GitLab

That design was trained in part utilizing their unreleased R1 "thinking" 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 brand-new release.

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across difficulties such as limitless repetition, poor readability, and language blending." ... so they also released:

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

I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can easily 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 6 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is a fascinating flex! They have actually models based on Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and morphomics.science 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 works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?

(I likewise just observed the MIT license files say "Copyright (c) 2023 DeepSeek" so they might require to pay a 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 currently beginning to appear. So far I have actually attempted just 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 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 design has been brought, LLM can talk to it also. I prefer utilizing LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

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

Okay, bphomesteading.com so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's a fascinating mix. Let me think of how these 2 characters might communicate in a funny situation.

First, let's consider their attributes. Pelicans are known for their long beaks and library.kemu.ac.ke Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're usually discovered in cooler environments, like icebergs or snowy areas. So, combining these 2 into a tea space setting is already an amusing image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full 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, has a hard time to find comfy chairs, so it rests on the table by accident, overturning 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 incidents, the walrus searches for and says with a smile, "This isn't so fishy any longer." 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 room. Their sizes result in comical chaos.

• Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less ridiculous. The follow-up joke presents "krill," a play on words that ties into both ("fish") and tea, making it humorous while fitting the style.
  
  So yeah, the joke is dreadful. But the process of getting there was such an interesting insight into how these new designs work.
  
  This was a fairly small 8B model. I'm anticipating attempting 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 preferred GPT-4 class model that I have actually worked 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 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 aspects wrong, so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It believed some more and gave me this:
  
  Just like the earlier joke, the chain of thought in the records was much more intriguing than the end outcome.
  
  Other methods to attempt DeepSeek-R1
  
  If you desire to attempt the model out without setting up anything at all you can do so using chat.deepseek.com-you'll need to create an account (sign in with Google, use an email address or provide a Chinese +86 phone number) and after that select the "DeepThink" option listed below the prompt input box.
  
  DeepSeek use the design via their API, wiki.lafabriquedelalogistique.fr using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run triggers.
  
  This will not reveal you the reasoning tokens, regretfully. Those are dished out by the API (example here) however LLM doesn't yet have a method to display them.