Simon Willison's Weblog

That model was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, along with an entire household of new models 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, like most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters difficulties such as limitless repeating, poor readability, and language mixing." ... so they likewise launched:

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

I don't have the ability 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 models are available in.

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

This is an interesting flex! They have designs based upon Qwen 2.5 (14B, 32B, forum.batman.gainedge.org 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 designs are Apache certified so maybe MIT is OK?

Licensing aside, these distilled models are fascinating monsters.

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

Quantized variations are currently starting to appear. Up until now I've attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to play with.

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

First I brought and ran the design utilizing Ollama itself:

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

Once the design has actually been fetched, LLM can talk to it also. I prefer utilizing LLM for experiments due to the fact that it logs everything to SQLite for later exploration.

I installed the plugin and ran it like this:

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

Okay, so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's a fascinating combination. Let me consider how these 2 characters may engage in a humorous situation.

First, let's consider their qualities. Pelicans are understood for their long beaks and qoocle.com Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're usually discovered in cooler climates, like icebergs or snowy areas. So, integrating these two into a tea room setting is already an amusing 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 room together. The walrus, with its big size, struggles to discover comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to put saucers on the table, causing a couple of spills.

After a series of funny mishaps, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "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 comical mayhem.
- 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 funny while fitting the theme.

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

This was a fairly little 8B model. I'm anticipating experimenting with 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 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 variation of that Llama 3.3 70B R1 distilled model 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 very well:

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 believed some more and provided me this:

Similar to the earlier joke, the chain of thought in the transcript was much more fascinating than completion outcome.

Other ways to try DeepSeek-R1

If you want to attempt the design out without installing anything you can do so utilizing chat.deepseek.com-you'll require to create an account (check in with Google, utilize an email address or supply a Chinese +86 phone number) and then select the "DeepThink" choice below the timely input box.

DeepSeek provide the design by means of 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 use llm -m deepseek-reasoner 'prompt' to run triggers.

This won't reveal you the reasoning tokens, unfortunately. Those are provided by the API (example here) but LLM doesn't yet have a way to display them.