That design was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually released R1 itself, along with an entire household of new models obtained from that base.
There's a lot of stuff in the brand-new release.
DeepSeek-R1-Zero appears to be 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 endless repetition, poor readability, and language blending." ... so they also launched:
DeepSeek-R1-which "includes cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and reasoning tasks". That a person is also MIT licensed, and is a comparable 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 designs are something I can quickly have fun with myself. That's where the new distilled designs are available in.
To support the research 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 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 models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I likewise just saw 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 interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to appear. Up until now I've tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by it's really enjoyable to have fun 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 information and wiki.snooze-hotelsoftware.de starts an interactive chat interface.
Once the model has actually been brought, LLM can talk to it too. I choose using LLM for experiments since it logs everything to SQLite for later expedition.
I installed the plugin and ran it like this:
Each action begins with a ... pseudo-XML tag containing the chain of thought 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 need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's a fascinating combination. Let me think about how these two characters may interact in a funny situation.
First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically found in colder climates, like icebergs or snowy locations. So, integrating 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 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 space together. The walrus, with its big size, struggles to find comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to position dishes on the table, causing a couple of spills.
After a series of humorous incidents, the walrus looks up and states with a grin, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes lead to comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less absurd. The follow-up joke introduces "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 dreadful. But the process of getting there was such an interesting insight into how these brand-new models work.
This was a fairly small 8B model. I'm eagerly anticipating checking out the Llama 70B version, bphomesteading.com which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my favourite 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 design working like this-a 34GB download:
Can it draw a pelican?
I attempted my traditional Generate an SVG of a pelican riding a bike timely 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 gave me this:
Similar to the earlier joke, the chain of thought in the records was much more fascinating than the end outcome.
Other methods to try DeepSeek-R1
If you want to attempt the model out without installing anything you can do so using chat.deepseek.com-you'll need to develop an account (indication in with Google, use an email address or provide a Chinese +86 contact number) and after that pick the "DeepThink" choice below the timely input box.
DeepSeek use 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 configuration file:
Then run llm keys 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 provided by the API (example here) however LLM does not yet have a way to show them.