That design was trained in part utilizing their unreleased R1 "reasoning" design. Today they've released R1 itself, in addition to an entire family of brand-new designs obtained from that base.
There's a great deal of stuff in the new release.
DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as unlimited repetition, poor readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout math, code, and reasoning jobs". That one is also MIT certified, and visualchemy.gallery is a comparable size.
I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly play 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 an interesting flex! They have actually designs 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 works with the underlying Llama license. Qwen designs are Apache licensed so perhaps MIT is OK?
(I likewise simply discovered the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled designs are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are already beginning to appear. So far I have actually attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to play 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 model information and starts an interactive chat user interface.
Once the design has been brought, LLM can speak to it also. I choose utilizing LLM for experiments since it logs whatever to SQLite for later exploration.
I set up the plugin and ran it like this:
Each response starts with a ... pseudo-XML tag containing the chain of idea used to assist produce the response. For "a joke about a pelican and a walrus who run a tea space together" that began like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an interesting combination. Let me think about how these two characters may engage in a funny situation.
First, let's consider their attributes. 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 found in chillier climates, like icebergs or snowy locations. So, integrating these two into a tea room setting is already an amusing image.
[...]
It then thought for 20 paragraphs before outputting the joke! Here's the complete 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 comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, causing a few spills.
After a series of humorous accidents, the walrus searches for and says with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and wiki.myamens.com Walrus run an unlikely tea room. Their sizes result in comedic turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario ending up being less absurd. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the theme.
So yeah, the joke is terrible. But the process of getting there was such an intriguing insight into how these new designs work.
This was a fairly little 8B model. I'm anticipating 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 preferred GPT-4 class design that I've run on my own machine-I have high expectations.
Update 21st January 2025: yogaasanas.science 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 traditional Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing really 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 provided me this:
Just like the earlier joke, the chain of thought in the transcript was much more interesting than the end result.
Other ways to try DeepSeek-R1
If you want to try the model out without installing anything you can do so utilizing chat.deepseek.com-you'll require to produce an account (sign in with Google, utilize an email address or offer a Chinese +86 contact number) and after that choose the "DeepThink" alternative listed below the timely input box.
DeepSeek use the design by means of their API, using an . You can access that by means of LLM by dropping this into your extra-openai-models. yaml configuration file:
Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the reasoning tokens, regretfully. Those are provided by the API (example here) but LLM does not yet have a method to display them.