GitLab

That design was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, together with a whole family of new designs obtained from that base.

There's a great deal of things in the new release.

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

DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across math, code, and reasoning tasks". That one is likewise MIT certified, 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 designs are something I can easily play with myself. That's where the new distilled designs are available in.

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

This is a remarkable flex! They have actually designs 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 connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?

(I also simply noticed the MIT license files say "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 beasts.

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

Quantized versions are currently starting to appear. So far I've attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to have fun with.

I'm running it using the mix of Ollama, LLM and the llm-ollama plugin.

First I fetched and ran the model utilizing Ollama itself:

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

Once the model has actually been fetched, LLM can talk to it too. I choose using LLM for because it logs whatever to SQLite for asteroidsathome.net later expedition.

I installed the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to help generate the action. For "a joke about a pelican and a walrus who run a tea space together" that started like this:

Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an intriguing mix. Let me think of 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, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally found in cooler environments, like icebergs or snowy areas. So, combining 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 complete transcript and passfun.awardspace.us 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 accident, overturning the teapot. Meanwhile, the pelican, trying to help, wiki.snooze-hotelsoftware.de utilizes its beak to position saucers on the table, triggering a few spills.

After a series of funny incidents, 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 a not likely tea space. Their sizes result in comical mayhem.

• Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less unreasonable. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it humorous while fitting the theme.
  
  So yeah, the joke is awful. But the process of getting there was such an interesting insight into how these brand-new designs work.
  
  This was a fairly little 8B model. I'm looking forward to 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 favourite GPT-4 class model that I have actually 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 tried 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 incorrect, forum.batman.gainedge.org so I followed up with:
  
  the background wound up covering the remainder of the image
  
  It thought some more and offered me this:
  
  Similar to the earlier joke, the chain of believed in the transcript was much more interesting than the end outcome.
  
  Other ways to try DeepSeek-R1
  
  If you want to try the design out without installing anything at all you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or provide a Chinese +86 telephone number) and then select the "DeepThink" option listed below the timely input box.
  
  DeepSeek provide the design through their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and paste in your API key, then use llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not reveal you the thinking tokens, sadly. Those are served up by the API (example here) but LLM doesn't yet have a method to display them.