That model was trained in part using their unreleased R1 "thinking" design. Today they've launched R1 itself, together with a whole household of brand-new models obtained from that base.
There's a lot of stuff in the brand-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 clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters obstacles such as unlimited repeating, poor readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and thinking tasks". That a person is also MIT certified, and is a similar size.
I don't have the capability to run models larger 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 new distilled designs are available in.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and asteroidsathome.net 6 thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is an interesting 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 genbecle.com Llama 3.3 70B Instruct).
Weirdly those Llama designs have an MIT license connected, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache licensed so possibly MIT is OK?
(I likewise just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they might require 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 currently starting to appear. So far I have actually tried simply among 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 wiki.monnaie-libre.fr the llm-ollama plugin.
First I brought and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of model information and wiki.rrtn.org begins an interactive chat interface.
Once the design has been fetched, LLM can talk with it too. I prefer using LLM for experiments because it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to assist create the action. For "a joke about a pelican and a walrus who run a tea space together" that began like this:
Okay, so I need 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 think of how these two characters might engage in a funny scenario.
First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're usually found in chillier climates, like icebergs or snowy locations. So, integrating these 2 into a tea room 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 choose to open a quaint little tea space together. The walrus, with its big size, struggles to discover comfy chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to put dishes on the table, causing a few spills.
After a series of funny incidents, the walrus looks up and says with a smile, "This isn't so fishy anymore." 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 result in comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and higgledy-piggledy.xyz tea, making it funny while fitting the style.
So yeah, the joke is dreadful. But the procedure of getting there was such a fascinating insight into how these brand-new designs work.
This was a fairly small 8B design. I'm looking forward to 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 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 attempted my classic Generate an SVG of a pelican riding a bike timely too. It did refrain from doing effectively:
It aimed to me like it got the order of the aspects wrong, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and provided me this:
Similar to the earlier joke, the chain of thought in the records was far more interesting than the end result.
Other ways to attempt DeepSeek-R1
If you wish to attempt the design out without setting up anything you can do so using chat.deepseek.com-you'll require to produce an account (sign in with Google, use an email address or offer a Chinese +86 phone number) and after that pick the "DeepThink" option listed below the timely input box.
DeepSeek use the design through their API, gratisafhalen.be 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 deepseek and paste in your API key, then -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the reasoning tokens, sadly. Those are provided by the API (example here) however LLM doesn't yet have a way to display them.