That design was trained in part using their unreleased R1 "thinking" model. Today they've launched R1 itself, together with a whole family of new models obtained from that base.
There's a lot of things in the new release.
DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, sitiosecuador.com like many of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across difficulties such as limitless repetition, bad readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance comparable to OpenAI-o1 across mathematics, code, and thinking tasks". That a person is also MIT licensed, and is a similar size.
I don't have the capability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily have fun 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 dense 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 models have an MIT license connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?
(I likewise just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to reveal up. So far I've attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually 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 model using Ollama itself:
This downloads around 8.5 GB of model data and starts an interactive chat user interface.
Once the model has actually been fetched, LLM can speak to it as well. I choose utilizing LLM for experiments due to the fact that it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each response begins with a ... pseudo-XML tag containing the chain of thought used to assist create the response. 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 combination. Let me believe about how these two characters may engage in an amusing situation.
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 big teeth, thick fur, and they're typically found in cooler environments, like icebergs or snowy locations. So, combining 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 full 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 room together. The walrus, with its big size, has a hard time to find comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to place dishes on the table, triggering a couple of spills.
After a series of humorous mishaps, the walrus searches for and states with a smile, "This isn't so fishy any longer." 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 room. Their sizes cause comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less ridiculous. 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 arriving was such a into how these new models work.
This was a fairly little 8B model. I'm eagerly anticipating trying 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 preferred GPT-4 class model that I have actually 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 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 aspects 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 much more intriguing than completion result.
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 require to develop an account (indication in with Google, utilize an email address or offer a Chinese +86 contact number) and after that pick the "DeepThink" alternative listed below the timely 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 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 reveal you the thinking tokens, unfortunately. Those are provided by the API (example here) but LLM doesn't yet have a way to display them.