That design was trained in part using their unreleased R1 "thinking" model. Today they've launched R1 itself, together with an entire family of new designs obtained from that base.
There's a great deal of things in the brand-new release.
DeepSeek-R1-Zero appears to be 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 encounters obstacles such as unlimited repeating, bad readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and thinking jobs". That a person is likewise 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 models are something I can quickly 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, ura.cc DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is an interesting flex! They have models based upon Qwen 2.5 (14B, 32B, ura.cc 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 designs are so perhaps MIT is OK?
(I also just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they might require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to show up. So far I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to play with.
I'm running it using 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 model data and starts an interactive chat user interface.
Once the model has been fetched, LLM can speak with it as well. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for later exploration.
I installed the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to help produce the reaction. 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 combination. Let me believe about how these two characters may communicate in a funny situation.
First, let's consider their qualities. 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 generally discovered in cooler environments, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is currently an amusing image.
[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete records 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, has a hard time to discover comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to place saucers on the table, triggering a few spills.
After a series of funny accidents, the walrus searches for and says with a smile, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less unreasonable. The follow-up joke presents "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 awful. But the process of getting there was such an interesting insight into how these brand-new models work.
This was a fairly little 8B design. I'm eagerly anticipating experimenting with the Llama 70B variation, 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 run 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 design working like this-a 34GB download:
Can it draw a pelican?
I tried my traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing very well:
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 offered 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 wish to try the model out without setting up anything at all you can do so using chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or supply a Chinese +86 contact number) and then select the "DeepThink" choice below the prompt input box.
DeepSeek offer the design 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 secrets 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, sadly. Those are served up by the API (example here) however LLM does not yet have a method to show them.