That design was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually released R1 itself, in addition to a whole family of brand-new designs obtained from that base.
There's a great deal of things in the 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 tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters challenges such as unlimited repeating, bad readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That a person is also MIT licensed, and is a comparable size.
I don't have the ability 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 models 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 designs 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 models have an MIT license connected, which I'm uncertain is suitable with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?
(I likewise simply noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled designs are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are currently starting to appear. Up until now I have actually tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable to play with.
I'm running it using the mix 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 information and starts an interactive chat user interface.
Once the design has actually been brought, LLM can speak to it also. I prefer using LLM for experiments since it logs whatever to SQLite for later exploration.
I set up the plugin and ran it like this:
Each response starts with a ... pseudo-XML tag containing the chain of thought utilized to help produce the response. For "a joke about a pelican and a walrus who run a tea room together" that started like this:
Okay, so I require to come up with a joke about a pelican and asteroidsathome.net a walrus running a tea room together. Hmm, that's a fascinating combination. Let me believe about how these two characters may communicate in a funny scenario.
First, let's consider their characteristics. 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 usually found in cooler environments, like icebergs or snowy areas. So, combining these two into a tea space is currently 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 decide to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfortable chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to place saucers on the table, causing a couple of 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, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea room. Their sizes result in comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the situation becoming less ridiculous. The follow-up joke introduces "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 horrible. But the process of arriving was such an intriguing 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 favourite GPT-4 class model that I have actually operated 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 design working like this-a 34GB download:
Can it draw a pelican?
I attempted my classic 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 components incorrect, so I followed up with:
the background ended up covering the remainder of the image
It thought some more and gave me this:
Similar to the earlier joke, tandme.co.uk the chain of believed in the records was much more interesting than completion result.
Other methods to try DeepSeek-R1
If you wish to try the model out without installing anything you can do so using chat.deepseek.com-you'll need to produce an account (check in with Google, use an email address or provide a Chinese +86 telephone number) and then pick the "DeepThink" option below the prompt input box.
DeepSeek offer the model through their API, using an OpenAI-imitating endpoint. You can access that by means of 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 triggers.
This won't show you the reasoning tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a method to show them.