That design was trained in part using their unreleased R1 "reasoning" model. Today they've launched R1 itself, in addition to a whole household of new designs obtained from that base.
There's a whole lot of things 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 tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences difficulties such as limitless repeating, bad readability, and language blending." ... so they also launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and thinking jobs". That a person is also MIT accredited, and is a similar size.
I don't have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two 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 6 thick designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?
(I likewise just discovered 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 monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to reveal up. Up until now I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really enjoyable to play with.
I'm running it using the combination of Ollama, LLM and lespoetesbizarres.free.fr the llm-ollama plugin.
First I fetched and ran the design using Ollama itself:
This downloads around 8.5 GB of model information and begins an interactive chat interface.
Once the design has actually been fetched, LLM can speak with it too. I choose utilizing LLM for experiments because it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to help produce the reaction. For "a joke about a pelican and a walrus who run a tea room together" that began 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 an interesting mix. Let me think of how these two characters might interact in a funny situation.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're normally found in chillier climates, like icebergs or snowy locations. So, integrating these 2 into a tea space setting is already an amusing image.
[...]
It then believed 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 decide to open a quaint little tea room together. The walrus, with its huge size, struggles to find comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to put dishes on the table, triggering a few spills.
After a series of comical incidents, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "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 result in comedic turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less ridiculous. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the theme.
So yeah, the joke is terrible. But the process of getting there was such an interesting insight into how these brand-new designs work.
This was a fairly little 8B design. I'm looking 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 design that I've operated 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 effectively:
It aimed to me like it got the order of the components incorrect, 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 thought in the records was far more fascinating than the end outcome.
Other ways to try DeepSeek-R1
If you wish to try the model out without setting up anything at all you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or offer a Chinese +86 contact number) and after that choose the "DeepThink" alternative listed below the timely input box.
DeepSeek provide the model via their API, using an OpenAI-imitating endpoint. You can access that through 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 utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This will not show you the reasoning tokens, sadly. Those are provided by the API (example here) however LLM doesn't yet have a method to display them.