That model was trained in part using their unreleased R1 "thinking" design. Today they have actually released R1 itself, together with a whole household of brand-new designs obtained from that base.
There's an entire lot of things in the 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 clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences obstacles such as limitless repetition, poor readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance comparable to OpenAI-o1 across math, code, and reasoning jobs". That one is likewise MIT certified, and is a similar size.
I don't have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily play with myself. That's where the brand-new distilled designs are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating flex! They have models 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 works with the underlying Llama license. Qwen models are Apache certified so maybe MIT is OK?
(I also just observed the MIT license files state "Copyright (c) 2023 DeepSeek" so they might require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to appear. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to play with.
I'm running it utilizing 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 design data and begins an interactive chat user interface.
Once the design has actually been brought, LLM can talk with it too. I choose using LLM for experiments since it logs whatever to SQLite for later exploration.
I set up the plugin and ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of idea used to help create the action. 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 an intriguing mix. Let me think of how these two characters may connect in a funny circumstance.
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 normally found in chillier environments, higgledy-piggledy.xyz like icebergs or snowy areas. So, integrating these 2 into a tea space 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 trademarketclassifieds.com a walrus decide to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to put saucers on the table, causing a couple of spills.
After a series of funny accidents, the walrus searches for and states with a grin, "This isn't so fishy any longer." The pelican smirks and photorum.eclat-mauve.fr remarks, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comedic turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less ridiculous. 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 theme.
So yeah, the joke is terrible. But the process of getting there was such an intriguing insight into how these new designs work.
This was a fairly small 8B design. I'm anticipating trying out 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 design that I've worked 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 tried my traditional 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 wound up covering the remainder of the image
It believed some more and gave me this:
Just like the earlier joke, the chain of believed in the transcript was even more intriguing than completion outcome.
Other methods to try DeepSeek-R1
If you want to try the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to develop an account (indication in with Google, utilize an email address or offer a Chinese +86 telephone number) and then choose the "DeepThink" option listed below the prompt input box.
DeepSeek offer the model by means of 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 utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This won't show you the thinking tokens, unfortunately. Those are provided by the API (example here) but LLM does not yet have a way to show them.
