That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually launched R1 itself, along with a whole family of new models obtained from that base.
There's an entire lot of things in the new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, lespoetesbizarres.free.fr like many of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across difficulties such as limitless repeating, poor readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and thinking tasks". That a person is also 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 two models are something I can easily play with myself. That's where the brand-new distilled models are available in.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating flex! They have actually models based upon 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 maybe MIT is OK?
(I also simply discovered 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 beginning to show up. Up until now I've attempted 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 utilizing the mix 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 with it too. I choose utilizing LLM for experiments due to the fact that it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each response begins with a ... pseudo-XML tag containing the chain of idea used to help produce the action. For "a joke about a pelican and a walrus who run a tea space together" that began 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 about how these two characters might in a humorous circumstance.
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 usually found in cooler climates, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is currently an amusing image.
[...]
It then thought 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 decide to open a quaint little tea space together. The walrus, with its huge size, struggles to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position saucers on the table, triggering a few spills.
After a series of funny incidents, the walrus searches for and states with a smile, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less unreasonable. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it amusing while fitting the theme.
So yeah, the joke is awful. But the procedure of getting there was such an intriguing insight into how these brand-new models work.
This was a fairly little 8B design. I'm anticipating experimenting with 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 model 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 design working like this-a 34GB download:
Can it draw a pelican?
I tried my traditional Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing effectively:
It aimed to me like it got the order of the components wrong, so I followed up with:
the background wound 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 methods to try DeepSeek-R1
If you want to attempt the model out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll need to create an account (sign in with Google, use an email address or provide a Chinese +86 phone number) and then pick the "DeepThink" choice listed below the prompt input box.
DeepSeek use the design through 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 won't reveal you the reasoning tokens, regretfully. Those are dished out by the API (example here) but LLM doesn't yet have a way to show them.