Simon Willison's Weblog
That design was trained in part using their unreleased R1 "reasoning" design. Today they've released R1 itself, classifieds.ocala-news.com in addition to an entire household of new designs obtained from that base.
There's an entire lot of things in the brand-new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as endless repetition, poor readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance similar to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is also MIT licensed, classifieds.ocala-news.com and is a comparable 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 two 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 six thick designs distilled from DeepSeek-R1 based on Llama and 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 models have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I also simply noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may 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 starting to appear. So far I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to have fun with.
I'm running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the design using Ollama itself:
This downloads around 8.5 GB of model data and begins an interactive chat user interface.
Once the model has actually been brought, LLM can speak to it as well. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of thought utilized to help produce the action. For "a joke about a pelican and a walrus who run a tea room 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 a fascinating combination. Let me consider how these two characters might communicate in a funny 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 normally discovered in cooler environments, like icebergs or snowy areas. So, combining these two into a tea space setting is currently a funny image.
[...]
It then thought for 20 paragraphs before outputting the joke! Here's the full 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 big size, wifidb.science has a hard time to find comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to place dishes on the table, causing a couple of spills.
After a series of humorous accidents, the walrus looks up and says with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but 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 any longer" is a pun on the circumstance becoming less unreasonable. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the theme.
So yeah, the joke is terrible. But the procedure of getting there was such an intriguing insight into how these new designs work.
This was a fairly little 8B model. I'm eagerly anticipating attempting 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've 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 attempted my classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and offered me this:
Just like the earlier joke, the chain of thought in the transcript was far more intriguing than .
Other methods to attempt DeepSeek-R1
If you wish to try the model out without installing anything you can do so using chat.deepseek.com-you'll require to produce an account (sign in with Google, utilize an email address or supply a Chinese +86 phone number) and after that select the "DeepThink" alternative listed below the prompt input box.
DeepSeek provide 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 configuration file:
Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run triggers.
This will not reveal you the reasoning tokens, unfortunately. Those are dished out by the API (example here) but LLM doesn't yet have a way to display them.