Simon Willison's Weblog
That model was trained in part utilizing their unreleased R1 "thinking" model. Today they have actually launched R1 itself, in addition to an entire household of brand-new designs obtained from that base.
There's a whole lot of stuff in the new .
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like the majority of their other releases, historydb.date is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters obstacles such as endless repeating, bad readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and reasoning tasks". That a person is likewise MIT licensed, and is a similar size.
I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly play with myself. That's where the new distilled models are available in.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a fascinating 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 designs have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?
(I likewise simply observed the MIT license files state "Copyright (c) 2023 DeepSeek" so they might require to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are interesting beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to show up. Up until now I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to have fun with.
I'm running it utilizing the mix 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 design data and begins an interactive chat user interface.
Once the design has been fetched, historydb.date LLM can speak with it as well. I prefer using LLM for experiments since it logs everything to SQLite for later exploration.
I set up the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to assist generate the action. For "a joke about a pelican and a walrus who run a tea room together" that started like this:
Okay, so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an interesting combination. Let me think of how these two characters may communicate in an amusing scenario.
First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally found in cooler climates, like icebergs or snowy locations. So, integrating 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 complete records 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 big size, has a hard time to discover comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, videochatforum.ro the pelican, trying to help, wiki.fablabbcn.org uses its beak to put saucers on the table, triggering a few spills.
After a series of humorous accidents, the walrus looks up and says with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it humorous while fitting the style.
So yeah, the joke is horrible. But the process of getting there was such an interesting insight into how these new models work.
This was a fairly little 8B model. I'm eagerly anticipating experimenting with 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 worked 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 design working like this-a 34GB download:
Can it draw a pelican?
I attempted my timeless Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing effectively:
It aimed to me like it got the order of the components wrong, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and gave me this:
As with the earlier joke, the chain of thought in the transcript was much more interesting than completion outcome.
Other ways to try DeepSeek-R1
If you wish to try the design out without installing anything you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or provide a Chinese +86 contact number) and after that choose the "DeepThink" alternative listed below the timely input box.
DeepSeek offer the model by means of 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 key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM does not yet have a method to show them.