That design was trained in part using their unreleased R1 "reasoning" design. Today they've released R1 itself, in addition to a whole family of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across difficulties such as unlimited repetition, poor readability, and language blending." ... so they likewise released:

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

I don't have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily have fun with myself. That's where the new distilled models are available in.

To support the research study neighborhood, brotato.wiki.spellsandguns.com we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.

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

(I also simply saw 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 fascinating monsters.

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

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

I'm running it utilizing 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 starts an interactive chat interface.

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

I installed the plugin and ran it like this:

Each response starts with a ... pseudo-XML tag containing the chain of idea utilized to assist create the action. For "a joke about a pelican and a walrus who run a tea space together" that began like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an intriguing combination. Let me consider how these 2 characters might engage in a humorous circumstance.

First, let's consider their qualities. 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 typically found in colder climates, like icebergs or snowy locations. So, combining these two into a tea room setting is currently a funny image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the full transcript 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, struggles to find comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to put dishes on the table, causing a few spills.

After a series of funny accidents, the walrus looks up and states with a grin, "This isn't so fishy any longer." 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 lead to comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the theme.

So yeah, the joke is terrible. 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 eagerly anticipating experimenting with 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 preferred GPT-4 class design that I have actually operated 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 design working like this-a 34GB download:

Can it draw a pelican?

I tried my classic 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 aspects incorrect, so I followed up with:

the background wound up covering the remainder of the image

It believed some more and provided me this:

Similar to the earlier joke, the chain of thought in the transcript was even more interesting than completion result.

Other methods to try DeepSeek-R1

If you want to attempt the model out without setting up anything you can do so using chat.deepseek.com-you'll need to produce an account (sign in with Google, use an email address or supply a Chinese +86 phone number) and after that choose the "DeepThink" choice listed below the timely input box.

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

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

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