Simon Willison's Weblog

That model was trained in part using their unreleased R1 "thinking" design. Today they have actually released R1 itself, along with a whole family of brand-new models obtained from that base.

There's a great deal of things in the brand-new release.

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters challenges such as unlimited repeating, bad readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains efficiency equivalent to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT licensed, and wiki.eqoarevival.com is a similar 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 quickly have fun with myself. That's where the 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 on Llama and Qwen.

This is an interesting flex! They have actually models based on 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 have an MIT license attached, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?

(I likewise just discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled models are remarkable monsters.

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

Quantized versions are already beginning to reveal up. Up until now I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to have fun with.

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

First I brought and ran the model utilizing Ollama itself:

This downloads around 8.5 GB of model information and starts an interactive chat interface.

Once the design has actually been brought, LLM can talk to it too. I choose utilizing LLM for experiments since it logs whatever to SQLite for later exploration.

I set up the plugin and raovatonline.org ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought used to assist create 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 space together. Hmm, that's a fascinating combination. Let me think of how these 2 characters might engage in a funny scenario.

First, let's consider their attributes. 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 normally discovered in colder climates, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is currently an amusing image.

[...]
It then thought 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, struggles to find comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, uses its beak to place saucers on the table, causing a couple of spills.

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

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes result in comical mayhem. - Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less absurd. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, forum.altaycoins.com making it amusing while fitting the theme.

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

This was a fairly little 8B design. I'm eagerly anticipating experimenting with 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 preferred GPT-4 class model 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 classic 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 incorrect, so I followed up with:

the background ended up covering the remainder of the image

It thought some more and gave me this:

As with the earlier joke, wiki.dulovic.tech the chain of believed in the transcript was even more fascinating than completion result.

Other ways to attempt 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 produce an account (indication in with Google, use an email address or supply a Chinese +86 contact number) and then 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 through 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 utilize llm -m deepseek-reasoner 'prompt' to run prompts.

This won't show you the thinking tokens, regretfully. Those are served up by the API (example here) but LLM doesn't yet have a method to show them.