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 household of brand-new designs 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 most of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters challenges such as unlimited 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 thinking tasks". That one is also MIT accredited, and is a similar size.


I do not have the capability 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 quickly 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 dense 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 wiki.rolandradio.net 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 models are Apache accredited so maybe MIT is OK?


(I likewise simply discovered 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 designs are remarkable beasts.


Running DeepSeek-R1-Distill-Llama-8B-GGUF


Quantized versions are already beginning to reveal up. So far I've tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to play with.


I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.


First I brought and ran the design utilizing Ollama itself:


This downloads around 8.5 GB of model information and starts an interactive chat interface.


Once the model has been fetched, LLM can speak with it as well. I prefer using LLM for experiments because 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 thought utilized to assist produce 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 space together. Hmm, that's an intriguing combination. Let me think about how these two characters may communicate in a funny circumstance.


First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally discovered in chillier environments, like icebergs or snowy areas. 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 transcript and here's the output at the end, after the tag:


The Joke:


A pelican and a walrus decide to open a quaint little tea room together. The walrus, with its huge size, struggles to find comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position dishes on the table, causing a few spills.


After a series of humorous incidents, the walrus looks up and states with a grin, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, but we do have a great deal of krill in our tea!"


Explanation:


- Setup: Pelican and Walrus run an unlikely tea room. Their sizes result in comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less absurd. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, making it amusing while fitting the style.


So yeah, the joke is awful. But the process of getting there was such a fascinating insight into how these brand-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 run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design that I've 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 tried my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing really well:


It aimed to me like it got the order of the aspects wrong, so I followed up with:


the background ended up covering the remainder of the image


It thought some more and provided me this:


Just like the earlier joke, the chain of thought in the transcript was much more interesting than the end result.


Other ways to attempt DeepSeek-R1


If you wish to try the model out without installing anything at all you can do so using chat.deepseek.com-you'll require to produce an account (sign in with Google, utilize an email address or offer a Chinese +86 telephone number) and after that pick the "DeepThink" alternative listed below the prompt input box.


DeepSeek use the design 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 secret, then use llm -m 'timely' to run prompts.


This won't reveal you the reasoning tokens, sadly. Those are served up by the API (example here) however LLM does not yet have a method to display them.