That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually launched R1 itself, together with an entire family of brand-new designs obtained from that base.
There's a great deal of stuff in the brand-new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters obstacles such as limitless repeating, poor 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 thinking tasks". That one is also MIT accredited, and is a similar size.
I do not have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly play 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 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating flex! They have 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 connected, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?
(I also simply saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to appear. Up until now I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to have fun with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design data and utahsyardsale.com begins an interactive chat user interface.
Once the design has actually been brought, LLM can talk with it also. I choose utilizing LLM for experiments because it logs everything to SQLite for 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 utilized to help produce the action. For "a joke about a pelican and a walrus who run a tea room together" that began like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting combination. Let me believe about how these two characters might interact in an amusing situation.
First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're generally found in colder climates, like icebergs or snowy locations. 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 decide to open a quaint little tea space together. The walrus, with its huge size, struggles to find comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place dishes on the table, triggering a couple of spills.
After a series of comical mishaps, the walrus looks up and states with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "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 lead to comedic mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the style.
So yeah, the joke is horrible. But the process of getting there was such a fascinating insight into how these brand-new designs work.
This was a fairly small 8B design. I'm looking forward to trying out the Llama 70B variation, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class model that I've run 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 design working like this-a 34GB download:
Can it draw a pelican?
I attempted my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the aspects wrong, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and provided me this:
Similar to the earlier joke, the chain of believed in the records was even more intriguing than completion outcome.
Other methods to try DeepSeek-R1
If you want to attempt the model out without setting up anything at all you can do so using chat.deepseek.com-you'll require to produce an (indication in with Google, utilize an email address or provide a Chinese +86 phone number) and then pick the "DeepThink" option below the prompt input box.
DeepSeek use the design through their API, utilizing an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This won't show you the reasoning tokens, sadly. Those are dished out by the API (example here) however LLM does not yet have a way to display them.