That design was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, in addition to an entire household of brand-new models obtained from that base.
There's a whole lot of things in the brand-new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences challenges such as limitless repetition, bad readability, and language mixing." ... so they also released:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 across mathematics, code, and thinking jobs". That a person is likewise MIT licensed, and is a comparable 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 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 study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have models based on Qwen 2.5 (14B, 32B, Math 1.5 B and bphomesteading.com 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 is suitable with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?
(I likewise simply 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 designs are interesting beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already starting to appear. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really enjoyable to play with.
I'm running it utilizing the combination of Ollama, LLM and passfun.awardspace.us the llm-ollama plugin.
First I fetched and ran the model using Ollama itself:
This downloads around 8.5 GB of design information and starts an interactive chat user interface.
Once the design has actually been fetched, setiathome.berkeley.edu LLM can speak to it also. I prefer using LLM for experiments because it logs whatever to SQLite for later exploration.
I set up the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to help generate the response. For "a joke about a pelican and a walrus who run a tea space together" that started 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 an intriguing mix. Let me consider how these two characters may engage in an amusing scenario.
First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally found in chillier environments, like icebergs or snowy locations. So, integrating these 2 into a tea room setting is already a funny image.
[...]
It then thought 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 decide to open a quaint little tea space together. The walrus, with its huge 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, uses its beak to put saucers on the table, triggering a couple of spills.
After a series of humorous incidents, the walrus looks up and says with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and forum.altaycoins.com Walrus run a not likely tea space. Their sizes result in comedic mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it funny while fitting the style.
So yeah, the joke is terrible. But the process of arriving was such an interesting insight into how these brand-new models work.
This was a fairly small 8B design. I'm anticipating trying 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 model that I have actually run 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 model 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 really well:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and offered me this:
As with the earlier joke, the chain of thought in the transcript was much more interesting than the end result.
Other ways to attempt DeepSeek-R1
If you desire to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll need to produce an account (indication in with Google, use an email address or provide a Chinese +86 contact number) and after that select the "DeepThink" alternative below the timely input box.
DeepSeek use the design by means of 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 secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This will not reveal you the tokens, regretfully. Those are served up by the API (example here) however LLM doesn't yet have a method to show them.