That design was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, along with an entire household of new designs obtained from that base.
There's an entire lot of stuff in the 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 clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as limitless repeating, poor readability, and language mixing." ... so they also released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 throughout math, code, and thinking tasks". That a person is likewise MIT certified, and is a similar size.
I don't have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can quickly have fun with myself. That's where the new distilled designs are available in.
To support the research community, it-viking.ch 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 models based on Qwen 2.5 (14B, qoocle.com 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 attached, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache accredited so possibly MIT is OK?
(I likewise just saw 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 beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to show up. So far I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly 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 model using Ollama itself:
This downloads around 8.5 GB of model information and begins an interactive chat user interface.
Once the model has actually been brought, LLM can talk to it too. I prefer using LLM for experiments since it logs whatever to SQLite for later expedition.
I installed the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of thought used to help create 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 room together. Hmm, that's an interesting mix. Let me think of how these two characters may connect in an amusing scenario.
First, lespoetesbizarres.free.fr 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 typically discovered in cooler environments, wiki.insidertoday.org like icebergs or snowy areas. So, bbarlock.com integrating these 2 into a tea space setting is currently a funny image.
[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full transcript and here's the output at the end, asteroidsathome.net 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 comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put saucers on the table, triggering a couple of spills.
After a series of comical accidents, the walrus searches for and says with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less absurd. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, making it funny while fitting the theme.
So yeah, the joke is awful. But the procedure of getting there was such a fascinating insight into how these new designs work.
This was a fairly small 8B model. I'm eagerly anticipating checking 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 operated 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 attempted my classic Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing extremely well:
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 provided me this:
Just like the earlier joke, the chain of thought in the transcript was far more fascinating than the end result.
Other methods to attempt DeepSeek-R1
If you wish to attempt the model out without setting up anything you can do so utilizing chat.deepseek.com-you'll need to produce an account (indication in with Google, utilize an email address or offer a Chinese +86 contact number) and then select the "DeepThink" alternative below the timely input box.
DeepSeek provide 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 setup file:
Then run llm keys set deepseek and paste in your API key, then use llm -m deepseek-reasoner 'prompt' to run .
This will not reveal you the reasoning tokens, sadly. Those are served up by the API (example here) but LLM does not yet have a way to display them.