That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they've released R1 itself, in addition to a whole household of brand-new models obtained from that base.

There's a whole lot of stuff in the 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 clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero comes across obstacles such as limitless repeating, poor readability, and language mixing." ... so they also released:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and reasoning jobs". That one is likewise MIT accredited, and is a similar size.

I do not have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly have fun with myself. That's where the brand-new distilled designs are available in.

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

This is a fascinating flex! They have 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 connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?

(I also just discovered 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 designs are fascinating beasts.

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

Quantized variations are already beginning to reveal up. So far I've tried simply among 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 using the combination of Ollama, LLM and the llm-ollama plugin.

First I fetched and ran the model using Ollama itself:

This downloads around 8.5 GB of model data and starts an interactive chat user interface.

Once the model has actually been brought, LLM can talk to it as well. I choose using LLM for experiments since it logs everything to SQLite for wiki.rolandradio.net later exploration.

I installed the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought used to assist produce the action. For "a joke about a pelican and a walrus who run a tea space together" that began like this:

Okay, akropolistravel.com 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 combination. Let me think about how these 2 characters may interact in a humorous situation.

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 huge teeth, thick fur, and they're generally found in colder climates, visualchemy.gallery like icebergs or snowy locations. So, integrating these two into a tea room setting is currently an amusing image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full records and here's the output at the end, after the tag:

The Joke:

A pelican and a walrus choose to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to put dishes on the table, triggering a couple of spills.

After a series of humorous accidents, the walrus looks up and says with a grin, "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 a not likely tea room. Their sizes cause comedic chaos.

• Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less unreasonable. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it humorous while fitting the theme.
  
  So yeah, the joke is terrible. But the process of getting there was such an interesting insight into how these brand-new designs work.
  
  This was a fairly little 8B design. I'm anticipating experimenting with the Llama 70B version, systemcheck-wiki.de 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 design working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I tried my traditional Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing very well:
  
  It aimed to me like it got the order of the components incorrect, so I followed up with:
  
  the background wound 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 transcript was much more intriguing than completion result.
  
  Other methods to try DeepSeek-R1
  
  If you wish to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll require to produce an account (indication in with Google, utilize an email address or supply a Chinese +86 contact number) and after that pick the "DeepThink" alternative listed below the prompt input box.
  
  DeepSeek offer the design through 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 secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not show you the thinking tokens, unfortunately. Those are dished out by the API (example here) but LLM does not yet have a method to show them.