GitLab

That design was trained in part using their unreleased R1 "reasoning" design. Today they've launched R1 itself, together with a whole household of brand-new models obtained from that base.

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

DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like most of their other releases, wolvesbaneuo.com is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences challenges such as endless repetition, bad readability, and language blending." ... so they also launched:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and thinking tasks". That a person is likewise MIT accredited, and 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 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 6 thick models distilled from DeepSeek-R1 based upon Llama and Qwen.

This is an interesting 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 models have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache accredited so maybe MIT is OK?

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

Licensing aside, these distilled models are interesting beasts.

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

Quantized versions are currently beginning to reveal up. So far I have actually attempted just 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 utilizing the mix 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 model information and starts an interactive chat interface.

Once the model has actually been brought, LLM can talk with it as well. I choose using LLM for experiments because it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought used to assist produce the action. For "a joke about a pelican and a walrus who run a tea space together" that started like this:

Okay, so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an intriguing mix. Let me believe about how these two characters may interact in a funny circumstance.

First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or rocksoff.org water. Walruses have huge teeth, thick fur, and they're usually discovered in colder environments, like icebergs or snowy areas. So, combining these 2 into a tea room setting is currently an amusing image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete transcript 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 big size, struggles to find comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to put dishes on the table, causing a few spills.

After a series of humorous incidents, the walrus searches for and states with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes lead to comical turmoil.

• Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the style.
  
  So yeah, the joke is dreadful. But the process of getting there was such an intriguing insight into how these new models work.
  
  This was a fairly little 8B design. I'm eagerly anticipating checking out the Llama 70B version, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design that I've worked 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 traditional Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing very well:
  
  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 thought some more and provided me this:
  
  Just like the earlier joke, the chain of thought in the records was even more intriguing than the end result.
  
  Other methods to try DeepSeek-R1
  
  If you wish to try the design out without setting up anything you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, use an email address or a Chinese +86 contact number) and after that pick the "DeepThink" choice listed below the timely input box.
  
  DeepSeek offer the model via their API, utilizing an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
  
  This will not reveal you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM doesn't yet have a way to show them.