That design was trained in part using their unreleased R1 "thinking" design. Today they've launched R1 itself, together with an entire household of new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters obstacles such as endless repetition, bad readability, and language mixing." ... so they likewise launched:

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

I do not have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can quickly have fun with myself. That's where the new distilled models are available in.

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

This is a fascinating flex! They have actually 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 designs have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache certified so maybe MIT is OK?

(I also just discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they might require 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 variations are currently beginning to appear. So far I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually 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 utilizing Ollama itself:

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

Once the design has actually been fetched, LLM can speak with it as well. I prefer using LLM for experiments since it logs whatever to SQLite for later exploration.

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 action. For "a joke about a pelican and a walrus who run a tea room together" that started like this:

Okay, wiki-tb-service.com so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an intriguing combination. Let me think about how these 2 characters may communicate in a funny situation.

First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, setiathome.berkeley.edu often seen near the beach or water. Walruses have big teeth, thick fur, and they're usually found in cooler environments, like icebergs or snowy areas. So, combining these 2 into a tea room setting is already an amusing image.

[...]

It then believed for 20 paragraphs before outputting the joke! Here's the complete 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 huge size, 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 help, utilizes its beak to put dishes on the table, causing a few spills.

After a series of comical mishaps, the walrus looks up and states with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "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 cause comedic mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it funny while fitting the style.

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

This was a fairly small 8B design. I'm looking forward to 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 model that I've run 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 attempted my timeless Generate an SVG of a pelican riding a bike timely 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 wound up covering the remainder of the image

It believed some more and provided me this:

As with the earlier joke, the chain of thought in the records was far more interesting than completion result.

Other ways to attempt DeepSeek-R1

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

DeepSeek offer the design by means of their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:

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

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