GitLab

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

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

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across challenges such as unlimited repetition, bad readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency similar to OpenAI-o1 throughout mathematics, code, and thinking tasks". That a person is also MIT licensed, and is a similar size.

I do not have the ability 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 quickly play with myself. That's where the brand-new distilled models 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 upon Llama and Qwen.

This is a ! They have actually models based on 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 attached, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?

(I likewise just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require 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 currently beginning to reveal up. So far I have actually tried simply one of 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 utilizing 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 design data and starts an interactive chat interface.

Once the model has been fetched, LLM can talk with it too. I prefer 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 reaction starts with a ... pseudo-XML tag containing the chain of thought used to help produce the response. For "a joke about a pelican and a walrus who run a tea space together" that started like this:

Okay, 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 consider how these two characters may communicate in an amusing situation.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally discovered in colder climates, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is already a funny image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete 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 big size, struggles to find comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place dishes on the table, triggering a few spills.

After a series of comical mishaps, the walrus searches for 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: Pelican and Walrus run an unlikely tea room. Their sizes result in comedic mayhem.

• Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the theme.
  
  So yeah, the joke is horrible. But the process of arriving was such an interesting insight into how these brand-new models work.
  
  This was a fairly little 8B model. I'm eagerly anticipating trying out the Llama 70B variation, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design 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 design working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted my classic Generate an SVG of a pelican riding a bike timely too. It did refrain from doing extremely well:
  
  It aimed to me like it got the order of the aspects incorrect, historydb.date 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 believed in the transcript was even more interesting than completion result.
  
  Other ways to attempt DeepSeek-R1
  
  If you wish to attempt the design out without setting up anything you can do so using chat.deepseek.com-you'll require to develop an account (indication in with Google, use an email address or supply a Chinese +86 telephone number) and then select the "DeepThink" alternative below the timely input box.
  
  DeepSeek provide 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 setup file:
  
  Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
  
  This won't reveal you the thinking tokens, sadly. Those are dished out by the API (example here) however LLM doesn't yet have a method to display them.