GitLab

That design was trained in part using their unreleased R1 "reasoning" design. Today they have actually released R1 itself, along with an entire household of new designs obtained from that base.

There's an entire lot of stuff in the new release.

DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters obstacles such as endless repeating, poor readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That a person is also MIT accredited, and is a comparable size.

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

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

This is a remarkable 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 models have an MIT license connected, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?

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

Licensing aside, these distilled models are fascinating monsters.

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

Quantized versions are already beginning to appear. So far I have actually attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable 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 utilizing Ollama itself:

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

Once the model has actually been brought, LLM can talk to it as well. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for later exploration.

I installed the plugin and bphomesteading.com ran it like this:

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

Okay, setiathome.berkeley.edu so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating combination. Let me think of how these two characters may engage in a funny scenario.

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 big teeth, thick fur, and they're usually discovered in cooler environments, like icebergs or snowy locations. So, combining these two into a tea space setting is currently an amusing image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete 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 big size, struggles to discover comfortable chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, triggering a few spills.

After a series of humorous mishaps, the walrus searches for and states 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 an unlikely tea room. Their sizes cause comedic turmoil.

• Punchline: "This isn't so fishy any longer" is a pun on the situation becoming less ridiculous. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the style.
  
  So yeah, the joke is awful. But the process of getting there was such an interesting insight into how these brand-new models work.
  
  This was a fairly little 8B design. I'm anticipating attempting out the Llama 70B variation, 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: users.atw.hu 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 traditional Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the aspects wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It believed some more and provided me this:
  
  Just like the earlier joke, the chain of believed in the records was much more fascinating than the end result.
  
  Other ways to attempt DeepSeek-R1
  
  If you desire to attempt the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or provide a +86 telephone number) and then select the "DeepThink" choice listed below the prompt input box.
  
  DeepSeek use the model through their API, using an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
  
  This will not reveal you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM does not yet have a method to display them.