That model was trained in part utilizing their unreleased R1 "thinking" design. Today they've launched R1 itself, in addition to an entire family of new models obtained from that base.

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

DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences obstacles such as unlimited repetition, poor readability, and language mixing." ... so they also released:

DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout math, code, and reasoning tasks". That one is also MIT accredited, and is a similar size.

I do not have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can easily play with myself. That's where the brand-new distilled designs 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 upon Qwen 2.5 (14B, 32B, Math 1.5 B and classifieds.ocala-news.com Math 7B) and Llama 3 (Llama-3.1 8B and wiki.woge.or.at Llama 3.3 70B Instruct).

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

(I likewise just discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a little 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. Up until now I've attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to have fun with.

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

First I brought and ran the model using Ollama itself:

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

Once the design has been brought, LLM can talk with it too. I prefer using LLM for experiments because it logs everything to SQLite for later exploration.

I installed the plugin and ran it like this:

Each response 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 began like this:

Okay, so I require to come up with a joke about a pelican and oke.zone a walrus running a tea room together. Hmm, that's a fascinating combination. Let me think of how these two characters might connect in an amusing circumstance.

First, let's consider their attributes. Pelicans are understood for their long beaks and scientific-programs.science Webbed feet, frequently seen near the beach or pipewiki.org water. Walruses have big teeth, thick fur, and they're normally found in chillier environments, like icebergs or snowy areas. So, combining these 2 into a tea room setting is already a funny image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full transcript and disgaeawiki.info here's the output at the end, after the tag:

The Joke:

A pelican and photorum.eclat-mauve.fr a walrus decide to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to put dishes on the table, triggering a couple of spills.

After a series of comical accidents, the walrus searches for and states with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however we do have a great deal of krill in our tea!"

Explanation:

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

• Punchline: "This isn't so fishy any longer" is a pun on the situation becoming less unreasonable. 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 theme.
  
  So yeah, the joke is awful. 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 checking out 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 have actually 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 timeless 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 aspects wrong, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It thought some more and provided me this:
  
  Just like the earlier joke, the chain of believed in the transcript was even more intriguing than the end outcome.
  
  Other methods to attempt DeepSeek-R1
  
  If you wish to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll require to produce an account (sign in with Google, utilize an email address or supply a Chinese +86 phone number) and then choose the "DeepThink" choice listed below the prompt input box.
  
  DeepSeek provide the design via their API, using an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm secrets set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run prompts.
  
  This will not reveal you the thinking tokens, sadly. Those are dished out by the API (example here) but LLM doesn't yet have a way to display them.