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 a whole household of new models obtained from that base.

There's an entire lot of stuff in the new release.

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, rocksoff.org like most of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences difficulties such as endless repeating, bad readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across mathematics, code, and thinking tasks". That a person is likewise MIT certified, and is a similar size.

I do not have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can quickly play with myself. That's where the new distilled models are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is a fascinating flex! They have actually 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 models have an MIT license connected, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache certified so possibly MIT is OK?

Licensing aside, these distilled models are interesting monsters.

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

Quantized versions are currently starting to appear. So far I've tried simply one of 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 using the mix of Ollama, LLM and bio.rogstecnologia.com.br 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 interface.

Once the model has been fetched, LLM can speak with it too. I prefer utilizing LLM for experiments since 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 help produce the action. 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 sitiosecuador.com a walrus running a tea room together. Hmm, that's an interesting combination. Let me think of how these two characters may engage in a funny situation.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally discovered in colder climates, like icebergs or snowy locations. So, opentx.cz integrating these two 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 decide to open a quaint little tea space together. The walrus, with its huge size, suvenir51.ru struggles to find comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to put saucers on the table, causing a couple of spills.

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

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes result in comical turmoil.
- Punchline: "This isn't so fishy anymore" 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 funny while fitting the style.

So yeah, the joke is horrible. But the process of arriving was such a fascinating insight into how these new models work.

This was a fairly small 8B model. I'm eagerly anticipating 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 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 tried my timeless Generate an SVG of a pelican riding a bike timely too. It did refrain from doing extremely well:

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 believed some more and gave me this:

As with the earlier joke, the chain of believed in the records was much more intriguing than the end result.

Other ways to try DeepSeek-R1

If you desire to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to develop an account (indication in with Google, use an email address or supply a Chinese +86 contact number) and then choose the "DeepThink" alternative below the prompt input box.

DeepSeek provide the model via their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file: