That model was trained in part utilizing their unreleased R1 "thinking" design. Today they've launched R1 itself, along 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 appears to be the base design. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as unlimited repeating, bad readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That a person is also MIT licensed, and is a similar size.
I don't have the ability to run models larger 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 brand-new distilled models are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based upon Llama and systemcheck-wiki.de Qwen.
This is an interesting flex! They have actually models 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?
(I also just 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 remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to appear. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and wolvesbaneuo.com it's actually fun to have fun with.
I'm running it using 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 design data and begins an interactive chat user interface.
Once the design has been brought, LLM can talk with it too. I prefer utilizing LLM for experiments since it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each response begins with a ... tag containing the chain of thought used to assist produce the action. For "a joke about a pelican and a walrus who run a tea room together" that started like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, king-wifi.win that's an interesting combination. Let me think of how these 2 characters may interact in a humorous scenario.
First, let's consider their characteristics. Pelicans are understood for their long beaks and wiki.eqoarevival.com Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're generally found in cooler environments, like icebergs or snowy areas. So, combining these 2 into a tea room setting is currently a funny image.
[...]
It then believed 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 choose to open a quaint little tea space together. The walrus, with its big size, struggles to discover comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, causing a couple of spills.
After a series of funny mishaps, the walrus searches for and states with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes lead to comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the style.
So yeah, the joke is dreadful. But the process of arriving was such a fascinating insight into how these brand-new designs work.
This was a fairly small 8B model. I'm looking forward to 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 have actually operated 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 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 ended 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 fascinating than completion outcome.
Other methods to try DeepSeek-R1
If you wish to try the model out without installing anything you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or garagesale.es offer a Chinese +86 contact number) and then choose the "DeepThink" option listed below the prompt input box.
DeepSeek offer the model through their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml configuration file:
Then run llm keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This will not show you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM doesn't yet have a method to show them.