That design was trained in part utilizing their unreleased R1 "thinking" model. Today they've released R1 itself, together with an entire family of brand-new models obtained from that base.
There's a lot of stuff in the brand-new release.
DeepSeek-R1-Zero appears to be the base model. 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 experiences challenges such as endless repetition, poor readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 across math, code, and reasoning jobs". That a person is likewise MIT certified, and is a comparable size.
I do not have the ability to run models 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 models are available in.
To support the research study neighborhood, 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 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 compatible with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?
(I likewise simply discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to appear. So far I've attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to have fun with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model using Ollama itself:
This downloads around 8.5 GB of model data and begins an interactive chat user interface.
Once the design has been brought, LLM can speak with it as well. I choose using LLM for experiments because it logs everything to SQLite for later expedition.
I set up the plugin and wiki.monnaie-libre.fr ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to help create the response. For "a joke about a pelican and a walrus who run a tea space 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 a fascinating combination. Let me consider how these two characters might engage in an amusing circumstance.
First, utahsyardsale.com let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're normally found in cooler climates, like icebergs or snowy locations. So, combining these 2 into a tea space setting is already a funny image.
[...]
It then thought 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 octomo.co.uk a walrus decide to open a quaint little tea room together. The walrus, with its big size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, pyra-handheld.com the pelican, attempting to help, utilizes its beak to position dishes on the table, triggering a few spills.
After a series of funny incidents, the walrus looks up and states with a smile, "This isn't so fishy any longer." The pelican smirks and says, "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 lead to comedic turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less ridiculous. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, wiki.monnaie-libre.fr making it funny while fitting the style.
So yeah, the joke is terrible. But the process of arriving was such an intriguing insight into how these 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 design that I've operated on my own machine-I have high expectations.
Update 21st January 2025: accc.rcec.sinica.edu.tw 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 traditional Generate an SVG of a pelican riding a bicycle timely 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 ended up covering the remainder of the image
It thought some more and gave me this:
Just like the earlier joke, the chain of believed in the transcript was much more interesting than the end outcome.
Other ways to try DeepSeek-R1
If you desire to try the model out without setting up anything at all you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, utilize an email address or offer a Chinese +86 telephone number) and then choose the "DeepThink" alternative listed below the timely 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 setup file:
Then run llm secrets set deepseek and paste in your API key, disgaeawiki.info then utilize llm -m deepseek-reasoner 'timely' to run prompts.
This won't show you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a method to display them.
