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

There's a 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 warn that "DeepSeek-R1-Zero comes across difficulties such as limitless repetition, 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 throughout math, code, and thinking jobs". That one is likewise MIT certified, and is a comparable size.

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

To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick 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 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 suitable with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?

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

Licensing aside, these distilled models are remarkable beasts.

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

Quantized variations are already starting to show up. Up until now I've attempted just one of 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 fetched and ran the design using Ollama itself:

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

Once the design has been brought, LLM can speak with it as well. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for later exploration.

I installed the plugin and gratisafhalen.be ran it like this:

Each reaction starts 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 room together" that began like this:

Okay, so I require to come up with a joke about a pelican and wiki.myamens.com a walrus running a tea space together. Hmm, that's an intriguing mix. Let me believe about how these two characters may engage in a humorous circumstance.

First, larsaluarna.se let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're typically discovered in colder environments, like icebergs or snowy areas. So, combining these 2 into a tea space setting is currently a funny image.

[...]

It then believed 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 archmageriseswiki.com a walrus choose to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to position saucers on the table, causing a few spills.

After a series of comical mishaps, asteroidsathome.net the walrus searches for and says with a grin, "This isn't so fishy anymore." 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 an unlikely tea space. Their sizes lead to comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and bphomesteading.com tea, making it humorous while fitting the theme.

So yeah, the joke is awful. But the process of getting there was such a fascinating insight into how these new models work.

This was a fairly little 8B model. I'm eagerly anticipating trying out 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'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 tried my timeless 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 aspects wrong, so I followed up with:

the background wound up covering the remainder of the image

It thought some more and offered me this:

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

Other ways to try DeepSeek-R1

If you wish to try the model out without setting up anything at all you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or supply a Chinese +86 telephone number) and after that select the "DeepThink" alternative listed below the timely input box.

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

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

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