That design was trained in part using their unreleased R1 "thinking" model. Today they have actually released R1 itself, together with a whole family of new models obtained from that base.
There's a great deal of things in the new release.
DeepSeek-R1-Zero appears to be 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 unlimited repetition, poor readability, and language blending." ... so they also released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That one is also MIT accredited, and is a similar size.
I do not have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 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 6 dense models distilled from DeepSeek-R1 based on Llama and Qwen.
This is an interesting flex! They have models based on Qwen 2.5 (14B, oke.zone 32B, Math 1.5 B and Math 7B) and oke.zone 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 works with the underlying Llama license. Qwen models are Apache certified so maybe MIT is OK?
(I likewise simply saw the MIT license files say "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 beginning to reveal up. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to have fun with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and dokuwiki.stream ran the model using Ollama itself:
This downloads around 8.5 GB of model information and begins an interactive chat user interface.
Once the design has been brought, LLM can speak to it as well. I choose using LLM for experiments because it logs whatever to SQLite for later exploration.
I set up the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of idea utilized to assist generate the action. For "a joke about a pelican and a walrus who run a tea space together" that started like this:
Okay, astroberry.io so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting mix. Let me believe about how these 2 characters may connect in an amusing scenario.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally found in cooler environments, like icebergs or snowy locations. So, combining these two into a tea room setting is currently a funny image.
[...]
It then thought for 20 paragraphs before outputting the joke! Here's the complete records and here's the output at the end, after the tag:
The Joke:
A pelican and garagesale.es a walrus decide to open a quaint little tea room together. The walrus, with its big size, has a hard time to find comfy chairs, fraternityofshadows.com so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to place dishes on the table, a couple of spills.
After a series of comical accidents, the walrus searches for and says with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being 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 style.
So yeah, the joke is horrible. But the process of getting there was such an interesting insight into how these new models work.
This was a fairly little 8B design. I'm eagerly anticipating checking out 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 model that I have actually run on my own machine-I have high expectations.
Update 21st January 2025: 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 tried my timeless Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing really well:
It aimed to me like it got the order of the aspects incorrect, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and gave me this:
Just like the earlier joke, the chain of thought in the records was even more intriguing than the end outcome.
Other ways to try DeepSeek-R1
If you wish to attempt the design out without installing anything at all you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, utilize an email address or offer a Chinese +86 telephone number) and then pick the "DeepThink" choice listed below the timely input box.
DeepSeek provide the model 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 secrets set deepseek and paste in your API key, galgbtqhistoryproject.org then use llm -m deepseek-reasoner 'timely' to run prompts.
This will not reveal you the thinking tokens, regretfully. Those are dished out by the API (example here) but LLM doesn't yet have a way to show them.