Simon Willison s Weblog
That design was trained in part using their unreleased R1 "reasoning" design. Today they've released R1 itself, it-viking.ch along with a whole family of new models obtained from that base.
There's a great deal of things in the brand-new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as unlimited repetition, poor readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is likewise MIT certified, and is a similar size.
I don't have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.
To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating 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 models have an MIT license connected, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?
(I also simply saw the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need 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 beginning to appear. Up until now I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to play with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design data and starts an interactive chat interface.
Once the design has been brought, LLM can speak to it as well. I prefer using LLM for experiments since it logs everything to SQLite for forum.altaycoins.com later exploration.
I set up the plugin and ran it like this:
Each response begins with a ... pseudo-XML tag containing the chain of idea used to assist generate the response. 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 space together. Hmm, that's an interesting mix. Let me believe about how these two characters might communicate in an amusing situation.
First, let's consider their attributes. 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 generally found in colder environments, like icebergs or snowy locations. So, integrating these two into a tea room setting is currently an amusing 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 choose to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to put dishes on the table, causing a couple of spills.
After a series of humorous accidents, the walrus searches for and says with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "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 result in comedic mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less unreasonable. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and fraternityofshadows.com tea, making it funny while fitting the style.
So yeah, the joke is awful. But the procedure of arriving was such an interesting insight into how these brand-new designs work.
This was a fairly little 8B design. 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 preferred GPT-4 class model that I've worked 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 traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing extremely well:
It aimed to me like it got the order of the elements wrong, wiki.whenparked.com so I followed up with:
the background wound up covering the remainder of the image
It thought some more and prawattasao.awardspace.info provided me this:
As with the earlier joke, the chain of believed in the records was much more fascinating than the end outcome.
Other methods to attempt DeepSeek-R1
If you want to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (sign in with Google, use an or supply a Chinese +86 phone number) and then select the "DeepThink" alternative below the timely input box.
DeepSeek provide the model through their API, utilizing an OpenAI-imitating endpoint. You can access that by means of 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 deepseek-reasoner 'timely' to run triggers.
This will not reveal you the thinking tokens, regretfully. Those are served up by the API (example here) however LLM does not yet have a way to show them.
