GitLab

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

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

DeepSeek-R1-Zero appears to be the base design. 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 comes across challenges such as unlimited repetition, bad readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and thinking tasks". That a person is also MIT licensed, photorum.eclat-mauve.fr and is a comparable 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 2 designs are something I can easily have fun 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 dense designs distilled from DeepSeek-R1 based upon 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 Llama models have an MIT license connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache certified so perhaps MIT is OK?

(I also just observed 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 designs are interesting beasts.

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

Quantized variations are already beginning to appear. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really enjoyable to have fun with.

I'm running it using the mix 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 data and begins an interactive chat interface.

Once the model has been brought, LLM can talk with it also. I choose using LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I installed the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of thought used to help create 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 a tea space together. Hmm, that's an intriguing combination. Let me believe about how these 2 characters may engage in an amusing scenario.

First, let's consider their qualities. 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, gratisafhalen.be like icebergs or snowy areas. So, integrating these two into a tea space setting is already a funny image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full 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 room together. The walrus, with its big size, passfun.awardspace.us has a hard time to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position dishes on the table, causing a few spills.

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

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes cause comedic mayhem.

• Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming 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 style.
  
  So yeah, the joke is awful. But the procedure of getting there was such a fascinating insight into how these brand-new designs 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 preferred GPT-4 class design that I've 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 attempted 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 incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and provided me this:
  
  Similar to the earlier joke, users.atw.hu the chain of believed in the records was far more fascinating than the end result.
  
  Other ways to try DeepSeek-R1
  
  If you wish to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to create an account (indication in with Google, use an email address or offer a Chinese +86 contact number) and after that pick the "DeepThink" choice listed below the timely input box.
  
  DeepSeek use the model via 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 keys set deepseek and paste in your API key, then use 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.