That model was trained in part using their unreleased R1 "thinking" model. Today they have actually released R1 itself, wiki.rrtn.org in addition to a whole household of new designs obtained from that base.
There's a lot of stuff in the brand-new release.
DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters difficulties such as limitless repeating, poor readability, and language blending." ... so they also launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and reasoning jobs". That one is likewise MIT certified, and is a similar size.
I don't have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs are something I can quickly play with myself. That's where the new distilled models are available in.
To support the research study neighborhood, we have open-sourced DeepSeek-R1-Zero, utahsyardsale.com DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have actually models based upon Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and Llama 3 (Llama-3.1 8B and suvenir51.ru Llama 3.3 70B Instruct).
Weirdly those Llama designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?
(I also just observed 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 interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already beginning to show up. Up until now I've tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and higgledy-piggledy.xyz it's truly 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 model data and starts an interactive chat user interface.
Once the design has actually been brought, LLM can speak with it as well. I choose using LLM for experiments because it logs everything to SQLite for later expedition.
I installed the plugin and ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of idea utilized to assist generate the reaction. For "a joke about a pelican and a walrus who run a tea space together" that started like this:
Okay, so I require to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting combination. Let me consider how these 2 characters might connect in an amusing circumstance.
First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they're generally found in chillier climates, like icebergs or snowy locations. So, combining these two into a tea space setting is currently an amusing image.
[...]
It then thought 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 decide to open a quaint little tea room together. The walrus, with its huge size, has a hard time to find comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, annunciogratis.net uses its beak to place dishes on the table, causing a few spills.
After a series of funny accidents, the walrus looks up 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 a not likely tea space. Their sizes cause comedic mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the situation ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and systemcheck-wiki.de tea, making it funny while fitting the theme.
So yeah, the joke is dreadful. But the procedure of arriving was such an interesting insight into how these brand-new models work.
This was a fairly small 8B model. I'm eagerly 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 favourite GPT-4 class model that I've 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 classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing effectively:
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 gave me this:
Similar to the earlier joke, the chain of believed in the was even more fascinating than completion outcome.
Other methods to attempt DeepSeek-R1
If you want to try the model out without setting up anything you can do so using chat.deepseek.com-you'll require to create an account (indication in with Google, opensourcebridge.science use an email address or provide a Chinese +86 contact number) and after that select the "DeepThink" choice below the prompt input box.
DeepSeek provide the design by means of their API, using 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 keys set deepseek and paste in your API key, then use llm -m deepseek-reasoner 'timely' to run triggers.
This won't reveal you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM doesn't yet have a way to show them.