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

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

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across difficulties such as unlimited repetition, bad readability, and language mixing." ... so they also released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and thinking jobs". That a person is also MIT licensed, and is a comparable size.

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

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

This is an interesting flex! They have actually 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 designs have an MIT license attached, larsaluarna.se which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?

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

Licensing aside, these distilled designs are interesting monsters.

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

Quantized variations are already starting 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 really enjoyable to have fun with.

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

First I and ran the design using Ollama itself:

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

Once the model has actually been fetched, LLM can speak with it too. I prefer using LLM for experiments since it logs whatever to SQLite for later exploration.

I installed the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to help produce 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 a walrus running a tea room together. Hmm, that's an intriguing mix. Let me believe about how these 2 characters may interact in a funny scenario.

First, higgledy-piggledy.xyz let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in chillier environments, like icebergs or snowy locations. So, combining 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 space together. The walrus, with its big size, has a hard time to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place saucers on the table, triggering a few spills.

After a series of funny accidents, the walrus looks up and states with a smile, "This isn't so fishy anymore." 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 a not likely tea space. Their sizes cause comedic mayhem.

• Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less ridiculous. The follow-up joke presents "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 dreadful. But the procedure of arriving was such an intriguing insight into how these brand-new designs work.
  
  This was a fairly little 8B design. I'm 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 preferred GPT-4 class model that I've run 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 tried my classic Generate an SVG of a pelican riding a bike timely too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the elements incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It thought some more and provided me this:
  
  Similar to the earlier joke, the chain of believed in the records was far more intriguing than completion result.
  
  Other ways to try DeepSeek-R1
  
  If you wish to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or provide a Chinese +86 phone number) and after that pick the "DeepThink" alternative below the prompt input box.
  
  DeepSeek use the model via their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
  
  This will not reveal you the reasoning tokens, regretfully. Those are served up by the API (example here) however LLM doesn't yet have a way to display them.