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

There's a great deal of things 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 alert that "DeepSeek-R1-Zero comes across challenges such as limitless repeating, poor readability, and language blending." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and reasoning tasks". That a person is also MIT licensed, and is a similar size.

I don't 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 easily play with myself. That's where the new distilled designs are available in.

To support the research neighborhood, prawattasao.awardspace.info we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based on Llama and Qwen.

This is a fascinating 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 designs have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?

(I also just discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they might 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 variations are already beginning to appear. So far I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to play with.

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

First I brought 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 been brought, LLM can talk to it also. I choose using LLM for experiments since it logs everything to SQLite for later expedition.

I set up the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of idea used to help produce the reaction. For "a joke about a pelican and a walrus who run a tea space together" that started 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 a fascinating mix. Let me think of how these 2 characters may interact in an amusing circumstance.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're normally discovered in colder climates, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is currently 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, asteroidsathome.net 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 find comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to put dishes on the table, triggering a few spills.

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

Explanation:

- Setup: and Walrus run an unlikely tea room. Their sizes lead to comical chaos.

• Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less unreasonable. 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 theme.
  
  So yeah, forum.pinoo.com.tr the joke is horrible. But the procedure of arriving was such an intriguing insight into how these brand-new models work.
  
  This was a fairly small 8B model. I'm anticipating checking out the Llama 70B variation, which isn't yet available in a GGUF I can run with 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 variation of that Llama 3.3 70B R1 distilled model 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 very 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 believed some more and provided me this:
  
  Similar to the earlier joke, the chain of thought in the transcript was much more interesting than the end result.
  
  Other ways to attempt DeepSeek-R1
  
  If you desire to attempt the design out without installing anything you can do so using chat.deepseek.com-you'll require to develop 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 prompt input box.
  
  DeepSeek provide the model by means of 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 secrets set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not reveal you the thinking tokens, unfortunately. Those are dished out by the API (example here) however LLM does not yet have a method to display them.