That design was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually released R1 itself, together with an entire household of new models obtained from that base.
There's an entire lot of things in the new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters challenges such as limitless repeating, poor readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains performance equivalent to OpenAI-o1 throughout math, code, and reasoning tasks". That one is also MIT licensed, and is a comparable size.
I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily play with myself. That's where the brand-new distilled models are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 dense models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have actually 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 designs have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so maybe MIT is OK?
(I also just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to appear. Up until now I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually 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 model using Ollama itself:
This downloads around 8.5 GB of model data and begins an interactive chat interface.
Once the design has been fetched, LLM can speak with it too. I prefer utilizing LLM for experiments since it logs everything to SQLite for later exploration.
I set up the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of thought used to assist generate the reaction. For "a joke about a pelican and a walrus who run a tea room together" that began 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 mix. Let me consider how these 2 characters might connect in a humorous circumstance.
First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're typically discovered in chillier climates, like icebergs or snowy locations. So, combining these 2 into a tea space 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 a walrus decide to open a quaint little tea space together. The walrus, with its big size, has a hard time to discover comfortable chairs, opensourcebridge.science so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to put dishes on the table, causing a couple of 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 remarks, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: and Walrus run an unlikely tea room. Their sizes result in comedic chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the style.
So yeah, the joke is awful. But the procedure of arriving was such an interesting insight into how these brand-new designs work.
This was a fairly small 8B model. I'm looking forward to checking out the Llama 70B variation, which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class model that I have actually run 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 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 effectively:
It aimed to me like it got the order of the components incorrect, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and gave me this:
As with the earlier joke, the chain of believed in the transcript was far more fascinating than completion outcome.
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 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 below the prompt input box.
DeepSeek offer 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 configuration file:
Then run llm keys set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'prompt' to run triggers.
This will not reveal you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a way to show them.