That model was trained in part using their unreleased R1 "reasoning" model. Today they've released R1 itself, bphomesteading.com along with an entire household of brand-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 the majority of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences obstacles such as limitless repeating, poor readability, and language blending." ... so they also launched:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains efficiency similar to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That a person is likewise MIT licensed, and is a similar size.
I don't have the capability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.
To the research 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 a remarkable 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, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?
(I likewise just saw the MIT license files say "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 monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently beginning to show up. So far I have actually tried just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to play with.
I'm running it using the mix of Ollama, wiki.vifm.info LLM and the llm-ollama plugin.
First I brought and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of model data and begins an interactive chat user interface.
Once the model has actually been brought, LLM can speak with it as well. I choose utilizing LLM for experiments because it logs whatever to SQLite for later expedition.
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 create the response. 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 room together. Hmm, galgbtqhistoryproject.org that's a fascinating combination. Let me think about how these two characters might communicate in a humorous scenario.
First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or kigalilife.co.rw water. Walruses have big teeth, thick fur, and they're generally found in colder climates, like icebergs or snowy locations. So, integrating these two into a tea space setting is already an amusing image.
[...]
It then believed for forum.altaycoins.com 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, has a hard time to find comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, utilizes its beak to position saucers 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 mentions, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy any longer" is a pun on the scenario becoming 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 dreadful. But the procedure of getting there was such an interesting insight into how these brand-new designs work.
This was a fairly little 8B model. I'm looking forward to checking out 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 preferred GPT-4 class design that I have actually 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 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 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 believed some more and gave me this:
Just like the earlier joke, the chain of thought in the records was far more fascinating than the end outcome.
Other methods to try DeepSeek-R1
If you desire to try the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (indication in with Google, utilize an email address or provide a Chinese +86 phone number) and then pick the "DeepThink" option below the timely input box.
DeepSeek offer the model 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 key, then use llm -m deepseek-reasoner 'prompt' to run prompts.
This won't show you the thinking tokens, sadly. Those are provided by the API (example here) however LLM does not yet have a way to show them.