That model was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, together with a whole household of brand-new models 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 the majority of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across challenges such as unlimited repeating, bad readability, and language mixing." ... so they also released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and thinking jobs". That a person is also MIT licensed, and is a similar size.
I don't have the ability to run models bigger 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 brand-new distilled models are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense 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 connected, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache certified so maybe MIT is OK?
(I likewise simply saw the MIT license files say "Copyright (c) 2023 DeepSeek" so they may require to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are interesting beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are currently beginning to appear. So far I've tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to play with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design information and starts an interactive chat user interface.
Once the model has been brought, LLM can speak to it as well. I choose utilizing LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.
I installed the plugin and ran it like this:
Each response starts with a ... pseudo-XML tag containing the chain of idea used to assist produce 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 a fascinating combination. Let me consider how these 2 characters may engage in an amusing circumstance.
First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're generally found in chillier climates, like icebergs or snowy locations. So, integrating these 2 into a tea space setting is already an amusing image.
[...]
It then thought for parentingliteracy.com 20 paragraphs before outputting the joke! Here's the full 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 big size, has a hard time to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, uses its beak to place saucers on the table, triggering a couple of spills.
After a series of humorous accidents, the walrus looks up and says with a grin, "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 result in comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less unreasonable. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the style.
So yeah, the joke is awful. But the process of arriving was such a fascinating insight into how these brand-new designs work.
This was a fairly small 8B design. I'm eagerly anticipating 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 model that I have actually worked 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 attempted my classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing very well:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and offered me this:
Similar to the earlier joke, the chain of thought in the transcript was far more interesting than completion outcome.
Other methods to attempt DeepSeek-R1
If you wish to try the model out without setting up anything you can do so using chat.deepseek.com-you'll need to develop an account (indication in with Google, use an email address or supply a Chinese +86 telephone number) and after that pick the "DeepThink" choice listed below the timely input box.
DeepSeek use the model 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 key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the reasoning tokens, unfortunately. Those are provided by the API (example here) however LLM doesn't yet have a way to show them.
