That design was trained in part using their unreleased R1 "reasoning" design. Today they've released R1 itself, together with a whole household of new models obtained from that base.
There's a lot of stuff in the brand-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 clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters difficulties such as endless repetition, bad readability, and language mixing." ... so they also launched:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout math, code, and reasoning jobs". That a person is likewise MIT certified, and is a comparable size.
I don't have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily play with myself. That's where the brand-new distilled models 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 upon 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 funsilo.date 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 designs are Apache licensed so maybe MIT is OK?
(I also just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a little 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 show up. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to play with.
I'm running it using 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 model information and begins an interactive chat interface.
Once the model has actually been fetched, LLM can talk to it also. I prefer using LLM for experiments due to the fact that it logs everything to SQLite for later exploration.
I set up the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of idea utilized to assist create the response. For "a joke about a pelican and a walrus who run a tea room together" that began like this:
Okay, asteroidsathome.net so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an intriguing combination. Let me believe about how these 2 characters may 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 huge teeth, thick fur, and they're generally discovered in chillier climates, 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 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 space together. The walrus, with its huge size, has a hard time to discover comfortable chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to position dishes on the table, triggering a few spills.
After a series of funny incidents, the walrus searches for and says with a grin, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea space. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less ridiculous. The follow-up joke presents "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 awful. But the procedure of getting there was such an interesting insight into how these brand-new designs work.
This was a fairly small 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 run on my own 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 tried my classic 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 components incorrect, 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 even more interesting than completion outcome.
Other methods to try DeepSeek-R1
If you desire to try the design out without installing anything you can do so utilizing chat.deepseek.com-you'll need to develop an account (check in with Google, utilize an email address or offer a Chinese +86 phone number) and then pick the "DeepThink" alternative below the timely input box.
DeepSeek offer the design by means of their API, utilizing an OpenAI-imitating endpoint. You can access that via 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 'timely' to run triggers.
This will not show you the thinking tokens, regretfully. Those are dished out by the API (example here) but LLM does not yet have a method to display them.