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

There's an entire lot of stuff in the 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 tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters difficulties such as endless repeating, bad readability, and language mixing." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance comparable to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT licensed, and is a comparable size.

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

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

This is an interesting flex! They have actually models based on Qwen 2.5 (14B, higgledy-piggledy.xyz 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 connected, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache certified so maybe MIT is OK?

(I also simply discovered 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 remarkable beasts.

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

Quantized versions are currently beginning to reveal up. So far I've tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to play with.

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

First I brought and ran the model using Ollama itself:

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

Once the design has been fetched, LLM can talk with it as well. I prefer using LLM for experiments because it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each response starts with a ... pseudo-XML tag containing the chain of idea utilized to help generate the response. 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 hb9lc.org a walrus running a tea space together. Hmm, that's an interesting combination. Let me believe about how these 2 characters may engage in a humorous circumstance.

First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, typically 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, combining these two into a tea room setting is currently a funny image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full 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, with its huge size, struggles to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to place dishes on the table, triggering a few spills.

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

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes result in comedic mayhem.

• Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less unreasonable. The follow-up joke presents "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 a fascinating insight into how these brand-new models work.
  
  This was a fairly small 8B design. I'm looking forward to trying 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 model that I've worked 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 tried my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing really well:
  
  It aimed to me like it got the order of the components incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It thought some more and offered me this:
  
  Just like the earlier joke, the chain of thought in the records was much more fascinating than the end outcome.
  
  Other methods to attempt DeepSeek-R1
  
  If you desire to try the model out without setting up anything you can do so utilizing chat.deepseek.com-you'll require to create an account (check in with Google, utilize an email address or offer a Chinese +86 phone number) and after that select the "DeepThink" option below the prompt input box.
  
  DeepSeek provide the model through their API, tandme.co.uk 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 and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not reveal you the reasoning tokens, unfortunately. Those are provided by the API (example here) however LLM does not yet have a method to show them.