Simon Willison’s Weblog

That model was trained in part utilizing their unreleased R1 „reasoning“ design. Today they have actually released R1 itself, together with a whole family 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 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 difficulties such as unlimited repetition, poor readability, and language mixing.“ … so they also launched:

DeepSeek-R1-which „includes cold-start data before RL“ and „attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and reasoning tasks“. That a person is likewise MIT licensed, and is a comparable 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 quickly have fun with myself. That’s where the brand-new distilled designs are available in.

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

This is a remarkable 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 models have an MIT license connected, which I’m uncertain is suitable with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?

(I likewise just noticed the MIT license files state „Copyright (c) 2023 DeepSeek“ so they may require to pay a bit more attention to how they copied those in.)

Licensing aside, visualchemy.gallery these distilled models are fascinating monsters.

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

Quantized versions are currently starting to reveal up. Up until now I have actually attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it’s truly fun to play with.

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

First I brought and ran the model using Ollama itself:

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

Once the design has actually been brought, LLM can talk to it too. I prefer utilizing LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I installed the plugin and ran it like this:

Each begins with a … pseudo-XML tag containing the chain of idea utilized to assist create the reaction. For „a joke about a pelican and a walrus who run a tea space together“ that began like this:

Okay, bybio.co so I need 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 think of how these 2 characters may communicate in an amusing scenario.

First, let’s consider their qualities. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and wiki-tb-service.com they’re generally found in chillier environments, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is already 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 decide to open a quaint little tea room together. The walrus, with its big size, has a hard time to discover comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to put saucers on the table, triggering a few spills.

After a series of humorous incidents, the walrus looks up and says with a grin, „This isn’t so fishy any longer.“ The pelican smirks and says, „Maybe not, however we do have a lot of krill in our tea!“

Explanation:

– Setup: Pelican and elearnportal.science Walrus run an unlikely tea room. Their sizes lead to comedic turmoil.
– Punchline: „This isn’t so fishy anymore“ is a pun on the situation becoming less unreasonable. The follow-up joke presents „krill,“ a play on words that connects into both marine life („fish“) and tea, making it funny while fitting the theme.

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

This was a fairly small 8B model. I’m anticipating 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 favourite GPT-4 class design that I have actually 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 design working like this-a 34GB download:

Can it draw a pelican?

I tried my timeless Generate an SVG of a pelican riding a bike 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 offered me this:

Just like the earlier joke, the chain of thought in the records was even more intriguing than the end outcome.

Other methods to attempt DeepSeek-R1

If you desire to attempt the design out without installing anything you can do so using chat.deepseek.com-you’ll need to create an account (check in with Google, use an email address or supply a Chinese +86 telephone number) and after that choose the „DeepThink“ choice listed below the timely input box.

DeepSeek offer 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 configuration file:

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

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