That design was trained in part using their unreleased R1 “thinking” model. Today they have actually released R1 itself, together with a whole household of brand-new models obtained from that base.

There’s a great deal of stuff in the brand-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 limitless repeating, bad readability, and language mixing.” ... so they also released:

DeepSeek-R1-which “includes cold-start information before RL” and “attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and reasoning tasks”. That a person is likewise MIT accredited, macphersonwiki.mywikis.wiki 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 two models are something I can easily have fun with myself. That’s where the brand-new distilled designs are available in.

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

This is a fascinating 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 models have an MIT license connected, which I’m uncertain is suitable with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?

(I also just noticed 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 fascinating beasts.

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

Quantized versions are already beginning to show up. So far I’ve attempted simply among 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 fetched and ran the model using Ollama itself:

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

Once the design has been fetched, LLM can talk with it too. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each action starts with a ... pseudo-XML tag containing the chain of idea utilized to assist produce the action. For “a joke about a pelican and a walrus who run a tea room together” that began 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 an intriguing combination. Let me consider how these 2 characters may interact in a humorous circumstance.

First, let’s consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they’re generally found in chillier environments, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is already an amusing image.

[...]
It then thought 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 choose 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, trying to assist, uses its beak to put saucers on the table, causing a few spills.

After a series of humorous accidents, disgaeawiki.info the walrus looks up and states with a grin, “This isn’t so fishy anymore.” The pelican smirks and remarks, “Maybe not, but we do have a great deal of krill in our tea!“

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comical turmoil.

• Punchline: “This isn’t so fishy anymore” is a pun on the circumstance ending up being less unreasonable. The follow-up joke introduces “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 awful. But the procedure of arriving was such an interesting insight into how these new models work.
  
  This was a fairly small 8B design. I’m eagerly anticipating attempting 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’ve run on my own machine-I have high expectations.
  
  Update 21st January 2025: I got this quantized variation of that Llama 3.3 70B R1 distilled model working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted 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 components wrong, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and gave me this:
  
  As with the earlier joke, the chain of believed in the transcript was far more fascinating than completion result.
  
  Other methods to try DeepSeek-R1
  
  If you desire to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you’ll need to develop an account (indication in with Google, utilize an email address or provide a Chinese +86 contact number) and then choose the “DeepThink” option listed below the timely input box.
  
  DeepSeek offer the model via their API, utilizing an OpenAI-imitating endpoint. You can access that via 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 ‘timely’ to run prompts.
  
  This will not reveal you the thinking tokens, sadly. Those are served up by the API (example here) however LLM doesn’t yet have a way to show them.