That model was trained in part utilizing their unreleased R1 "thinking" model. Today they have actually released R1 itself, together with a whole household of new models obtained from that base.

There's a lot of stuff 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 tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero comes across obstacles such as limitless repetition, bad readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is likewise MIT certified, and is a comparable size.

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

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

This is an interesting flex! They have actually models based upon Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and Llama 3 (Llama-3.1 8B and wiki.rrtn.org Llama 3.3 70B Instruct).

Weirdly those Llama models have an MIT license attached, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache accredited so perhaps MIT is OK?

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

Licensing aside, these distilled designs are interesting beasts.

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

Quantized variations are already starting to appear. So far I've tried simply 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 using the mix of Ollama, LLM and the llm-ollama plugin.

First I brought and ran the design using Ollama itself:

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

Once the model has been brought, LLM can talk to it as well. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.

I set up the plugin and ran it like this:

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

Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating mix. Let me consider how these 2 characters may engage in a funny situation.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're normally found in cooler climates, like icebergs or snowy locations. So, integrating these two into a tea space setting is currently an amusing image.

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

The Joke:

A pelican and a walrus choose to open a quaint little tea space together. The walrus, with its huge size, struggles to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to put saucers on the table, causing a few spills.

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

Explanation:

- Setup: and Walrus run a not likely tea room. Their sizes lead to comedic chaos.

• Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, asteroidsathome.net making it humorous while fitting the style.
  
  So yeah, the joke is horrible. But the procedure of getting there was such an interesting insight into how these brand-new designs work.
  
  This was a fairly little 8B design. I'm looking forward to trying out the Llama 70B version, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class design that I have actually operated on my own machine-I have high expectations.
  
  Update 21st January 2025: forum.pinoo.com.tr 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 bicycle prompt 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 offered me this:
  
  As with the earlier joke, the chain of believed in the transcript was much more interesting than completion outcome.
  
  Other methods to attempt DeepSeek-R1
  
  If you wish to attempt the model out without installing anything you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or offer a Chinese +86 phone number) and then select the "DeepThink" choice listed below the timely input box.
  
  DeepSeek offer the model via their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and it-viking.ch paste in your API key, then use llm -m deepseek-reasoner 'timely' to run prompts.
  
  This will not reveal you the thinking tokens, unfortunately. Those are served up by the API (example here) but LLM doesn't yet have a way to show them.