That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they've launched R1 itself, in addition to a whole household of new designs obtained from that base.
There's an entire lot of stuff in the brand-new release.
DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as limitless repeating, poor readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance comparable to OpenAI-o1 throughout math, code, and reasoning tasks". That a person is also MIT accredited, and is a similar size.
I do not have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly have fun 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 6 dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is an interesting flex! They have 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 models have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?
(I likewise just observed the MIT license files state "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 beginning to reveal up. So far I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to play with.
I'm running it utilizing the mix 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 model information and gdprhub.eu begins an interactive chat user interface.
Once the model has actually been fetched, LLM can talk with it as well. I prefer utilizing LLM for experiments due to the fact that it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each reaction starts with a ... tag containing the chain of thought used to help produce the reaction. 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, oke.zone that's an interesting combination. Let me think about how these 2 characters may connect in an amusing circumstance.
First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically found in chillier environments, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is already a funny 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 space together. The walrus, with its huge size, struggles to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to assist, 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 anymore." The pelican smirks and remarks, "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 anymore" is a pun on the scenario ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it amusing while fitting the style.
So yeah, the joke is terrible. But the procedure of getting there was such an interesting insight into how these new models work.
This was a fairly small 8B design. I'm anticipating checking 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 have actually run 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 bicycle 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 thought some more and offered me this:
Just like the earlier joke, the chain of believed in the records was even more interesting than completion outcome.
Other methods to attempt DeepSeek-R1
If you wish to try the model out without installing anything at all you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or provide a Chinese +86 contact number) and then pick the "DeepThink" choice below the prompt input box.
DeepSeek use the design via their API, using an OpenAI-imitating endpoint. You can access that via 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 use llm -m deepseek-reasoner 'prompt' to run triggers.
This won't show you the thinking tokens, sadly. Those are dished out by the API (example here) however LLM doesn't yet have a way to display them.