That model was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually released R1 itself, together with an entire household 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 the majority of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as limitless repeating, bad readability, and language blending." ... so they also released:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That a person is also MIT certified, and is a similar size.

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

To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, archmageriseswiki.com and 6 dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is an interesting flex! They have actually 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 compatible with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?

(I likewise just saw 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 remarkable monsters.

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

Quantized versions are already starting to reveal up. Up until now I've attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to have fun with.

I'm running it using the combination 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 model information and starts an interactive chat interface.

Once the model has been brought, LLM can talk to it also. I prefer using LLM for experiments because it logs whatever 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 thought utilized to assist create the response. For "a joke about a pelican and a walrus who run a tea space together" that began like this:

Okay, wolvesbaneuo.com so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting mix. Let me think of how these two characters might connect in a funny scenario.

First, let's consider their attributes. Pelicans are known for gratisafhalen.be their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're usually found in cooler climates, 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 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 huge size, struggles to discover comfortable chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to on the table, causing a couple of spills.

After a series of funny accidents, the walrus searches for and says with a smile, "This isn't so fishy anymore." The pelican smirks and historydb.date says, "Maybe not, however we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes result in comical chaos.

• Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less absurd. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the style.
  
  So yeah, the joke is terrible. But the procedure of getting there was such an interesting insight into how these new models work.
  
  This was a fairly little 8B design. I'm anticipating 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 preferred GPT-4 class model 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 model working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I tried my timeless 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 believed some more and provided me this:
  
  As with the earlier joke, the chain of believed in the transcript was far more interesting than the end outcome.
  
  Other ways to attempt DeepSeek-R1
  
  If you want to try the model out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or supply a Chinese +86 contact number) and after that pick the "DeepThink" choice listed below the timely input box.
  
  DeepSeek offer the model through their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm secrets set deepseek and paste in your API key, then use llm -m deepseek-reasoner 'prompt' to run triggers.
  
  This will not show you the reasoning tokens, unfortunately. Those are served up by the API (example here) however LLM doesn't yet have a way to display them.