That design was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, along with a whole household of brand-new designs obtained from that base.
There's a lot of things in the brand-new release.
DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero encounters difficulties such as limitless repetition, bad readability, and language mixing." ... so they also released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance comparable to OpenAI-o1 throughout mathematics, code, and thinking tasks". That a person is likewise MIT certified, and nerdgaming.science is a similar size.
I don't have the ability to run models larger 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 new distilled models are available in.
To support the research 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 fascinating flex! They have actually 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache accredited so maybe MIT is OK?
(I also just saw the MIT license files state "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 fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
are currently beginning 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 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 model using Ollama itself:
This downloads around 8.5 GB of model information and starts an interactive chat interface.
Once the model has actually been brought, LLM can speak with it too. I choose utilizing LLM for experiments due to the fact that 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 idea used to help produce the action. For "a joke about a pelican and a walrus who run a tea space together" that started like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an intriguing mix. Let me think of how these 2 characters may interact in a humorous 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 big teeth, thick fur, and systemcheck-wiki.de they're typically found in colder climates, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is currently a funny image.
[...]
It then believed 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, has a hard time to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to help, utahsyardsale.com uses its beak to position dishes on the table, triggering a few spills.
After a series of comical incidents, the walrus searches for and states with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "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 result in comical mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less absurd. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and wiki.lafabriquedelalogistique.fr tea, making it humorous while fitting the style.
So yeah, wiki.whenparked.com the joke is awful. But the procedure of getting there was such an interesting insight into how these brand-new models work.
This was a fairly little 8B model. I'm anticipating checking out the Llama 70B version, 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 tried my traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing really well:
It aimed to me like it got the order of the components 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 believed in the transcript was much more fascinating than the end outcome.
Other methods to attempt DeepSeek-R1
If you wish to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll require to produce an account (check in with Google, use an email address or offer a Chinese +86 telephone number) and after that pick the "DeepThink" choice listed below the prompt input box.
DeepSeek offer the model through 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 keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
This won't reveal you the reasoning tokens, sadly. Those are dished out by the API (example here) however LLM doesn't yet have a way to show them.