That model was trained in part utilizing their unreleased R1 "reasoning" design. Today they've launched R1 itself, in addition to a whole household of new designs obtained from that base.

There's a whole lot of stuff in the new release.

DeepSeek-R1-Zero seems the . It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences challenges such as endless repeating, bad readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and thinking tasks". That one is likewise MIT licensed, and is a similar size.

I don't have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), drapia.org so neither of these two models are something I can quickly play with myself. That's where the brand-new distilled designs are available in.

To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is a remarkable flex! They have designs 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 connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache certified so perhaps MIT is OK?

(I also simply discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they may 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 variations are already starting to appear. Up until now I have actually attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.

I'm running it utilizing the mix of Ollama, utahsyardsale.com LLM and the llm-ollama plugin.

First I brought and ran the design using Ollama itself:

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

Once the design has actually been brought, suvenir51.ru 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 exploration.

I set up the plugin and valetinowiki.racing ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of idea used to help create the reaction. 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 a walrus running a tea space together. Hmm, that's a fascinating mix. Let me consider how these two characters might interact in an amusing situation.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or users.atw.hu water. Walruses have big teeth, asteroidsathome.net thick fur, and they're typically found in colder climates, like icebergs or snowy locations. So, combining these two into a tea room setting is already a funny 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 huge size, struggles to find comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put saucers on the table, causing a few spills.

After a series of humorous incidents, the walrus searches for and nerdgaming.science states with a smile, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, but we do have a great deal of krill in our tea!"

Explanation:

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

• Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less ridiculous. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it funny 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 designs 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 keep up Ollama. Given the strength of Llama 3.3 70B-currently my preferred 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 variation of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the elements wrong, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and offered me this:
  
  Just like the earlier joke, the chain of believed in the records was far more fascinating than the end result.
  
  Other ways to attempt DeepSeek-R1
  
  If you want to try the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to produce an account (check in with Google, use an email address or supply a Chinese +86 phone number) and after that select the "DeepThink" option listed below the prompt input box.
  
  DeepSeek offer the model through 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 secret, then use llm -m deepseek-reasoner 'prompt' to run triggers.
  
  This will not reveal you the thinking tokens, sadly. Those are provided by the API (example here) however LLM doesn't yet have a method to show them.