That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually launched R1 itself, along with a whole household of brand-new designs obtained from that base.
There's an entire lot of things in the brand-new release.
DeepSeek-R1-Zero appears to be the base model. 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 comes across challenges such as endless repetition, bad readability, and language mixing." ... so they also released:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance comparable to OpenAI-o1 across math, code, and thinking tasks". That one is likewise MIT licensed, and is a comparable size.
I do not 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 quickly have fun with myself. That's where the new distilled designs are available in.
To support the research study neighborhood, 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 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 compatible with the underlying Llama license. Qwen designs are Apache accredited so possibly MIT is OK?
(I also simply discovered the MIT license files say "Copyright (c) 2023 DeepSeek" so they may require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are interesting beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to show up. Up until now I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really enjoyable to play with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design information and starts an interactive chat interface.
Once the design has actually been fetched, LLM can speak with it as well. I choose using 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 idea utilized to assist create the response. For "a joke about a pelican and a walrus who run a tea space together" that began like this:
Okay, so I require 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 think of how these two characters might interact in a funny circumstance.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're normally found in cooler climates, like icebergs or snowy locations. So, integrating these 2 into a tea space setting is already a funny image.
[...]
It then believed 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 choose to open a quaint little tea room together. The walrus, with its huge size, struggles to discover comfy 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, triggering a few spills.
After a series of humorous incidents, the walrus looks up and says with a smile, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less ridiculous. The follow-up joke introduces "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 terrible. But the process of arriving was such an intriguing insight into how these new models work.
This was a fairly small 8B model. I'm 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 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 model working like this-a 34GB download:
Can it draw a pelican?
I tried my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the aspects wrong, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and provided me this:
As with the earlier joke, the chain of thought in the transcript was much more fascinating than completion outcome.
Other ways to attempt DeepSeek-R1
If you wish to try the model out without setting up anything at all you can do so using chat.deepseek.com-you'll need to create an account (sign in with Google, utilize an email address or oke.zone supply a Chinese +86 telephone number) and after that select the "DeepThink" alternative below the timely input box.
DeepSeek use the model by means of their API, utilizing 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 secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This won't reveal you the reasoning tokens, unfortunately. Those are dished out by the API (example here) however LLM does not yet have a way to show them.