That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they've launched R1 itself, in addition to a whole household of new designs obtained from that base.
There's a great deal of stuff in the new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters obstacles such as unlimited repeating, bad readability, and language mixing." ... so they also released:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and thinking jobs". That a person is also MIT accredited, and vmeste-so-vsemi.ru is a comparable size.
I don't have the capability to run models larger 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 brand-new distilled designs are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, gdprhub.eu DeepSeek-R1, and galgbtqhistoryproject.org 6 dense designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is an interesting flex! They have actually models based on Qwen 2.5 (14B, 32B, asystechnik.com 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 works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I likewise just discovered the MIT license files state "Copyright (c) 2023 DeepSeek" so they might require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to appear. Up until now I've attempted simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to have fun with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model using Ollama itself:
This downloads around 8.5 GB of design data and oke.zone begins an interactive chat user interface.
Once the model has been brought, LLM can speak to it too. I prefer utilizing LLM for experiments because it logs whatever to SQLite for later expedition.
I set up the plugin and ran it like this:
Each response starts with a ... pseudo-XML tag containing the chain of idea utilized to assist generate 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 room together. Hmm, that's an interesting . Let me consider how these two characters may interact in a funny scenario.
First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're normally discovered in colder climates, like icebergs or snowy areas. So, integrating these two into a tea room setting is already an amusing image.
[...]
It then believed 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 choose to open a quaint little tea room together. The walrus, grandtribunal.org with its big size, has a hard time to find comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to position saucers on the table, causing a few spills.
After a series of comical incidents, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, but 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 turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less ridiculous. 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 theme.
So yeah, the joke is dreadful. But the process of getting there was such an intriguing insight into how these new designs work.
This was a fairly little 8B model. I'm eagerly anticipating trying 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 favourite GPT-4 class design that I have actually operated on my own machine-I have high expectations.
Update 21st January 2025: humanlove.stream I got this quantized variation of that Llama 3.3 70B R1 distilled model working like this-a 34GB download:
Can it draw a pelican?
I tried my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the elements wrong, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and provided me this:
As with the earlier joke, the chain of thought in the transcript was far more intriguing than the end outcome.
Other ways to try DeepSeek-R1
If you want to try the model out without setting up anything you can do so using chat.deepseek.com-you'll require to create an account (check in with Google, use an email address or offer a Chinese +86 telephone number) and then pick the "DeepThink" choice listed below the timely input box.
DeepSeek use the model by means of their API, using an OpenAI-imitating endpoint. You can access that through 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 use llm -m deepseek-reasoner 'timely' to run prompts.
This will not reveal you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM doesn't yet have a way to display them.