That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually launched R1 itself, in addition to a whole family of new designs obtained from that base.
There's a whole lot of things in the new release.
DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as limitless repetition, bad readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance similar to OpenAI-o1 across math, code, and reasoning jobs". That one 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 2 models are something I can easily play with myself. That's where the brand-new distilled designs are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based on Llama and chessdatabase.science Qwen.
This is a remarkable 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 models are Apache licensed so perhaps MIT is OK?
(I likewise simply discovered 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 models are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to reveal up. Up until now I have actually tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to have fun with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of model information and starts an interactive chat interface.
Once the design has actually been brought, LLM can speak with it also. I prefer using LLM for experiments because it logs whatever to SQLite for later exploration.
I set up the plugin and wiki.lafabriquedelalogistique.fr ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of thought used to help create the reaction. 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 intriguing mix. Let me think of how these two characters might interact in a funny situation.
First, genbecle.com let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're usually found in cooler environments, like icebergs or snowy areas. So, integrating these two into a tea room setting is currently a funny image.
[...]
It then believed 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 decide to open a quaint little tea space together. The walrus, with its huge size, struggles to find comfy chairs, iuridictum.pecina.cz so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place saucers on the table, triggering a couple of spills.
After a series of funny mishaps, the walrus searches for and states with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes lead to comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.
So yeah, the joke is horrible. But the procedure of getting there was such an intriguing insight into how these new models work.
This was a fairly little 8B model. I'm anticipating trying 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 favourite GPT-4 class design that I've worked 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 traditional Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing very well:
It aimed to me like it got the order of the components wrong, so I followed up with:
the background ended up the remainder of the image
It believed some more and provided me this:
Similar to the earlier joke, the chain of thought in the records was far more intriguing than the end result.
Other methods to attempt DeepSeek-R1
If you desire to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to develop 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 prompt input box.
DeepSeek provide the design by means of their API, using an OpenAI-imitating endpoint. You can access that through 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 'prompt' to run prompts.
This won't show you the thinking tokens, sadly. Those are served up by the API (example here) however LLM doesn't yet have a method to display them.