That design was trained in part utilizing their unreleased R1 "thinking" model. Today they've released R1 itself, in addition to an entire household of brand-new designs obtained from that base.
There's a whole lot of stuff in the brand-new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across difficulties such as endless repetition, poor readability, and language blending." ... so they also released:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across math, code, and reasoning jobs". That a person is also MIT accredited, and is a similar size.
I do not have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily play with myself. That's where the new distilled models are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have actually models based on Qwen 2.5 (14B, lovewiki.faith 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 certified so perhaps MIT is OK?
(I also simply noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need 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 variations are already starting to show up. So far I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to have fun with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of design information and begins an interactive chat interface.
Once the model has actually been brought, LLM can talk with it too. 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 ... tag containing the chain of idea used to assist 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 a fascinating combination. Let me consider how these two characters might connect in an amusing scenario.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally found in chillier climates, like icebergs or snowy locations. So, combining these 2 into a tea space setting is already a funny image.
[...]
It then thought 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 choose to open a quaint little tea space together. The walrus, with its big size, struggles to discover comfortable chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place dishes on the table, triggering a few spills.
After a series of funny incidents, the walrus looks up 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 comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the theme.
So yeah, the joke is dreadful. But the procedure of arriving was such an intriguing insight into how these brand-new models work.
This was a fairly little 8B design. I'm looking forward to trying 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 model that I've run 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 bike prompt too. It did refrain from doing really well:
It aimed to me like it got the order of the elements wrong, king-wifi.win so I followed up with:
the background ended up covering the remainder of the image
It believed some more and provided me this:
Just like the earlier joke, the chain of thought in the records was far more intriguing than the end outcome.
Other methods to try DeepSeek-R1
If you wish to try the model out without installing 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 phone number) and then pick the "DeepThink" choice listed below the prompt input box.
DeepSeek provide the design via their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:
Then run llm secrets 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, sadly. Those are provided by the API (example here) but LLM doesn't yet have a method to display them.