That design was trained in part using their unreleased R1 "reasoning" design. Today they have actually launched R1 itself, together with an entire family of new models obtained from that base.

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

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

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT certified, and is a comparable size.

I do not have the ability 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 community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is an interesting flex! 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 connected, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?

(I also simply noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled models are fascinating monsters.

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

Quantized versions are currently starting to show up. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to have fun with.

I'm running it using 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 model data and begins an interactive chat user interface.

Once the design has actually been fetched, LLM can speak to it too. I prefer using LLM for experiments since it logs whatever to SQLite for later exploration.

I installed 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 started like this:

Okay, 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 consider how these two characters might engage in an amusing circumstance.

First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, akropolistravel.com and galgbtqhistoryproject.org they're generally found in cooler environments, like icebergs or snowy locations. So, combining these 2 into a tea room setting is currently a funny 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 decide to open a quaint little tea room together. The walrus, with its big size, struggles to discover comfy chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to put dishes on the table, causing a couple of spills.

After a series of comical mishaps, the walrus searches for and says with a grin, "This isn't so fishy anymore." The smirks and mentions, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes cause comical turmoil.

• Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.
  
  So yeah, the joke is dreadful. But the process of getting there was such an interesting insight into how these brand-new designs work.
  
  This was a fairly small 8B design. I'm eagerly anticipating 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 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 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 effectively:
  
  It aimed to me like it got the order of the elements wrong, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and offered me this:
  
  As with the earlier joke, the chain of believed in the transcript was even more intriguing than the end outcome.
  
  Other methods to try DeepSeek-R1
  
  If you wish to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll need to develop an account (sign in with Google, use an email address or provide a Chinese +86 telephone number) and then choose the "DeepThink" choice listed below the timely input box.
  
  DeepSeek offer the model via their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml configuration file:
  
  Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not reveal you the reasoning tokens, regretfully. Those are dished out by the API (example here) however LLM does not yet have a way to display them.