That model was trained in part using their unreleased R1 "thinking" design. Today they've launched R1 itself, along with an entire household of brand-new designs obtained from that base.
There's a great deal 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 caution that "DeepSeek-R1-Zero experiences obstacles such as unlimited repeating, bad readability, and language blending." ... so they also released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That a person is likewise MIT licensed, and is a comparable size.
I do not have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly have fun with myself. That's where the new distilled models are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable 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 models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so maybe MIT is OK?
(I likewise just discovered the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need to pay a little 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've attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly enjoyable 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 design utilizing Ollama itself:
This downloads around 8.5 GB of design data and starts an interactive chat user interface.
Once the design has actually been brought, LLM can speak to it also. I prefer using LLM for experiments since it logs whatever 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 thought used to assist create the response. For "a joke about a pelican and a walrus who run a tea space 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 combination. Let me believe about how these two characters might communicate in an amusing circumstance.
First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, disgaeawiki.info thick fur, and they're generally found in cooler climates, like icebergs or snowy locations. So, integrating these 2 into a tea space setting is already 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 oke.zone a walrus decide to open a quaint little tea space together. The walrus, with its big size, struggles to find comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to position saucers on the table, causing a couple of spills.
After a series of humorous incidents, the walrus looks up and states with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, however 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 turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less unreasonable. The follow-up joke presents "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 procedure of getting there was such an intriguing insight into how these brand-new models work.
This was a fairly small 8B model. I'm anticipating attempting out 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 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 tried my traditional Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the elements wrong, so I followed up with:
the background ended up covering the remainder of the image
It thought some more and archmageriseswiki.com gave me this:
Just like the earlier joke, the chain of thought in the transcript was even more fascinating than completion result.
Other ways to attempt DeepSeek-R1
If you wish to try the design out without setting up anything at all you can do so using chat.deepseek.com-you'll require to produce an account (sign in with Google, utilize an email address or supply a Chinese +86 contact number) and after that pick the "DeepThink" option listed below the timely input box.
DeepSeek offer the model by means of their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. file:
Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the reasoning tokens, unfortunately. Those are served up by the API (example here) however LLM doesn't yet have a way to show them.