That model was trained in part using their unreleased R1 "reasoning" model. Today they've released R1 itself, along with a whole family of new models obtained from that base.
There's a great deal of stuff 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 tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero comes across obstacles such as unlimited repetition, bad readability, and language mixing." ... so they also released:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains efficiency equivalent to OpenAI-o1 across mathematics, code, and thinking tasks". That one is likewise MIT accredited, and is a similar size.
I do not 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 easily have fun with myself. That's where the brand-new distilled designs are available in.
To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is an interesting flex! They have 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 attached, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?
(I also just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are interesting beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already starting to appear. Up until now I've attempted just one of 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 fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design information and starts an interactive chat interface.
Once the design has been fetched, wiki.rolandradio.net LLM can speak to it too. I prefer 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 thought utilized to help generate 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 believe about how these 2 characters may connect in a funny situation.
First, let's consider their attributes. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and wiki.dulovic.tech they're normally discovered in cooler climates, like icebergs or snowy locations. So, integrating these 2 into a tea room 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 decide to open a quaint little tea room together. The walrus, with its big size, struggles to find comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to put dishes on the table, causing a few spills.
After a series of funny incidents, the walrus searches for and states with a grin, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea space. Their sizes result in comedic mayhem.
- Punchline: "This isn't so fishy anymore" 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 galgbtqhistoryproject.org tea, making it amusing while fitting the theme.
So yeah, the joke is terrible. But the procedure of getting there was such a fascinating insight into how these new models work.
This was a fairly small 8B model. I'm eagerly anticipating trying 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 preferred GPT-4 class design that I've worked on my own have high expectations.
Update 21st January 2025: I got this quantized version of that Llama 3.3 70B R1 distilled model 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 components incorrect, so I followed up with:
the background ended up covering the remainder of the image
It thought some more and gave me this:
As with the earlier joke, the chain of believed in the transcript was far more interesting than completion outcome.
Other ways to try DeepSeek-R1
If you wish to attempt the model out without installing anything you can do so utilizing chat.deepseek.com-you'll need to produce an account (sign in with Google, use an email address or offer a Chinese +86 contact number) and then pick the "DeepThink" option listed below the timely input box.
DeepSeek offer the design by means of their API, utilizing 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, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
This won't reveal you the reasoning tokens, sadly. Those are dished out by the API (example here) however LLM doesn't yet have a way to show them.