That model was trained in part using their unreleased R1 "reasoning" design. Today they've launched R1 itself, along with an entire household of brand-new models obtained from that base.
There's an entire lot of stuff in the brand-new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters obstacles such as limitless repeating, poor readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains efficiency equivalent to OpenAI-o1 across mathematics, code, and thinking tasks". That a person is also MIT accredited, and is a similar size.
I do not have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly play with myself. That's where the new distilled designs are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable 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 designs have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I likewise simply saw 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 variations are already starting to appear. Up until now I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.
I'm running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design data and begins an interactive chat user interface.
Once the model has been brought, LLM can talk to it too. I prefer using LLM for experiments due to the fact that it logs whatever to SQLite for mariskamast.net later expedition.
I installed the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to help 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 require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating combination. Let me think of how these two characters might connect in a funny circumstance.
First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're generally discovered in colder climates, like icebergs or snowy areas. So, combining these 2 into a tea space setting is currently an amusing image.
[...]
It then believed 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 room together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to place saucers on the table, triggering a couple of spills.
After a series of humorous accidents, the walrus searches for and says 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 comedic turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming 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 theme.
So yeah, the joke is awful. But the process of arriving was such an interesting insight into how these brand-new designs work.
This was a fairly little 8B model. I'm looking forward to experimenting with 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 design that I've operated 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 traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing extremely well:
It aimed to me like it got the order of the elements wrong, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and gave me this:
As with the earlier joke, the chain of believed in the records was even more interesting than the end outcome.
Other ways to attempt DeepSeek-R1
If you want to attempt the design out without setting up anything you can do so utilizing chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or supply a Chinese +86 phone number) and after that select the "DeepThink" alternative listed below the timely input box.
DeepSeek offer 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 'timely' to run triggers.
This will not show you the thinking tokens, regretfully. Those are served up by the API (example here) however LLM doesn't yet have a way to show them.
