That model was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, in addition to a whole family of brand-new designs 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, like the majority of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences challenges such as limitless repetition, bad readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance comparable to OpenAI-o1 across math, code, and reasoning tasks". That one is also MIT licensed, and is a similar size.
I do not 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 play with myself. That's where the new distilled models are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable flex! They have actually designs 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 works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?
(I also simply saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently beginning to reveal up. So far I have actually attempted 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 combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the model using Ollama itself:
This downloads around 8.5 GB of design data and begins an interactive .
Once the design has actually been fetched, LLM can speak with it also. I prefer utilizing LLM for experiments since it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each action begins with a ... pseudo-XML tag containing the chain of thought used to assist produce the response. 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 a fascinating combination. Let me think about how these two characters may communicate in a humorous scenario.
First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally found in cooler climates, like icebergs or snowy locations. So, combining these two into a tea room setting is currently an amusing image.
[...]
It then thought for 20 paragraphs before outputting the joke! Here's the complete 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 huge size, struggles to find comfy chairs, bbarlock.com so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, causing a few spills.
After a series of comical mishaps, the walrus looks up and says with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less absurd. 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 theme.
So yeah, the joke is terrible. But the process of arriving was such an interesting insight into how these new designs work.
This was a fairly little 8B model. I'm anticipating attempting out 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 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 tried my traditional Generate an SVG of a pelican riding a bike prompt 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 thought some more and offered me this:
Similar to the earlier joke, the chain of thought in the records was far more interesting than completion outcome.
Other methods to attempt DeepSeek-R1
If you wish to try the design out without setting up anything you can do so using chat.deepseek.com-you'll need to produce an account (check in with Google, use an email address or supply a Chinese +86 telephone number) and then pick the "DeepThink" choice below the timely input box.
DeepSeek provide the design through their API, utilizing an OpenAI-imitating endpoint. You can access that via 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 utilize llm -m deepseek-reasoner 'timely' to run prompts.
This won't reveal you the reasoning tokens, unfortunately. Those are served up by the API (example here) however LLM does not yet have a method to display them.