That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually released R1 itself, together with a whole household of brand-new designs obtained from that base.

There's an entire lot of stuff in the brand-new release.

DeepSeek-R1-Zero seems the base model. 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 encounters challenges such as limitless repeating, poor readability, and language mixing." ... so they also released:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across mathematics, code, and reasoning jobs". That one is also MIT licensed, and is a comparable size.

I do not have the ability to run models larger 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 brand-new distilled models are available in.

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

This is a fascinating flex! They have actually models 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 attached, higgledy-piggledy.xyz which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?

(I likewise just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)

Licensing aside, these distilled models are fascinating monsters.

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

Quantized versions are currently starting to reveal up. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to have fun with.

I'm running it utilizing the combination of Ollama, ai-db.science LLM and the llm-ollama plugin.

First I fetched and ran the model using Ollama itself:

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

Once the design has been brought, LLM can talk with it also. I prefer using LLM for experiments since it logs whatever to SQLite for later exploration.

I set up the plugin and visualchemy.gallery ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to help create the response. For "a joke about a pelican and a walrus who run a tea room together" that began like this:

Okay, so I need to come up with a joke about a pelican and a a tea room together. Hmm, that's an interesting mix. Let me think of how these 2 characters may communicate in a funny scenario.

First, let's consider their qualities. 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 found in chillier environments, like icebergs or snowy locations. So, integrating these two into a tea space setting is currently a funny image.

[...]
It then believed 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 big size, has a hard time to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to place saucers on the table, causing a few spills.

After a series of humorous accidents, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and brotato.wiki.spellsandguns.com Walrus run an unlikely tea space. Their sizes cause comical turmoil.

• Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it amusing 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 small 8B design. I'm anticipating trying the Llama 70B version, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class design that I've operated 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 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 aspects incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It thought some more and offered me this:
  
  Similar to the earlier joke, higgledy-piggledy.xyz the chain of believed in the transcript was even more interesting than the end outcome.
  
  Other ways to try DeepSeek-R1
  
  If you want to attempt the design out without setting up anything you can do so using chat.deepseek.com-you'll require to produce an account (check in with Google, use an email address or provide a Chinese +86 phone number) and after that choose the "DeepThink" option listed below the prompt input box.
  
  DeepSeek use the model via their API, utilizing an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm secrets set deepseek and paste in your API key, 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 does not yet have a method to show them.