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

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

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences difficulties such as endless repetition, poor readability, and language mixing." ... so they also launched:

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

I don't have the ability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can quickly play with myself. That's where the new distilled models are available in.

To support the research study neighborhood, 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 designs 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 models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?

(I likewise simply noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they might require to pay a bit more attention to how they copied those in.)

Licensing aside, these distilled models are remarkable monsters.

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

Quantized variations are currently beginning to appear. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to play with.

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

First I fetched and ran the model utilizing Ollama itself:

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

Once the design has actually been brought, LLM can talk to it as well. I prefer utilizing LLM for experiments since it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to assist create the action. For "a joke about a pelican and a walrus who run a tea room together" that started like this:

Okay, so I require to come up with a joke about a pelican and disgaeawiki.info a walrus running a tea room together. Hmm, that's a fascinating combination. Let me believe about how these 2 characters may connect in a humorous circumstance.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, classifieds.ocala-news.com and they're normally discovered in cooler environments, like icebergs or snowy locations. So, combining these 2 into a tea room setting is already a funny image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete 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, struggles to discover comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to place dishes on the table, triggering a couple of spills.

After a series of comical accidents, the walrus searches for setiathome.berkeley.edu and states 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 Walrus run a not likely tea room. Their sizes lead to comical turmoil.

• Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less unreasonable. The follow-up joke introduces "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 awful. But the process of arriving was such an interesting insight into how these new designs work.
  
  This was a fairly small 8B design. I'm looking forward to checking out 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 favourite GPT-4 class design that I have actually 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 traditional Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing effectively:
  
  It aimed to me like it got the order of the aspects wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It thought some more and gave me this:
  
  Similar to the earlier joke, the chain of believed in the records was far more interesting than the end result.
  
  Other methods to attempt DeepSeek-R1
  
  If you desire to attempt the design out without installing anything at all you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or provide a Chinese +86 contact number) and after that select the "DeepThink" alternative listed below the timely input box.
  
  DeepSeek offer the model via their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
  
  This won't reveal you the thinking tokens, unfortunately. Those are provided by the API (example here) however LLM does not yet have a method to show them.