That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they've released R1 itself, in addition to a whole family of new models obtained from that base.
There's a whole lot of things in the brand-new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero comes across difficulties such as limitless repeating, poor readability, and language mixing." ... so they also launched:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is also MIT accredited, and is a similar 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 2 designs are something I can easily 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 forum.pinoo.com.tr six thick designs 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 designs have an MIT license attached, asteroidsathome.net which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?
(I also simply saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled designs are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to appear. Up until now I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually enjoyable 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 around 8.5 GB of design information and starts an interactive chat user interface.
Once the design has actually been fetched, LLM can talk with it also. I choose utilizing LLM for experiments since it logs whatever to SQLite for later expedition.
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 produce the action. For "a joke about a pelican and a walrus who run a tea space together" that started 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 of how these two characters may communicate in an amusing scenario.
First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically found in cooler environments, like icebergs or snowy areas. So, combining these 2 into a tea space setting is currently an amusing 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 space together. The walrus, with its big size, struggles to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place saucers on the table, triggering a couple of spills.
After a series of comical incidents, the walrus searches for and states with a grin, "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 Walrus run an unlikely tea space. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less unreasonable. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, making it amusing while fitting the style.
So yeah, the joke is terrible. But the process of getting there was such an intriguing 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 variation, 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 design 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 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 prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the aspects incorrect, so I followed up with:
the background ended up covering the remainder of the image
It thought some more and offered me this:
Just like the earlier joke, the chain of thought in the records was far more interesting than completion outcome.
Other methods to try DeepSeek-R1
If you wish to attempt the design out without installing anything you can do so utilizing chat.deepseek.com-you'll require to create an account (indication in with Google, use an email address or offer a Chinese +86 telephone number) and then select the "DeepThink" option listed below the prompt input box.
DeepSeek use the design through their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm secrets set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
This won't reveal you the reasoning tokens, regretfully. Those are dished out by the API (example here) however LLM does not yet have a way to display them.