That design was trained in part using their unreleased R1 "thinking" design. Today they have actually launched R1 itself, along with a whole family of brand-new models obtained from that base.
There's a lot of stuff 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 alert that "DeepSeek-R1-Zero comes across obstacles such as limitless repeating, bad readability, and language blending." ... so they also launched:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance comparable to OpenAI-o1 throughout math, code, and thinking tasks". That one is likewise MIT licensed, and is a comparable 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 play with myself. That's where the new designs are available in.
To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is an interesting flex! They have 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 models have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?
(I likewise just discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are currently starting to appear. So far I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really enjoyable to play with.
I'm running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the design using Ollama itself:
This downloads around 8.5 GB of model data and starts an interactive chat user interface.
Once the design has actually been brought, LLM can talk to it also. I prefer using LLM for experiments since it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each response starts with a ... pseudo-XML tag containing the chain of idea used to help produce the action. For "a joke about a pelican and a walrus who run a tea space together" that started 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 an intriguing combination. Let me think about how these two characters may communicate in a humorous 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 cooler environments, like icebergs or snowy areas. So, integrating these 2 into a tea room setting is currently a funny image.
[...]
It then thought 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, wiki-tb-service.com with its big size, has a hard time to discover comfortable chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place dishes on the table, triggering a couple of spills.
After a series of comical mishaps, the walrus searches for and says with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes cause comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less unreasonable. 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 procedure of getting there was such an interesting insight into how these brand-new models work.
This was a fairly little 8B design. I'm looking forward to experimenting with 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 model that I have actually operated 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 model working like this-a 34GB download:
Can it draw a pelican?
I tried my classic 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 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 believed in the records was even more fascinating than completion outcome.
Other methods to try DeepSeek-R1
If you desire to try the design out without installing anything you can do so utilizing chat.deepseek.com-you'll require to create an account (indication in with Google, utilize an email address or offer a Chinese +86 phone number) and after that pick the "DeepThink" alternative below the timely input box.
DeepSeek provide the design by means of their API, utilizing an OpenAI-imitating endpoint. You can access that via 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, regretfully. Those are served up by the API (example here) however LLM doesn't yet have a way to display them.