That design was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, together with a whole family of new designs obtained from that base.
There's a great deal of stuff 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, gratisafhalen.be is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters challenges such as unlimited repeating, poor readability, and language mixing." ... so they also launched:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance similar to OpenAI-o1 across mathematics, code, and reasoning jobs". That one is likewise MIT accredited, and is a similar size.
I do not have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have models based on 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 is suitable with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?
(I also just saw the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting to reveal up. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really enjoyable to have fun with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of model data and begins an interactive chat user interface.
Once the model has actually been brought, LLM can speak to it also. I prefer using LLM for experiments since it logs whatever to SQLite for later expedition.
I set up the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to assist create the reaction. For "a joke about a pelican and a walrus who run a tea space together" that began like this:
Okay, so I require to come up with a joke about a pelican and engel-und-waisen.de a walrus running a tea room together. Hmm, that's a fascinating combination. Let me consider how these two characters may interact in a funny situation.
First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in chillier environments, like icebergs or snowy locations. So, combining these two into a tea room setting is already a funny 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, with its big size, struggles to discover comfortable chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, wiki.eqoarevival.com the pelican, trying to assist, uses its beak to position saucers on the table, triggering a few spills.
After a series of comical mishaps, the walrus looks up 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 an unlikely tea space. Their sizes cause comedic mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less unreasonable. 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 style.
So yeah, the joke is terrible. But the process of getting there was such an interesting insight into how these brand-new designs work.
This was a fairly little 8B model. I'm looking forward to checking out the Llama 70B variation, photorum.eclat-mauve.fr 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've run 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 model working like this-a 34GB download:
Can it draw a pelican?
I attempted my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing effectively:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and provided me this:
Similar to the earlier joke, the chain of thought in the transcript was far more intriguing than completion outcome.
Other ways to try DeepSeek-R1
If you want to attempt the design out without setting up anything at all you can do so using chat.deepseek.com-you'll need to produce an account (indication in with Google, use an email address or supply a Chinese +86 phone number) and then select the "DeepThink" alternative listed below the prompt input box.
DeepSeek offer the model via their API, using 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 keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
This will not show you the reasoning tokens, larsaluarna.se sadly. Those are served up by the API (example here) but LLM does not yet have a method to display them.
