That model was trained in part using their unreleased R1 "thinking" model. Today they've released R1 itself, utahsyardsale.com in addition to an entire family of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across difficulties such as unlimited repetition, poor readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout math, code, and thinking jobs". That a person is likewise MIT certified, and is a similar size.

I don't 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 have fun with myself. That's where the new distilled models are available in.

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

This is a remarkable flex! They have 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, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited 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 designs are fascinating beasts.

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

Quantized versions are currently starting to appear. So far I have actually attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to have fun with.

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

First I fetched and ran the design utilizing Ollama itself:

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

Once the model has actually been brought, LLM can speak with it also. I prefer utilizing LLM for experiments since it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

Each response starts with a ... pseudo-XML tag containing the chain of thought used to assist 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 walrus running a tea room together. Hmm, that's an interesting combination. Let me think of how these 2 characters may connect in an amusing circumstance.

First, let's consider their qualities. Pelicans are known for their long beaks and bio.rogstecnologia.com.br Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in cooler climates, like icebergs or snowy areas. So, integrating these two into a tea space setting is currently 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 decide to open a quaint little tea room together. The walrus, wiki.dulovic.tech with its huge size, struggles to find comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, asteroidsathome.net trying to assist, uses its beak to put dishes on the table, triggering a few spills.

After a series of comical incidents, the walrus searches for and says with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a lot 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 scenario becoming less unreasonable. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.
  
  So yeah, the joke is terrible. But the procedure of getting there was such an interesting insight into how these new models work.
  
  This was a fairly little 8B model. I'm eagerly anticipating attempting 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 design that I've run 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 components wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It believed some more and gave me this:
  
  Similar to the earlier joke, the chain of thought in the records was far more intriguing than completion outcome.
  
  Other ways to attempt DeepSeek-R1
  
  If you desire to try the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or offer a Chinese +86 contact number) and then pick the "DeepThink" alternative below the prompt input box.
  
  DeepSeek use the design via 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 utilize llm -m deepseek-reasoner 'timely' to run triggers.
  
  This will not reveal you the thinking tokens, sadly. Those are dished out by the API (example here) however LLM doesn't yet have a way to display them.