That model was trained in part using their unreleased R1 "thinking" design. Today they have actually launched R1 itself, along with a whole family of brand-new models obtained from that base.
There's a whole lot of things 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 tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across difficulties such as unlimited repetition, poor readability, and language blending." ... so they also released:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout math, code, and thinking jobs". That one is likewise MIT accredited, and is a similar 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 play with myself. That's where the new distilled designs are available in.
To support the research neighborhood, we have DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based on Llama and Qwen.
This is an interesting flex! They have designs 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 models have an MIT license attached, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?
(I also just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently beginning to show up. Up until now I've tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and wiki-tb-service.com it's actually enjoyable to play with.
I'm running it using the combination of Ollama, LLM and bbarlock.com the llm-ollama plugin.
First I brought and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of model information and begins an interactive chat interface.
Once the model has been fetched, LLM can speak with it as well. I choose using LLM for experiments due to the fact that it logs whatever to SQLite for later expedition.
I set up the plugin and ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of thought used to help generate the reaction. For "a joke about a pelican and a walrus who run a tea space 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 a fascinating mix. Let me think of how these two characters might communicate in a humorous scenario.
First, let's consider their characteristics. 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 typically found in cooler environments, like icebergs or snowy locations. So, integrating these two into a tea space setting is already an amusing image.
[...]
It then believed 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 choose to open a quaint little tea space together. The walrus, with its big size, has a hard time to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to place dishes on the table, triggering a couple of spills.
After a series of comical incidents, the walrus looks up and says with a smile, "This isn't so fishy any longer." The pelican smirks and mentions, "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 comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less unreasonable. 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 theme.
So yeah, the joke is awful. But the process of arriving was such an interesting insight into how these brand-new models work.
This was a fairly little 8B model. I'm anticipating trying the Llama 70B version, 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 design 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 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 ended up covering the remainder of the image
It thought some more and offered me this:
Just like the earlier joke, the chain of believed in the records was far more fascinating than completion result.
Other methods to attempt DeepSeek-R1
If you want to attempt the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (indication in with Google, utilize an email address or supply a Chinese +86 contact number) and then pick the "DeepThink" option 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 show you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM doesn't yet have a way to show them.