That model was trained in part using their unreleased R1 "thinking" model. Today they have actually launched R1 itself, in addition to an entire family of new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like the majority of their other releases, archmageriseswiki.com is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across obstacles such as endless repetition, bad readability, and language blending." ... so they also released:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across mathematics, code, and thinking tasks". That one is likewise MIT licensed, and is a similar size.

I do not have the capability to run models larger 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 brand-new distilled models are available in.

To support the research study community, code.snapstream.com we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is a remarkable flex! They have designs 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 designs have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?

(I likewise just discovered the MIT license files say "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 remarkable beasts.

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

Quantized versions are currently starting to show up. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to have fun with.

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

First I brought and ran the design using Ollama itself:

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

Once the design has been fetched, LLM can talk with it too. I choose 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 action begins with a ... pseudo-XML tag containing the chain of thought utilized to assist produce the action. 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 akropolistravel.com a walrus running a tea room together. Hmm, that's a fascinating combination. Let me think about how these 2 characters may engage in an amusing scenario.

First, let's consider their attributes. 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 typically discovered in colder environments, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is currently an amusing image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the complete transcript and here's the output at the end, oke.zone after the tag:

The Joke:

A pelican and a walrus decide to open a quaint little tea space together. The walrus, with its huge size, has a hard time to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to position dishes on the table, causing a few spills.

After a series of funny accidents, the walrus looks up 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 a not likely tea space. Their sizes result in comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the style.

So yeah, the joke is horrible. But the process of arriving was such an intriguing insight into how these brand-new designs work.

This was a fairly small 8B model. I'm looking forward to checking out the Llama 70B variation, utahsyardsale.com 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 design that I have actually 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 tried my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing very well:

It aimed to me like it got the order of the elements wrong, so I followed up with:

the background wound up covering the remainder of the image

It believed some more and gave me this:

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

Other methods to try DeepSeek-R1

If you wish to try the design out without installing anything at all you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, utilize an email address or supply a Chinese +86 telephone number) and then choose the "DeepThink" choice below the prompt input box.

DeepSeek use the design via their API, utilizing an OpenAI-imitating endpoint. You can access that through 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 won't reveal you the thinking tokens, sadly. Those are served up by the API (example here) however LLM does not yet have a way to show them.