That model was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, together with an entire family of brand-new models obtained from that base.
There's a great deal 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 clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences obstacles such as endless repeating, poor readability, and language mixing." ... so they likewise released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency similar to OpenAI-o1 throughout math, code, and reasoning tasks". That a person is likewise MIT licensed, and is a comparable size.
I do not have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily have fun with myself. That's where the brand-new distilled models are available in.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have designs based upon Qwen 2.5 (14B, 32B, wiki.whenparked.com 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 designs are Apache licensed so maybe MIT is OK?
(I likewise simply noticed 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, hb9lc.org these distilled models are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to reveal up. So far I have actually tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.
I'm running it utilizing the combination 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 design has been brought, LLM can speak with it also. I choose utilizing LLM for since it logs everything to SQLite for wavedream.wiki later exploration.
I installed the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of idea utilized to help generate the action. For "a joke about a pelican and a walrus who run a tea space together" that started like this:
Okay, fishtanklive.wiki so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting mix. Let me think about how these 2 characters may engage in an amusing scenario.
First, let's consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, genbecle.com thick fur, and they're typically discovered in chillier environments, like icebergs or snowy locations. So, combining these two into a tea room setting is already a funny image.
[...]
It then believed 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, has a hard time to find comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to place dishes on the table, triggering a couple of spills.
After a series of funny incidents, the walrus searches for and says with a smile, "This isn't so fishy anymore." The pelican smirks and says, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and chessdatabase.science Walrus run an unlikely tea space. Their sizes result in comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less ridiculous. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, making it funny while fitting the style.
So yeah, the joke is terrible. But the procedure of getting there was such a fascinating insight into how these brand-new designs work.
This was a fairly little 8B model. I'm eagerly anticipating checking out 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 favourite GPT-4 class design that I have actually worked 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 design 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 effectively:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and provided me this:
Just like the earlier joke, the chain of thought in the transcript was far more intriguing than completion outcome.
Other ways to attempt DeepSeek-R1
If you wish to try the design out without installing anything at all you can do so using chat.deepseek.com-you'll need to produce an account (indication in with Google, use an email address or provide a Chinese +86 contact number) and then pick the "DeepThink" choice below the timely input box.
DeepSeek provide the design via their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm keys set deepseek and biolink.palcurr.com paste in your API key, then use llm -m deepseek-reasoner 'prompt' to run triggers.
This will not reveal you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a way to display them.