Simon Willison’s Weblog

That model was trained in part utilizing their unreleased R1 “reasoning” design. Today they’ve released R1 itself, in addition to a whole household of brand-new designs obtained from that base.

There’s a great deal of stuff in the brand-new release.

DeepSeek-R1-Zero appears to be the base model. It’s over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek alert that “DeepSeek-R1-Zero comes across difficulties such as unlimited repeating, bad readability, and language mixing.” … so they likewise launched:

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

I do not have the ability 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 have fun with myself. That’s where the brand-new distilled models 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 upon Llama and Qwen.

This is a fascinating flex! They have models 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 attached, which I’m uncertain works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?

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

Licensing aside, these distilled designs are interesting beasts.

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

Quantized versions are currently starting to reveal up. So far I’ve attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it’s truly enjoyable 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 wiki.tld-wars.space starts an interactive chat interface.

Once the model has been brought, setiathome.berkeley.edu LLM can talk to it also. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

Each action starts with a … pseudo-XML tag containing the chain of thought utilized to assist create the response. For “a joke about a pelican and a walrus who run a tea room together” that began like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that’s a fascinating mix. Let me think of how these two characters may engage in a funny circumstance.

First, 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, thick fur, and they’re typically found in cooler environments, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is currently 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 space together. The walrus, with its huge size, struggles to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position dishes on the table, causing a few spills.

After a series of comical mishaps, the walrus looks up and states with a smile, “This isn’t so fishy any longer.” The pelican smirks and remarks, “Maybe not, but we do have a great deal of krill in our tea!”

Explanation:

– Setup: Pelican and wiki.fablabbcn.org Walrus run an unlikely tea space. Their sizes lead to comedic mayhem.
– Punchline: “This isn’t so fishy anymore” is a pun on the situation ending up being less absurd. The follow-up joke presents “krill,” a play on words that connects into both marine life (“fish”) and tea, making it humorous while fitting the style.

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

This was a fairly little 8B design. I’m looking forward to experimenting with the Llama 70B variation, 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 design that I’ve 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 model working like this-a 34GB download:

Can it draw a pelican?

I tried my an SVG of a pelican riding a bicycle prompt too. It did refrain from doing effectively:

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

the background wound up covering the remainder of the image

It believed some more and gave me this:

As with the earlier joke, the chain of believed in the transcript was even more interesting than the end outcome.

Other methods to try DeepSeek-R1

If you wish to attempt 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, utilize an email address or provide a Chinese +86 contact number) and after that select the “DeepThink” alternative below the prompt input box.

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

This will not show you the reasoning tokens, sadly. Those are dished out by the API (example here) however LLM does not yet have a method to show them.