That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually launched R1 itself, together with an entire family of brand-new models obtained from that base.
There's an entire lot of stuff in the brand-new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across obstacles such as unlimited repetition, poor readability, and language blending." ... so they also released:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout math, code, and thinking tasks". That a person is likewise MIT accredited, and is a comparable size.
I do not have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily play 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, DeepSeek-R1, and six dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have actually models 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 designs have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?
(I likewise simply discovered the MIT license files say "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 versions are already starting to reveal up. Up until now I've attempted just among 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 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 design information and starts an interactive chat interface.
Once the model has been fetched, LLM can speak to it as well. I choose using LLM for experiments since it logs whatever to SQLite for engel-und-waisen.de later exploration.
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 assist create the action. For "a joke about a pelican and a walrus who run a tea room together" that began like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's a fascinating mix. Let me think about how these 2 characters might engage in a funny circumstance.
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 big teeth, thick fur, and they're typically found in cooler climates, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is currently an amusing image.
[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete 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, with its big size, has a hard time to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put dishes on the table, causing a couple of spills.
After a series of funny accidents, humanlove.stream 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 lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea space. Their sizes lead to comedic 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 connects into both marine life ("fish") and tea, making it amusing while fitting the style.
So yeah, the joke is awful. But the process of arriving was such an intriguing insight into how these brand-new models work.
This was a fairly small 8B model. I'm anticipating checking out the Llama 70B variation, 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 design that I have actually operated 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 timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing 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 provided me this:
Just like the earlier joke, the chain of thought in the transcript was far more intriguing than the end outcome.
Other ways to attempt DeepSeek-R1
If you desire to try the model out without setting up anything you can do so using chat.deepseek.com-you'll need to create an account (check in with Google, utilize an email address or provide a Chinese +86 contact number) and after that select the "DeepThink" option listed below the prompt input box.
DeepSeek use the model via their API, using an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the reasoning tokens, unfortunately. Those are provided by the API (example here) however LLM doesn't yet have a way to display them.