That model was trained in part using their unreleased R1 "thinking" model. Today they've launched R1 itself, along with an entire household of new designs obtained from that base.
There's a great deal of stuff in the 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 warn that "DeepSeek-R1-Zero encounters challenges such as unlimited repeating, poor readability, and language blending." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and thinking tasks". That one is also MIT accredited, and is a similar size.
I do not have the capability to run designs larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can quickly have fun with myself. That's where the 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 on Llama and Qwen.
This is an interesting flex! They have actually 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 is compatible with the underlying Llama license. Qwen designs are Apache certified so maybe MIT is OK?
(I also just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to appear. So far I've attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly enjoyable to have fun with.
I'm running it utilizing the mix of Ollama, LLM and larsaluarna.se the llm-ollama plugin.
First I brought and ran the model using Ollama itself:
This downloads around 8.5 GB of design data and starts an interactive chat user interface.
Once the design has been fetched, LLM can talk with it too. I choose utilizing LLM for experiments because it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of idea used to help generate the action. 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 space together. Hmm, bbarlock.com that's an intriguing combination. Let me think about how these two characters might interact in an amusing scenario.
First, bio.rogstecnologia.com.br let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're usually found in chillier environments, like icebergs or snowy locations. So, combining these two into a tea space setting is currently an amusing image.
[...]
It then thought for 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 huge size, struggles to discover comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting 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 oke.zone says with a smile, "This isn't so fishy anymore." 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 lead to comical turmoil.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less absurd. The follow-up joke presents "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 horrible. But the process of getting there was such a fascinating insight into how these brand-new designs work.
This was a fairly little 8B design. I'm eagerly anticipating trying 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 model that I've 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 model 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 aspects wrong, so I followed up with:
the background ended up covering the remainder of the image
It thought some more and offered me this:
As with the earlier joke, forum.altaycoins.com the chain of thought in the transcript was even more interesting than completion result.
Other methods to DeepSeek-R1
If you wish to attempt the design out without setting up anything you can do so using chat.deepseek.com-you'll need to create an account (check in with Google, use an email address or elearnportal.science supply a Chinese +86 contact number) and after that select the "DeepThink" option 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 secrets set deepseek and paste in your API secret, koha-community.cz then use llm -m deepseek-reasoner 'timely' to run prompts.
This won't show you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a way to show them.