That design was trained in part utilizing their unreleased R1 "thinking" model. Today they have actually launched R1 itself, together with an entire family of 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 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 repetition, poor readability, and language blending." ... so they also released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance comparable to OpenAI-o1 across mathematics, code, and thinking jobs". That a person is also MIT certified, and is a comparable size.
I don't have the ability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily have fun with myself. That's where the 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 an interesting flex! They have actually models based on Qwen 2.5 (14B, opentx.cz 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 is suitable with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I also just observed 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 models are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to show up. Up until now I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by AI-and it's truly enjoyable to play with.
I'm running it utilizing the mix of Ollama, yewiki.org LLM and wiki.rolandradio.net the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of model data and begins an interactive chat interface.
Once the model has been fetched, LLM can talk with it also. I choose utilizing LLM for experiments since it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of thought used to help create the response. For "a joke about a pelican and a walrus who run a tea space together" that started 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 an interesting combination. Let me believe about how these 2 characters may engage in a funny situation.
First, let's consider their qualities. Pelicans are understood for koha-community.cz their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, garagesale.es and they're usually discovered in cooler environments, like icebergs or snowy areas. So, integrating these two into a tea room 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 archmageriseswiki.com a walrus choose to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to place dishes on the table, causing a couple of spills.
After a series of comical accidents, the walrus searches for and states with a grin, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea space. Their sizes lead to comedic mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the theme.
So yeah, the joke is terrible. But the process of getting there was such a fascinating insight into how these brand-new models work.
This was a fairly little 8B model. I'm eagerly anticipating checking out 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 favourite GPT-4 class design that I've operated 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 design working like this-a 34GB download:
Can it draw a pelican?
I tried my traditional Generate an SVG of a pelican riding a bicycle timely 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 thought some more and gave me this:
As with 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 attempt the design out without setting up anything at all you can do so using chat.deepseek.com-you'll require to produce an account (check in with Google, qoocle.com use an email address or provide a Chinese +86 contact number) and then pick the "DeepThink" choice listed below the timely input box.
DeepSeek use the design through their API, using 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 prompts.
This won't show you the thinking tokens, unfortunately. Those are dished out by the API (example here) but LLM doesn't yet have a method to display them.