That design was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually launched R1 itself, along with a whole family of brand-new designs obtained from that base.
There's a great deal of stuff 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 alert that "DeepSeek-R1-Zero comes across challenges such as limitless repeating, bad readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout math, code, and reasoning tasks". That one is also MIT certified, and is a comparable size.
I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily play with myself. That's where the brand-new distilled designs 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 actually 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so possibly MIT is OK?
(I likewise simply saw 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 interesting beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are currently starting to appear. So far I've attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to play with.
I'm running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and tandme.co.uk ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design information and starts an interactive chat interface.
Once the model has actually been brought, ai-db.science LLM can talk to it also. I choose using LLM for experiments due to the fact that it logs whatever to SQLite for later exploration.
I installed the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of thought utilized to help generate the reaction. For "a joke about a pelican and a walrus who run a tea room together" that started like this:
Okay, so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's a fascinating mix. Let me think of how these 2 characters may connect in a funny situation.
First, let's consider their attributes. Pelicans are known 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 cooler climates, wiki.snooze-hotelsoftware.de like icebergs or snowy locations. So, integrating these two into a tea room setting is currently a funny 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 decide to open a quaint little tea space together. The walrus, with its big size, has a hard time to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place dishes on the table, causing a couple of spills.
After a series of humorous incidents, the walrus searches for 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 cause comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less ridiculous. The follow-up joke presents "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 awful. But the procedure of arriving was such an intriguing insight into how these designs work.
This was a fairly little 8B design. I'm looking forward to attempting out the Llama 70B version, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class model that I've 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 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 prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the components incorrect, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and gave me this:
Just like the earlier joke, the chain of thought in the records was much more interesting than the end outcome.
Other methods to attempt DeepSeek-R1
If you wish to try the design out without setting up anything you can do so using chat.deepseek.com-you'll need to create an account (sign in with Google, utilize an email address or supply a Chinese +86 phone number) and after that pick the "DeepThink" alternative listed below the timely input box.
DeepSeek provide the model via their API, utilizing an OpenAI-imitating endpoint. You can access that via 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 use llm -m deepseek-reasoner 'prompt' to run triggers.
This won't reveal you the reasoning tokens, regretfully. Those are provided by the API (example here) but LLM doesn't yet have a way to show them.