That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they've released R1 itself, along with a whole household of brand-new designs obtained from that base.
There's an entire lot of stuff in the new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero comes across difficulties such as limitless repetition, bad readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That a person is also MIT certified, and is a similar size.
I do not have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can quickly play with myself. That's where the new distilled models are available in.
To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based on Llama and Qwen.
This is a fascinating flex! They have models 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 designs have an MIT license connected, which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?
(I also simply observed the MIT license files say "Copyright (c) 2023 DeepSeek" so they might require to pay a little 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 starting to show up. So far I've tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly enjoyable to play with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the design using Ollama itself:
This downloads around 8.5 GB of design data and begins an interactive chat interface.
Once the model has actually been brought, LLM can speak with it as well. I choose utilizing LLM for experiments because it logs everything to SQLite for later expedition.
I installed the plugin and ran it like this:
Each response begins with a ... pseudo-XML tag containing the chain of idea utilized to help generate the response. 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 intriguing combination. Let me think about how these 2 characters might interact in a humorous scenario.
First, let's consider their qualities. 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 discovered in colder climates, like icebergs or snowy locations. So, combining these 2 into a tea room setting is already a funny 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 room together. The walrus, with its big size, struggles to find comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to put saucers on the table, triggering a couple of spills.
After a series of humorous mishaps, the walrus searches for and gratisafhalen.be says with a smile, "This isn't so fishy any longer." 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 cause .
- Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less unreasonable. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the style.
So yeah, the joke is awful. But the procedure of arriving was such an intriguing insight into how these brand-new models 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 very well:
It aimed to me like it got the order of the elements wrong, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and offered me this:
Similar to the earlier joke, the chain of believed in the transcript was even more intriguing than completion outcome.
Other methods to try DeepSeek-R1
If you wish to try the model out without setting up anything you can do so using chat.deepseek.com-you'll require to develop an account (indication in with Google, utilize an email address or provide a Chinese +86 phone number) and then select the "DeepThink" alternative listed below the prompt input box.
DeepSeek provide the design by means of their API, utilizing an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm secrets set deepseek and paste in your API key, then use llm -m deepseek-reasoner 'prompt' to run triggers.
This will not show you the thinking tokens, regretfully. Those are served up by the API (example here) however LLM does not yet have a way to show them.