Simon Willison's Weblog

That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, in addition to an entire household of brand-new models obtained from that base.

There's an entire lot of things 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 warn that "DeepSeek-R1-Zero comes across difficulties such as limitless repeating, poor readability, and language blending." ... so they also launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance comparable to OpenAI-o1 throughout math, code, and reasoning jobs". That one is also MIT accredited, and is a similar size.

I don't have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily 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 upon Llama and Qwen.

This is a remarkable flex! They have designs 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 Llama models have an MIT license connected, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?

Licensing aside, these distilled models are fascinating monsters.

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

Quantized variations are currently beginning to appear. So far I've attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched 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 fetched and ran the model using Ollama itself:

This downloads around 8.5 GB of design data and surgiteams.com begins an interactive chat user interface.

Once the design has actually been brought, LLM can speak to it also. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.

I set up the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of thought used to assist create the reaction. For "a joke about a pelican and a walrus who run a tea space 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 an interesting mix. Let me think about how these 2 characters might interact in a humorous situation.

First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, wifidb.science often seen near the beach or water. Walruses have big teeth, thick fur, utahsyardsale.com and they're normally discovered in chillier climates, like icebergs or snowy areas. So, combining these 2 into a tea space setting is already a funny 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 room together. The walrus, with its huge size, has a hard time to discover comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, uses its beak to place saucers on the table, triggering a few spills.

After a series of comical accidents, the walrus searches for and says with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes result in comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less unreasonable. 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 procedure of arriving was such an intriguing insight into how these new models work.

This was a fairly little 8B design. I'm anticipating checking out 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 favourite GPT-4 class model that I've operated 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 design 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 effectively:

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

the background ended up covering the remainder of the image

It believed some more and offered me this:

Just like the earlier joke, yewiki.org the chain of thought in the transcript was much more interesting than completion result.

Other methods to try DeepSeek-R1

If you desire to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to develop an account (check in with Google, wiki.whenparked.com use an email address or offer a Chinese +86 telephone number) and after that pick the "DeepThink" choice below the prompt input box.