That design was trained in part utilizing their unreleased R1 "thinking" model. Today they've released R1 itself, together with a whole household of new models obtained from that base.
There's a whole 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 warn that "DeepSeek-R1-Zero comes across obstacles such as endless repetition, poor readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and thinking tasks". That a person is also MIT accredited, and is a comparable size.
I don't have the capability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), forums.cgb.designknights.com so neither of these 2 designs are something I can easily play with myself. That's where the new distilled models are available in.
To support the research study neighborhood, 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 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 attached, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?
(I likewise simply discovered 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 designs are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to reveal up. Up until now I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to play with.
I'm running it using the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of design data and starts an interactive chat user interface.
Once the model has actually been fetched, LLM can talk with it too. I prefer using LLM for experiments due to the fact that 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 utilized to assist produce 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 room together. Hmm, that's an interesting combination. Let me consider how these two characters may connect in an amusing circumstance.
First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're usually found in chillier environments, like icebergs or snowy locations. 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 full transcript 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 room together. The walrus, with its big size, struggles to find comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to position saucers on the table, triggering a few spills.
After a series of funny incidents, the walrus looks up and says with a grin, "This isn't so fishy anymore." The pelican smirks and cadizpedia.wikanda.es remarks, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes result in comical turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less ridiculous. The follow-up joke presents "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 awful. But the process of arriving was such a fascinating insight into how these new models work.
This was a fairly small 8B design. I'm out 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 favourite GPT-4 class design that I've operated on my own machine-I have high expectations.
Update 21st January 2025: systemcheck-wiki.de 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 timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and offered me this:
Just like the earlier joke, the chain of thought in the transcript was much more intriguing than the end result.
Other methods to attempt DeepSeek-R1
If you want to try the model out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll need to develop an account (indication in with Google, use an email address or offer a Chinese +86 telephone number) and after that select the "DeepThink" choice below the prompt input box.
DeepSeek offer the design 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 configuration file:
Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run prompts.
This will not show you the reasoning tokens, unfortunately. Those are provided by the API (example here) but LLM doesn't yet have a method to display them.