That design was trained in part utilizing their unreleased R1 “thinking” model. Today they’ve launched R1 itself, in addition to a whole family of new designs obtained from that base.

There’s an entire lot of stuff in the new release.

DeepSeek-R1-Zero seems the base model. It’s over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek caution that “DeepSeek-R1-Zero comes across difficulties such as limitless repetition, poor readability, and language blending.” … so they also launched:

DeepSeek-R1-which “includes cold-start information before RL” and “attains efficiency comparable to OpenAI-o1 across mathematics, code, and thinking tasks”. That a person is also MIT accredited, and is a comparable 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 brand-new distilled designs are available in.

To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based upon Llama and Qwen.

This is a fascinating flex! They have 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 designs have an MIT license attached, which I’m uncertain works with the underlying Llama license. Qwen models are Apache licensed so possibly MIT is OK?

(I likewise just observed the MIT license files say “Copyright © 2023 DeepSeek” so they might need to pay a bit more attention to how they copied those in.)

Licensing aside, these distilled designs are fascinating monsters.

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

Quantized versions are already 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 gratisafhalen.be it’s truly fun 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 model utilizing Ollama itself:

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

Once the design has actually been fetched, LLM can talk with it as well. I prefer using LLM for experiments due to the fact that it logs everything to SQLite for later exploration.

I set up the plugin and wiki.philipphudek.de ran it like this:

Each action begins with a … pseudo-XML tag containing the chain of thought utilized 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 space together. Hmm, that’s a fascinating mix. Let me think about how these two characters might communicate in a humorous situation.

First, let’s consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they’re generally discovered in chillier environments, like icebergs or elearnportal.science snowy areas. So, integrating these 2 into a tea space setting is already 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 choose to open a quaint little tea room together. The walrus, with its big size, struggles to chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, wiki.vifm.info the pelican, trying to help, utilizes its beak to place saucers on the table, triggering a couple of spills.

After a series of humorous incidents, the walrus looks up and states with a grin, “This isn’t so fishy any longer.” The pelican smirks and mentions, “Maybe not, however we do have a lot of krill in our tea!”

Explanation:

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

• Punchline: “This isn’t so fishy any longer” is a pun on the scenario becoming less absurd. The follow-up joke presents “krill,” a play on words that ties into both marine life (“fish”) and akropolistravel.com tea, making it amusing while fitting the style.
  
  So yeah, the joke is horrible. But the procedure of arriving was such an intriguing insight into how these new designs work.
  
  This was a fairly small 8B model. 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 favourite 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 timeless Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing really 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 gave me this:
  
  Similar to the earlier joke, demo.qkseo.in the chain of thought in the transcript was far more interesting than completion result.
  
  Other ways to attempt DeepSeek-R1
  
  If you want to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you’ll need to produce an account (check in with Google, use an email address or supply a Chinese +86 contact number) and after that pick the “DeepThink” choice 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 secret, then use llm -m deepseek-reasoner ‘prompt’ to run triggers.
  
  This won’t show you the reasoning tokens, regretfully. Those are provided by the API (example here) however LLM doesn’t yet have a method to show them.