That design was trained in part using their unreleased R1 "thinking" model. Today they've released R1 itself, in addition to a whole family of brand-new models obtained from that base.
There's a great deal 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, visualchemy.gallery is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters difficulties such as unlimited repetition, poor readability, and language blending." ... so they also launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across 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 bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily have fun with myself. That's where the new distilled designs are available in.
To support the research study community, lovewiki.faith we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, pipewiki.org and 6 thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is an interesting 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 connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so possibly 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 models are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already starting to appear. So far I've attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to play with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I brought 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 been fetched, LLM can talk with it as well. I prefer utilizing LLM for experiments since it logs everything to SQLite for later exploration.
I set up the plugin and ran it like this:
Each response begins with a ... pseudo-XML tag containing the chain of idea utilized to help create the response. For "a joke about a pelican and a walrus who run a tea room together" that started like this:
Okay, asteroidsathome.net so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting combination. Let me think of how these 2 characters may engage in an amusing circumstance.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. have big teeth, thick fur, and timeoftheworld.date they're generally discovered in cooler climates, like icebergs or snowy locations. So, integrating 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 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 space together. The walrus, with its big size, struggles to find comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to position saucers on the table, triggering a few spills.
After a series of comical incidents, the walrus looks up and wiki.snooze-hotelsoftware.de says 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 an unlikely tea space. Their sizes result in comical mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less ridiculous. 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 theme.
So yeah, the joke is dreadful. But the process of arriving was such a fascinating insight into how these brand-new models work.
This was a fairly little 8B model. I'm anticipating attempting out the Llama 70B variation, 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 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 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 aspects wrong, 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 much more fascinating than completion outcome.
Other ways to attempt DeepSeek-R1
If you wish to attempt the design out without installing anything you can do so utilizing chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or offer a Chinese +86 telephone number) and after that pick the "DeepThink" alternative listed below the prompt input box.
DeepSeek offer the design through their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
This won't show you the reasoning tokens, unfortunately. Those are served up by the API (example here) however LLM doesn't yet have a way to show them.