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

There's a whole lot of things in the new release.

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

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That a person is also MIT accredited, and is a similar size.

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

To support the research community, we have open-sourced DeepSeek-R1-Zero, galgbtqhistoryproject.org DeepSeek-R1, and 6 dense designs 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 wiki.snooze-hotelsoftware.de Math 7B) and Llama 3 (Llama-3.1 8B and Llama 3.3 70B Instruct).

Weirdly those Llama designs have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?

(I also simply discovered the MIT license files state "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 designs are remarkable monsters.

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

Quantized variations are currently beginning to appear. So far I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to play with.

I'm running it utilizing 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 information and kenpoguy.com starts an interactive chat user interface.

Once the model has been brought, LLM can talk to it also. I prefer utilizing LLM for experiments since it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

Each response begins with a ... pseudo-XML tag containing the chain of idea used to help generate the action. For "a joke about a pelican and a walrus who run a tea room 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 an interesting combination. Let me believe about how these 2 characters might engage in an amusing circumstance.

First, disgaeawiki.info let's consider their attributes. Pelicans are understood for forum.altaycoins.com their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in cooler climates, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is already an amusing image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full 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 room together. The walrus, with its big size, has a hard time to find comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to position dishes on the table, causing a few spills.

After a series of humorous incidents, the walrus searches for and states with a smile, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, however 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 comedic mayhem.

• Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less ridiculous. 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 style.
  
  So yeah, the joke is awful. But the process of arriving was such an interesting insight into how these new designs work.
  
  This was a fairly small 8B model. I'm 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 have actually 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 timeless Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing very 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 thought some more and larsaluarna.se gave me this:
  
  As with the earlier joke, the chain of thought in the records was even more interesting than completion outcome.
  
  Other methods to try DeepSeek-R1
  
  If you desire to try the model out without installing anything you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, utilize an email address or provide a Chinese +86 contact number) and then choose the "DeepThink" alternative listed below the timely input box.
  
  DeepSeek offer the design via their API, utilizing 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 secret, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
  
  This won't show you the thinking tokens, regretfully. Those are dished out by the API (example here) but LLM does not yet have a way to display them.