Simon Willison’s Weblog

That model was trained in part utilizing their unreleased R1 “thinking” model. Today they have actually launched R1 itself, in addition to an entire family of new models obtained from that base.

There’s a great deal of stuff 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 obstacles such as unlimited repetition, bad readability, and language blending.” … so they likewise released:

DeepSeek-R1-which “incorporates cold-start data before RL” and “attains performance comparable to OpenAI-o1 throughout mathematics, code, and reasoning tasks”. That one is also MIT accredited, galgbtqhistoryproject.org 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 easily 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 6 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.

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

(I likewise simply saw the MIT license files say “Copyright (c) 2023 DeepSeek” so they might require to pay a bit more attention to how they copied those in.)

Licensing aside, akropolistravel.com these distilled designs are remarkable monsters.

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

Quantized versions are currently starting to appear. Up until now I have actually tried just one of 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 using the mix 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 begins an interactive chat user interface.

Once the model has been fetched, LLM can talk with it as well. I prefer utilizing LLM for experiments since it logs whatever 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 used to help produce the response. For “a joke about a pelican and a walrus who run a tea room together” that began like this:

Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that’s an intriguing combination. Let me believe about how these 2 characters might communicate in a funny circumstance.

First, let’s consider their qualities. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they’re normally found in cooler environments, like icebergs or snowy locations. So, combining these 2 into a tea space setting is currently a funny image.

[…]

It then thought for 20 paragraphs before outputting the joke! Here’s the complete records 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, struggles to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to put dishes on the table, triggering a couple of spills.

After a series of humorous incidents, the walrus searches for and says with a smile, “This isn’t so fishy any longer.” The pelican smirks and says, “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 result in comedic mayhem.
– Punchline: “This isn’t so fishy any longer” is a pun on the scenario becoming less . 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 terrible. But the procedure of getting there was such a fascinating insight into how these new designs work.

This was a fairly little 8B design. I’m looking forward to trying out the Llama 70B version, 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 model that I have actually 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 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 prompt too. It did refrain from doing effectively:

It aimed to me like it got the order of the aspects 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 thought in the transcript was much more intriguing than the end outcome.

Other ways to try DeepSeek-R1

If you desire to try the model out without installing anything you can do so using chat.deepseek.com-you’ll require to develop an account (check in with Google, use an email address or supply a Chinese +86 telephone number) and then choose the “DeepThink” option below the timely input box.

DeepSeek use the model through 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 keys set deepseek and paste in your API key, then use llm -m deepseek-reasoner ‘prompt’ to run triggers.

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