That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they've launched R1 itself, in addition to an entire family of new designs obtained from that base.
There's an entire lot of stuff in the new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across obstacles such as limitless repeating, poor readability, and language blending." ... so they also released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and reasoning jobs". That a person is also MIT accredited, and is a similar size.
I don't have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can easily play 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 6 thick models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating flex! They have designs based upon 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?
(I likewise simply saw the MIT license files state "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 beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to appear. So far I have actually tried 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 running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model using Ollama itself:
This downloads around 8.5 GB of design data and begins an interactive chat interface.
Once the model has been fetched, LLM can speak with it as well. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.
I installed the plugin and ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of idea utilized to assist produce the reaction. For "a joke about a pelican and a walrus who run a tea room together" that started 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 intriguing combination. Let me believe about how these two characters might engage in an amusing scenario.
First, let's consider their attributes. 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 discovered 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 a walrus decide to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfy chairs, akropolistravel.com so it sits on the table by mishap, overturning the teapot. Meanwhile, funsilo.date the pelican, attempting to assist, uses its beak to position saucers on the table, triggering a few spills.
After a series of funny incidents, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes result in comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less unreasonable. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, making it amusing while fitting the theme.
So yeah, the joke is awful. But the procedure of arriving was such an interesting insight into how these new designs work.
This was a fairly small 8B model. I'm trying 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 preferred GPT-4 class design 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 model 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 extremely well:
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 provided me this:
As with the earlier joke, the chain of thought in the transcript was far more interesting than the end result.
Other methods to attempt DeepSeek-R1
If you wish to try the model out without installing anything you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or provide a Chinese +86 phone number) and after that select the "DeepThink" alternative below the timely input box.
DeepSeek use the model 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 configuration file:
Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This won't reveal you the thinking tokens, sadly. Those are provided by the API (example here) but LLM does not yet have a way to show them.