That model was trained in part using their unreleased R1 “reasoning” model. Today they’ve launched R1 itself, together with a whole family of brand-new models obtained from that base.

There’s a great deal of stuff in the brand-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 warn that “DeepSeek-R1-Zero encounters difficulties such as unlimited repeating, poor readability, and language mixing.” … so they likewise released:

DeepSeek-R1-which “integrates cold-start information before RL” and “attains performance similar to OpenAI-o1 across math, code, and reasoning tasks”. That one is also MIT certified, and is a comparable size.

I do not 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 quickly play with myself. That’s where the brand-new distilled models are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

This is a remarkable 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 connected, which I’m uncertain works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?

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

Licensing aside, these distilled models are remarkable beasts.

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

Quantized versions are currently starting to appear. So far I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and 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 fetched and ran the model using 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 speak to it as well. I choose using LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I set up the plugin and setiathome.berkeley.edu ran it like this:

Each reaction begins with a … pseudo-XML tag containing the chain of thought used to help generate the action. For “a joke about a pelican and a walrus who run a tea space together” that began 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 an interesting combination. Let me think of how these 2 characters may interact in a humorous circumstance.

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

[…]
It then thought 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 space together. The walrus, with its huge size, has a hard time to discover comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position saucers on the table, triggering a few spills.

After a series of funny accidents, the walrus looks up and states with a grin, “This isn’t so fishy any longer.” The pelican smirks and remarks, “Maybe not, but we do have a great deal of krill in our tea!”

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes lead to comedic turmoil.

• Punchline: “This isn’t so fishy anymore” is a pun on the situation becoming less . The follow-up joke introduces “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 awful. But the process of getting there was such a fascinating insight into how these new models work.
  
  This was a fairly little 8B model. I’m looking forward to experimenting with the Llama 70B variation, 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 variation of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted my classic Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the components incorrect, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It believed some more and provided me this:
  
  As with the earlier joke, the chain of believed in the transcript was much more intriguing than the end outcome.
  
  Other ways to try DeepSeek-R1
  
  If you desire to try the design out without installing anything you can do so using chat.deepseek.com-you’ll need to create an account (sign in with Google, utilize an email address or offer a Chinese +86 phone number) and then choose the “DeepThink” choice listed below the prompt input box.
  
  DeepSeek use the model via their API, using 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 secret, then utilize llm -m deepseek-reasoner ‘prompt’ to run triggers.
  
  This will not reveal you the reasoning tokens, sadly. Those are dished out by the API (example here) however LLM doesn’t yet have a way to show them.