That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, along with a whole 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 caution that "DeepSeek-R1-Zero encounters obstacles such as limitless repeating, poor readability, and language mixing." ... so they also released:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout math, code, and reasoning tasks". That one is likewise MIT licensed, and is a similar size.
I don't have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can quickly play with myself. That's where the new distilled models are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable flex! They have actually models 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 designs have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?
(I also simply saw the MIT license files say "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 monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to reveal up. Up until now I've attempted 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 using the combination 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 data and begins an interactive chat user interface.
Once the model has been fetched, LLM can speak to it too. I prefer utilizing LLM for experiments since it logs whatever to SQLite for later expedition.
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 create the action. 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 space together. Hmm, that's a fascinating mix. Let me think of how these 2 characters might connect in a funny circumstance.
First, let's consider their qualities. 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 discovered in cooler environments, like icebergs or snowy areas. So, combining these 2 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 space together. The walrus, with its big size, struggles to discover comfortable chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, pl.velo.wiki the pelican, attempting to help, uses its beak to put saucers on the table, triggering a couple of spills.
After a series of comical incidents, the walrus looks up and states with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less unreasonable. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the style.
So yeah, the joke is horrible. But the procedure of arriving was such an interesting insight into how these new models work.
This was a fairly little 8B model. I'm eagerly anticipating experimenting with the Llama 70B variation, which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class model that I have actually worked 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 design working like this-a 34GB download:
Can it draw a pelican?
I attempted my traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing very well:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and gave me this:
Similar to the earlier joke, the chain of thought in the transcript was even more interesting than the end outcome.
Other ways to attempt DeepSeek-R1
If you desire to attempt the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or provide a Chinese +86 telephone number) and after that select the "DeepThink" alternative below the timely input box.
DeepSeek offer the model via their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml configuration file:
Then run llm keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner to run triggers.
This won't reveal you the thinking tokens, sadly. Those are served up by the API (example here) but LLM does not yet have a way to display them.