That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually launched R1 itself, along with an entire household of new designs obtained from that base.
There's a great deal of stuff in the brand-new release.
DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, wiki.vst.hs-furtwangen.de like most of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences challenges such as limitless repetition, bad readability, and language blending." ... so they also launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and reasoning tasks". That one is likewise MIT licensed, and is a similar size.
I do not have the ability 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 models are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based on Llama and online-learning-initiative.org Qwen.
This is a remarkable flex! They have designs based on Qwen 2.5 (14B, gratisafhalen.be 32B, Math 1.5 B and Math 7B) and Llama 3 (Llama-3.1 8B and Llama 3.3 70B Instruct).
Weirdly those Llama models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?
(I likewise just saw the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are fascinating monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to appear. So far I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly enjoyable to play with.
I'm it using the mix 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 model data and begins an interactive chat user interface.
Once the model has been brought, LLM can speak with it too. I prefer 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 starts with a ... pseudo-XML tag containing the chain of thought used to help produce the action. 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 believe about how these two characters may connect in a funny scenario.
First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're normally discovered in cooler climates, like icebergs or snowy areas. So, combining these two into a tea space setting is currently an amusing image.
[...]
It then believed 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 a walrus choose to open a quaint little tea room together. The walrus, with its big size, has a hard time to find comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, wiki.snooze-hotelsoftware.de uses its beak to position dishes on the table, causing a couple of spills.
After a series of funny accidents, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and remarks, "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 cause 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 ties into both marine life ("fish") and tea, making it amusing while fitting the style.
So yeah, the joke is dreadful. But the procedure of arriving was such an interesting insight into how these new models work.
This was a fairly little 8B model. I'm anticipating checking out 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 favourite GPT-4 class design that I've worked 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 attempted my traditional Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing effectively:
It aimed to me like it got the order of the aspects wrong, 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, galgbtqhistoryproject.org the chain of thought in the transcript was far more interesting than completion outcome.
Other ways to attempt DeepSeek-R1
If you desire to attempt the model out without installing anything you can do so utilizing chat.deepseek.com-you'll require to produce an account (check in with Google, utilize an email address or provide a Chinese +86 phone number) and after that select the "DeepThink" option listed below the prompt input box.
DeepSeek offer the design via 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 secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
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.