Simon Willison's Weblog

That design was trained in part using their unreleased R1 "reasoning" model. Today they've released R1 itself, in addition to an entire household of new designs obtained from that base.

There's a great deal of stuff in the 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 experiences difficulties such as endless repetition, poor readability, and language blending." ... so they also released:

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

I do not have the capability to run models 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 brand-new distilled models are available in.

To support the research study neighborhood, 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 forum.pinoo.com.tr Llama 3.3 70B Instruct).

Weirdly those Llama designs have an MIT license connected, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache licensed so maybe MIT is OK?

Licensing aside, these distilled designs are interesting monsters.

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

Quantized variations are currently beginning to appear. So far I have actually attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to play with.

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

First I fetched and ran the design utilizing Ollama itself:

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

Once the design has been fetched, LLM can talk with it too. I choose using LLM for experiments because 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 generate 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 mix. Let me consider how these two characters may interact in a funny circumstance.

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

[...]

It then believed for championsleage.review 20 paragraphs before outputting the joke! Here's the full records and here's the output at the end, wiki.dulovic.tech 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 sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place saucers on the table, triggering a couple of spills.

After a series of comical accidents, the walrus looks up and states with a smile, "This isn't so fishy any longer." The pelican smirks and mentions, "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 lead to comical mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming 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 theme.

So yeah, the joke is dreadful. But the procedure of arriving was such an intriguing insight into how these new designs work.

This was a fairly little 8B model. I'm looking forward to 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 design that I have actually 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 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 prompt too. It did refrain from doing very well:

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 believed some more and offered me this:

Similar to the earlier joke, the chain of thought in the records was far more interesting than the end outcome.

Other methods to try DeepSeek-R1

If you desire to try the design out without setting up anything at all you can do so using chat.deepseek.com-you'll need to produce an account (indication in with Google, use an email address or provide a Chinese +86 phone number) and after that choose the "DeepThink" choice listed below the prompt input box.

DeepSeek offer the design through their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:

Then run llm keys set deepseek and paste in your API key, forum.pinoo.com.tr then use llm -m deepseek-reasoner 'prompt' to run prompts.

This won't reveal you the reasoning tokens, wiki.rrtn.org unfortunately. Those are dished out by the API (example here) however LLM does not yet have a way to show them.