That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they've launched R1 itself, in addition to an entire household of new designs obtained from that base.
There's a great deal of things in the new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters obstacles such as unlimited repetition, bad readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and reasoning jobs". That a person is likewise MIT certified, and is a comparable size.
I don't have the ability to run than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily have fun with myself. That's where the new distilled designs are available in.
To support the research community, 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 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 works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I also simply observed 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 models are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already beginning to show up. Up until now I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to have fun with.
I'm running it using the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the design using Ollama itself:
This downloads around 8.5 GB of model data and bryggeriklubben.se starts an interactive chat interface.
Once the model has actually been brought, LLM can speak with it also. I choose using LLM for experiments because it logs whatever to SQLite for later expedition.
I set up the plugin and yogicentral.science ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to assist create the response. 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, that's a fascinating mix. Let me believe about how these 2 characters may connect in an amusing scenario.
First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally discovered in cooler environments, asteroidsathome.net like icebergs or snowy locations. So, integrating these two into a tea room 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 asteroidsathome.net a walrus decide to open a quaint little tea room together. The walrus, with its big size, has a hard time to find comfortable chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, causing a few spills.
After a series of humorous mishaps, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario 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 amusing while fitting the theme.
So yeah, the joke is awful. But the process of getting there was such a fascinating insight into how these 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 run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class model that I've worked 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 tried my traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing effectively:
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 believed some more and gave me this:
As with the earlier joke, the chain of thought in the records was far more intriguing than the end result.
Other ways to attempt DeepSeek-R1
If you want to attempt the design out without setting up anything you can do so utilizing chat.deepseek.com-you'll require to develop an account (indication in with Google, utilize an email address or offer a Chinese +86 contact number) and then select the "DeepThink" alternative listed below the timely input box.
DeepSeek offer the design via 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 key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not show you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM doesn't yet have a method to show them.