That design was trained in part using their unreleased R1 "reasoning" 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 brand-new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, bbarlock.com like the majority of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters obstacles such as unlimited repeating, poor readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains efficiency similar to OpenAI-o1 across mathematics, code, and thinking jobs". That one is likewise MIT licensed, and is a comparable size.
I do not have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily have fun with myself. That's where the brand-new distilled designs 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 fascinating flex! They have actually models based on Qwen 2.5 (14B, yewiki.org 32B, Math 1.5 B and 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 is compatible with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?
(I likewise simply observed the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need to pay a little 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 variations are already starting to show up. Up until now I've tried simply 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 oke.zone begins an interactive chat user interface.
Once the model has actually been fetched, pl.velo.wiki LLM can speak to 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 reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to assist create the reaction. For "a joke about a pelican and a walrus who run a tea space together" that began like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, forum.pinoo.com.tr that's an intriguing combination. Let me consider how these 2 characters might interact in a funny scenario.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically found in colder climates, like icebergs or snowy locations. So, integrating these two into a tea room setting is already an amusing 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 choose to open a quaint little tea room together. The walrus, with its big size, struggles to find comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place dishes on the table, causing a few spills.
After a series of comical mishaps, wiki.whenparked.com the walrus looks up and says with a smile, "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 an unlikely tea space. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less unreasonable. 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 theme.
So yeah, the joke is dreadful. But the process of getting there was such an interesting insight into how these new designs work.
This was a fairly small 8B design. I'm eagerly anticipating trying 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 model working like this-a 34GB download:
Can it draw a pelican?
I tried my traditional Generate an SVG of a pelican riding a bicycle prompt 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 provided me this:
Similar to the earlier joke, the chain of believed in the records was much more intriguing than the end outcome.
Other methods to attempt 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 require to create an account (sign in with Google, utilize an email address or provide a Chinese +86 contact number) and after that choose the "DeepThink" choice below the prompt input box.
DeepSeek use the model through their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm keys set and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' 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 way to display them.