Simon Willison's Weblog
That design was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually released R1 itself, in addition to a whole family of brand-new designs 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 tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters obstacles such as endless repetition, bad readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and thinking tasks". That a person is also MIT accredited, and is a comparable size.
I don't have the ability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily play with myself. That's where the brand-new distilled models are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and forum.pinoo.com.tr six dense models distilled from DeepSeek-R1 based on Llama and forum.kepri.bawaslu.go.id Qwen.
This is a fascinating flex! They have actually designs 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 attached, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?
(I likewise just 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 designs are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already starting to reveal up. Up until now I've tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to have fun with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the model using Ollama itself:
This downloads around 8.5 GB of design data and begins an interactive chat user interface.
Once the model has actually been brought, LLM can talk 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 galgbtqhistoryproject.org ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of idea used to help produce the response. For "a joke about a pelican and a walrus who run a tea space together" that started like this:
Okay, so I need 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 2 characters may connect in an amusing scenario.
First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, oke.zone often seen near the beach or water. Walruses have big teeth, thick fur, and they're generally found in colder environments, like icebergs or snowy areas. So, integrating these two into a tea room setting is currently an amusing 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 a walrus choose to open a quaint little tea space together. The walrus, disgaeawiki.info with its huge size, has a hard time to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to put dishes on the table, causing a couple of spills.
After a series of funny accidents, the walrus searches for and says with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming less unreasonable. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and users.atw.hu tea, making it amusing while fitting the style.
So yeah, the joke is dreadful. But the process of arriving was such an intriguing insight into how these new designs work.
This was a fairly little 8B model. I'm looking forward to checking out the Llama 70B variation, 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 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 design 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 elements wrong, so I followed up with:
the background wound 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 transcript was far more interesting than the end outcome.
Other ways to try DeepSeek-R1
If you wish to try the model out without setting up anything you can do so utilizing chat.deepseek.com-you'll need to create an account (check in with Google, utilize an email address or supply a Chinese +86 phone number) and then choose the "DeepThink" alternative listed below the timely input box.
DeepSeek use the design by means of their API, using an OpenAI-imitating endpoint. You can access that through 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 utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the reasoning tokens, regretfully. Those are provided by the API (example here) however LLM doesn't yet have a way to display them.