That design was trained in part using their unreleased R1 "thinking" design. Today they've launched R1 itself, in addition to an entire family of new designs obtained from that base.
There's a whole lot of stuff 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 challenges such as limitless repeating, bad readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency similar to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That one is also MIT certified, and is a comparable size.
I don't have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs 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, utahsyardsale.com DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based upon 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 suitable with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?
(I also just saw the MIT license files state "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 designs are fascinating monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently beginning to appear. So far I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really enjoyable 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 design using Ollama itself:
This downloads around 8.5 GB of model information and larsaluarna.se starts an interactive chat user interface.
Once the model has actually been brought, LLM can speak with it as well. I prefer utilizing LLM for experiments because it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each response starts 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 started like this:
Okay, yewiki.org 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 mix. Let me think of how these two characters may connect in a funny scenario.
First, oke.zone let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're usually discovered in colder environments, like icebergs or snowy areas. So, combining these 2 into a tea room setting is currently a funny image.
[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full 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 comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to position saucers on the table, triggering a few spills.
After a series of humorous mishaps, the walrus searches for and states with a smile, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes lead to comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance becoming less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and tea, making it humorous while fitting the theme.
So yeah, the joke is terrible. But the process of arriving was such a fascinating insight into how these brand-new designs work.
This was a fairly small 8B model. I'm looking forward to experimenting with 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 have actually operated 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 traditional 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 offered me this:
As with the earlier joke, the chain of believed in the transcript was far more intriguing than completion outcome.
Other methods to attempt DeepSeek-R1
If you wish to attempt the design 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 passfun.awardspace.us supply a Chinese +86 contact number) and kenpoguy.com after that choose the "DeepThink" alternative below the timely input box.
DeepSeek provide the model through their API, using 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 keys set deepseek and paste in your API secret, opentx.cz then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
This won't reveal you the reasoning tokens, . Those are dished out by the API (example here) but LLM doesn't yet have a method to display them.