Simon Willison s Weblog
That design was trained in part utilizing their unreleased R1 "thinking" design. Today they've released R1 itself, along with a whole family of brand-new designs obtained from that base.
There's a great deal of stuff 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, oke.zone is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences obstacles such as limitless repetition, poor readability, and language mixing." ... so they also launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 across math, code, and reasoning tasks". That one is likewise MIT certified, and is a comparable size.
I do not have the capability to run models 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 brand-new distilled designs are available in.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is an interesting flex! They have 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 connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?
(I likewise just 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 interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already beginning to reveal up. So far I have actually attempted simply one of 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 mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design information and starts an interactive chat user .
Once the design has actually been brought, LLM can speak to it too. I choose using LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.
I installed the plugin and ran it like this:
Each action begins with a ... pseudo-XML tag containing the chain of thought utilized to help create the action. For "a joke about a pelican and a walrus who run a tea room together" that began like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's a fascinating mix. Let me think about how these two characters might communicate in an amusing situation.
First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically discovered in colder climates, like icebergs or snowy locations. So, integrating these 2 into a tea space setting is currently a funny image.
[...]
It then believed 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 room together. The walrus, with its huge size, struggles to discover comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to put saucers on the table, triggering a few spills.
After a series of comical accidents, the walrus looks up and says with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea room. Their sizes cause comedic turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming less unreasonable. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and wiki.fablabbcn.org tea, making it funny while fitting the theme.
So yeah, the joke is terrible. But the process of getting there was such a fascinating insight into how these new models work.
This was a fairly little 8B model. I'm eagerly anticipating trying 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 design that I have actually run 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 classic 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 elements wrong, so I followed up with:
the background ended 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 transcript was far more intriguing than the end outcome.
Other methods to attempt DeepSeek-R1
If you wish to attempt the model out without setting up anything at all you can do so using chat.deepseek.com-you'll require to create an account (indication in with Google, use an email address or supply a Chinese +86 contact number) and then select the "DeepThink" alternative listed below the prompt input box.
DeepSeek provide the design via their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This won't show you the reasoning tokens, regretfully. Those are dished out by the API (example here) however LLM does not yet have a way to display them.
