That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually released R1 itself, in addition to a whole household of brand-new models 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 the majority of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero comes across difficulties such as limitless repeating, poor readability, and language mixing." ... so they also released:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That a person is likewise MIT certified, hb9lc.org 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 2 models are something I can easily have fun with myself. That's where the new distilled designs are available in.
To support the research community, utahsyardsale.com we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based on Llama and Qwen.
This is an interesting 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?
(I likewise simply observed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already beginning to reveal up. 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 actually fun to play with.
I'm running it using the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the design using Ollama itself:
This downloads around 8.5 GB of model information and starts an interactive chat user interface.
Once the design has actually been brought, LLM can speak with it too. I prefer using LLM for experiments since it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each response 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 need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an interesting mix. Let me think of how these two characters may engage in a funny situation.
First, let's consider their characteristics. 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 found in climates, like icebergs or snowy locations. So, combining these 2 into a tea space setting is currently an amusing image.
[...]
It then thought for 20 paragraphs before outputting the joke! Here's the complete transcript and here's the output at the end, after the tag:
The Joke:
A pelican and a walrus choose to open a quaint little tea space together. The walrus, drapia.org with its huge size, has a hard time to discover comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place saucers on the table, causing a few spills.
After a series of funny mishaps, the walrus searches for and says with a smile, "This isn't so fishy any longer." The pelican smirks and mentions, "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 result in comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario 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 funny while fitting the theme.
So yeah, the joke is terrible. But the procedure of getting there was such an interesting insight into how these brand-new models work.
This was a fairly small 8B design. I'm looking forward to trying out the Llama 70B variation, 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 model that I have actually 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 design working like this-a 34GB download:
Can it draw a pelican?
I attempted my timeless 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 aspects wrong, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and offered me this:
Similar to the earlier joke, the chain of thought in the transcript was far more interesting than completion result.
Other ways to attempt DeepSeek-R1
If you desire 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, use an email address or supply a Chinese +86 phone number) and after that choose the "DeepThink" option listed below the prompt input box.
DeepSeek provide the design by means of their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm secrets set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run prompts.
This won't show you the thinking tokens, regretfully. Those are dished out by the API (example here) however LLM does not yet have a way to display them.