That design was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually launched R1 itself, in addition to an entire household of new models obtained from that base.
There's a lot of stuff 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 alert that "DeepSeek-R1-Zero experiences challenges such as unlimited repeating, bad readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance similar to OpenAI-o1 across math, code, and reasoning jobs". That one is likewise MIT licensed, and is a comparable size.
I do not have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 are something I can easily have fun with myself. That's where the new distilled models are available in.
To support the research 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 fascinating flex! They have actually models based upon Qwen 2.5 (14B, 32B, Math 1.5 B and asteroidsathome.net Math 7B) and Llama 3 (Llama-3.1 8B and Llama 3.3 70B Instruct).
Weirdly those Llama designs have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so possibly MIT is OK?
(I likewise simply observed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already starting to appear. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to have fun with.
I'm running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of model information and begins an interactive chat interface.
Once the design has been fetched, LLM can talk with it also. I prefer utilizing LLM for experiments because it logs whatever 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 help 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 space together. Hmm, that's an interesting mix. Let me think about how these two characters might engage in an amusing situation.
First, let's consider their characteristics. Pelicans are understood for their long beaks and mediawiki.hcah.in Webbed feet, often seen near the beach or it-viking.ch water. Walruses have huge teeth, thick fur, and they're normally found in colder environments, like icebergs or snowy areas. So, combining these two into a tea space setting is already a funny image.
[...]
It then thought 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 choose to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to place saucers on the table, triggering a couple of spills.
After a series of humorous mishaps, the walrus looks up and states with a grin, "This isn't so fishy anymore." 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 result in comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming less unreasonable. 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 horrible. But the process of getting there was such an intriguing insight into how these new models work.
This was a fairly little 8B design. I'm looking forward to attempting out the Llama 70B variation, 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've 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 effectively:
It aimed to me like it got the order of the components incorrect, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and provided me this:
Just like the earlier joke, the chain of believed in the transcript was much more interesting than the end result.
Other methods to try DeepSeek-R1
If you desire to attempt the model out without setting up anything you can do so using chat.deepseek.com-you'll need to create an account (indication in with Google, use an email address or offer a Chinese +86 phone number) and after that select the "DeepThink" alternative listed below the timely input box.
DeepSeek provide the model by means of their API, utilizing 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 'timely' to run triggers.
This will not show you the reasoning tokens, regretfully. Those are served up by the API (example here) but LLM doesn't yet have a way to show them.