Simon Willison’s Weblog

That design was trained in part utilizing their unreleased R1 “thinking” design. Today they’ve launched R1 itself, together with an entire household of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base model. It’s over 650GB in size and, forum.pinoo.com.tr like the majority of their other releases, is under a tidy MIT license. DeepSeek alert that “DeepSeek-R1-Zero experiences challenges such as endless repetition, bad readability, and language mixing.” … so they likewise released:

DeepSeek-R1-which “includes cold-start data before RL” and “attains efficiency similar to OpenAI-o1 across math, code, and reasoning jobs”. That a person is also MIT certified, and is a comparable size.

I don’t have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly have fun with myself. That’s where the brand-new distilled designs are available in.

To support the research neighborhood, 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 fascinating 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 designs are Apache licensed so perhaps MIT is OK?

(I likewise just 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 designs are remarkable beasts.

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

Quantized versions are already starting to appear. So far I’ve 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 fetched and ran the design using Ollama itself:

This downloads around 8.5 GB of design data and begins an interactive chat interface.

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

I set up the plugin and ran it like this:

Each action starts with a … pseudo-XML tag containing the chain of thought utilized to help create the action. For “a joke about a pelican and a walrus who run a tea space together” that started 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 mix. Let me think of how these two characters might engage in a humorous circumstance.

First, let’s consider their attributes. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they’re usually discovered in cooler environments, like icebergs or snowy locations. So, integrating these two into a tea space 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 choose to open a quaint little tea space together. The walrus, with its big size, struggles to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place dishes on the table, a few spills.

After a series of funny incidents, oke.zone the walrus looks up and states with a grin, “This isn’t so fishy anymore.” 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 room. Their sizes cause comical chaos.
– Punchline: “This isn’t so fishy anymore” is a pun on the situation becoming less unreasonable. 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 theme.

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

This was a fairly little 8B design. I’m looking forward to trying the Llama 70B version, 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 version of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:

Can it draw a pelican?

I attempted my traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing effectively:

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

the background ended up covering the remainder of the image

It thought some more and gave me this:

Just like the earlier joke, the chain of believed in the records was much more interesting than the end outcome.

Other methods to try DeepSeek-R1

If you wish to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you’ll need to produce an account (sign in with Google, use an email address or offer a Chinese +86 phone number) and then select the “DeepThink” choice listed below the timely input box.

DeepSeek provide the design by means of their API, utilizing an OpenAI-imitating endpoint. You can access that via 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 use llm -m deepseek-reasoner ‘prompt’ to run prompts.

This won’t reveal you the reasoning tokens, regretfully. Those are served up by the API (example here) but LLM doesn’t yet have a method to show them.