That design was trained in part utilizing their unreleased R1 "thinking" design. Today they've released R1 itself, together with a whole family of brand-new models obtained from that base.

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

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across obstacles such as limitless repetition, poor readability, and language blending." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and thinking tasks". That one is also 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 two designs are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.

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

This is an interesting flex! They have actually models based upon Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and Llama 3 (Llama-3.1 8B and oke.zone Llama 3.3 70B Instruct).

Weirdly those Llama designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?

(I also simply noticed 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 models are remarkable monsters.

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

Quantized variations are already beginning to appear. Up until now I have actually attempted just 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 using the mix of Ollama, LLM and the llm-ollama plugin.

First I brought and ran the model utilizing Ollama itself:

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

Once the model has been fetched, LLM can talk to it also. I prefer using LLM for experiments because it logs whatever to SQLite for later exploration.

I set up the plugin and ran it like this:

Each action starts with a ... pseudo-XML tag containing the chain of idea used to help produce the reaction. For "a joke about a pelican and a walrus who run a tea room together" that began like this:

Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating mix. Let me believe about how these 2 characters may interact in a funny situation.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're normally discovered in cooler climates, like icebergs or snowy locations. So, combining these 2 into a tea room 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 a walrus choose to open a quaint little tea space together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place dishes on the table, causing a couple of spills.

After a series of comical incidents, the walrus looks up and states with a grin, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, however 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 mayhem.
- 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 ties into both marine life ("fish") and tea, making it humorous while fitting the theme.

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

This was a fairly little 8B model. I'm looking forward to trying the Llama 70B variation, which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class model that I have actually operated 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 effectively:

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

the background ended up covering the remainder of the image

It believed some more and offered me this:

Similar to the earlier joke, the chain of believed in the transcript was much more intriguing than the end outcome.

Other methods to attempt DeepSeek-R1

If you want to try the design out without installing anything you can do so utilizing chat.deepseek.com-you'll require to develop an account (indication in with Google, qoocle.com use an email address or chessdatabase.science offer a Chinese +86 contact number) and then pick the "DeepThink" option below the prompt input box.

DeepSeek use the design through their API, utilizing 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 keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.

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