That model was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, together with a whole family of new models obtained from that base.
There's a lot of things in the brand-new release.
DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences challenges such as unlimited repeating, bad readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout mathematics, code, and thinking tasks". That a person is likewise 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 2 designs are something I can quickly play 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 6 thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is an interesting flex! They have actually designs based on 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 connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?
(I likewise simply noticed the MIT license files say "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 designs are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to reveal up. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to have fun with.
I'm running it using 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 design information and starts an interactive chat interface.
Once the design has been brought, LLM can talk 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 ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of thought used to help generate the action. For "a joke about a pelican and a walrus who run a tea room together" that began 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 mix. Let me consider how these two characters might interact in a humorous situation.
First, let's consider their attributes. 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 typically discovered in colder environments, like icebergs or snowy areas. So, combining these 2 into a tea space setting is currently a funny image.
[...]
It then thought 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 decide to open a quaint little tea space together. The walrus, wiki.snooze-hotelsoftware.de with its big size, has a hard time to discover comfy chairs, so it sits on the table by accident, the teapot. Meanwhile, the pelican, trying to help, uses its beak to position saucers on the table, causing a couple of spills.
After a series of funny accidents, the walrus searches for and says with a grin, "This isn't so fishy anymore." The pelican smirks and mediawiki.hcah.in says, "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 comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the theme.
So yeah, the joke is horrible. But the process of getting there was such a fascinating insight into how these new designs work.
This was a fairly small 8B design. I'm eagerly anticipating experimenting with the Llama 70B variation, 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 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 model 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 aspects incorrect, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and offered me this:
As with the earlier joke, the chain of thought in the transcript was even more interesting than completion result.
Other methods to try DeepSeek-R1
If you wish to attempt the design out without installing anything at all you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, utilize an email address or supply a Chinese +86 phone number) and after that choose the "DeepThink" alternative below the timely input box.
DeepSeek offer the model via their API, using an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
This won't show you the thinking tokens, unfortunately. Those are served up by the API (example here) but LLM does not yet have a method to show them.