That design was trained in part using their unreleased R1 "reasoning" design. Today they've launched R1 itself, in addition to a whole household of brand-new designs obtained from that base.
There's a lot of stuff in the 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 clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across obstacles such as endless repetition, bad readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across math, code, and thinking tasks". That one is likewise 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 2 designs are something I can easily have fun with myself. That's where the brand-new distilled models are available in.
To support the research community, we have open-sourced DeepSeek-R1-Zero, forum.batman.gainedge.org DeepSeek-R1, and 6 thick designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating 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 models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?
(I likewise just noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled designs are fascinating monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to reveal up. Up until now I've attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and library.kemu.ac.ke it's really fun to play with.
I'm running it using the mix of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of model information and begins an interactive chat interface.
Once the model has been brought, LLM can speak with it also. I prefer using LLM for experiments because it logs everything to SQLite for strikez.awardspace.info later exploration.
I installed the plugin and drapia.org ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of idea used to help generate the reaction. 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 room together. Hmm, that's a fascinating combination. Let me consider how these 2 characters might connect in a humorous situation.
First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically discovered in colder climates, like icebergs or snowy areas. So, integrating these two into a tea space setting is already an amusing image.
[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full 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 huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to position dishes on the table, triggering a few spills.
After a series of comical accidents, the walrus searches for and states with a smile, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and oke.zone Walrus run a not likely tea room. Their sizes lead to comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less unreasonable. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it humorous while fitting the style.
So yeah, the joke is horrible. But the process of arriving was such an interesting insight into how these new designs work.
This was a fairly little 8B model. I'm looking forward to trying 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 preferred GPT-4 class model that I have actually operated 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 bike timely too. It did refrain from doing effectively:
It aimed to me like it got the order of the components wrong, so I followed up with:
the background ended up covering the remainder of the image
It thought some more and offered me this:
Similar to the earlier joke, the chain of believed in the records was far more interesting than completion result.
Other methods to attempt DeepSeek-R1
If you desire to try the model out without setting up anything at all you can do so using chat.deepseek.com-you'll need to create an account (indication in with Google, use an email address or akropolistravel.com supply a Chinese +86 contact number) and then pick the "DeepThink" alternative below the timely input box.
DeepSeek use the design by means of their API, using 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 use llm -m deepseek-reasoner 'timely' to run triggers.
This won't reveal you the reasoning tokens, unfortunately. Those are provided by the API (example here) but LLM doesn't yet have a method to display them.
