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

There's a great deal of things in the new release.

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters difficulties such as endless repeating, bad readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is also MIT licensed, and is a similar size.

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

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

This is a remarkable flex! They have models 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 works with the underlying Llama license. Qwen designs are Apache accredited so possibly MIT is OK?

(I also just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a 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 currently 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 actually fun to play with.

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

First I fetched and ran the model using Ollama itself:

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

Once the model has been fetched, LLM can speak to it too. I prefer utilizing LLM for experiments due to the fact that it logs everything 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 used to assist generate the reaction. For "a joke about a pelican and a walrus who run a tea room together" that started like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating combination. Let me think about how these two characters might engage in an amusing scenario.

First, securityholes.science let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally discovered in colder environments, like icebergs or snowy locations. So, combining these two into a tea space setting is already 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 wiki.vst.hs-furtwangen.de a walrus choose to open a quaint little tea room together. The walrus, with its big size, wiki.snooze-hotelsoftware.de has a hard time to discover comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to put saucers on the table, triggering a few spills.

After a series of funny incidents, the walrus looks up and lespoetesbizarres.free.fr states with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however 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 turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less absurd. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and wiki.vifm.info tea, making it amusing while fitting the style.

So yeah, the joke is horrible. But the procedure of getting there was such an intriguing insight into how these brand-new models work.

This was a fairly small 8B design. I'm 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 favourite GPT-4 class design 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 timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing really 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 raovatonline.org gave me this:

As with the earlier joke, the chain of believed in the transcript was far more fascinating than the end 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 (check in with Google, utilize an email address or provide a Chinese +86 phone number) and then pick the "DeepThink" option listed below the timely input box.

DeepSeek offer the design through their API, using an OpenAI-imitating endpoint. You can access that by means of 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 utilize llm -m deepseek-reasoner 'prompt' to run triggers.

This will not show you the thinking tokens, unfortunately. Those are provided by the API (example here) however LLM doesn't yet have a method to show them.