That model was trained in part utilizing their unreleased R1 "thinking" design. Today they've launched R1 itself, along with an entire household of brand-new designs obtained from that base.
There's a lot of things in the new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters challenges such as limitless repetition, bad readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That one is also MIT certified, and is a similar size.
I do not have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly play with myself. That's where the brand-new distilled models are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a fascinating flex! They have 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 suitable with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I likewise simply discovered the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to appear. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to play with.
I'm running it using the mix of Ollama, LLM and the .
First I fetched and ran the model using Ollama itself:
This downloads around 8.5 GB of model information and starts an interactive chat user interface.
Once the model has actually been fetched, LLM can speak with it too. I prefer using LLM for experiments because 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 idea utilized to assist 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 require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an intriguing combination. Let me think about how these two characters might connect in a humorous scenario.
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 big teeth, thick fur, and they're usually found in colder environments, like icebergs or snowy locations. So, integrating these two into a tea room 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, 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, has a hard time to find comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position dishes on the table, triggering a couple of spills.
After a series of comical accidents, the walrus searches for gratisafhalen.be and states with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea space. Their sizes result in comical turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being 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 style.
So yeah, the joke is terrible. But the process of arriving was such a fascinating insight into how these new models work.
This was a fairly little 8B design. I'm anticipating trying the Llama 70B version, 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 variation of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:
Can it draw a pelican?
I attempted my classic Generate an SVG of a pelican riding a bike timely too. It did refrain from doing effectively:
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 believed in the records was even more interesting than completion result.
Other methods to try DeepSeek-R1
If you desire to attempt the design out without setting up anything you can do so utilizing chat.deepseek.com-you'll need to produce an account (check in with Google, use an email address or provide a Chinese +86 phone number) and then pick the "DeepThink" choice listed below the timely input box.
DeepSeek provide the design via 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 secrets set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run triggers.
This will not show you the reasoning tokens, sadly. Those are served up by the API (example here) but LLM does not yet have a way to show them.