeek-R1

If you desire to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to produce an account (check in with Google, use an email address or offer a Chinese +86 contact number) and after that select 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 via LLM by dropping this into your extra-openai-models. yaml setup file:

Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.

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