Simon Willison's Weblog

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

There's an entire lot of stuff 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 clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences challenges such as limitless repeating, poor readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is likewise MIT accredited, and is a similar size.

I don't have the ability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly play 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 six thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is a fascinating flex! They have actually designs based upon 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 attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so possibly MIT is OK?

Licensing aside, these distilled designs are fascinating monsters.

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

Quantized variations are already starting to show up. So far I have actually tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.

I'm running it utilizing the mix 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 model information and starts an interactive chat user interface.

Once the design has actually been brought, addsub.wiki LLM can speak with it also. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for utahsyardsale.com later expedition.

I set up the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of thought utilized to help produce 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 think of how these 2 characters may communicate in a funny scenario.

First, systemcheck-wiki.de let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, annunciogratis.net thick fur, and they're usually discovered in cooler climates, like icebergs or wiki.rolandradio.net snowy areas. So, combining these two into a tea room setting is currently an amusing image.

[...]

It then believed for 20 paragraphs before outputting the joke! Here's the complete 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 huge size, has a hard time to find comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to place saucers on the table, triggering a couple of spills.

After a series of humorous accidents, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes result in comedic mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less ridiculous. 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 horrible. But the process of arriving was such an intriguing insight into how these brand-new models work.

This was a fairly small 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 worked 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 tried my timeless Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing effectively:

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

the background ended up covering the remainder of the image

It thought some more and offered me this:

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

Other ways to attempt DeepSeek-R1

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

DeepSeek offer the design via their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:

Then run llm keys set deepseek and systemcheck-wiki.de paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run prompts.

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