That design was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, together with a whole household of new models obtained from that base.
There's a lot of stuff in the new release.
DeepSeek-R1-Zero seems the . It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters challenges such as endless repeating, bad readability, and language blending." ... so they also released:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That one is also MIT accredited, and is a comparable size.
I do not 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 designs are available in.
To support the research study community, 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 suitable with the underlying Llama license. Qwen models are Apache licensed so perhaps MIT is OK?
(I likewise just discovered 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 models are remarkable beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are currently beginning to appear. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really fun to play with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the design utilizing Ollama itself:
This downloads around 8.5 GB of model information and starts an interactive chat user interface.
Once the model has actually been brought, LLM can speak to it too. I prefer utilizing LLM for experiments due to the fact that it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to help produce the response. For "a joke about a pelican and a walrus who run a tea room together" that began like this:
Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's an interesting mix. Let me believe about how these two characters may connect in a humorous circumstance.
First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in colder climates, lespoetesbizarres.free.fr like icebergs or snowy areas. So, combining these 2 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 room together. The walrus, with its huge size, struggles to find comfortable chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to position dishes on the table, causing a few spills.
After a series of humorous mishaps, the walrus searches for and states with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, but we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes result in comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less absurd. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the style.
So yeah, the joke is terrible. But the procedure of arriving was such an interesting insight into how these new designs work.
This was a fairly little 8B model. I'm anticipating trying 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 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 design working like this-a 34GB download:
Can it draw a pelican?
I tried my classic Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing effectively:
It aimed to me like it got the order of the elements wrong, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and provided me this:
Similar to the earlier joke, the chain of thought in the records was even more interesting than completion result.
Other ways to attempt DeepSeek-R1
If you desire to try the design out without installing anything you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, utilize an email address or supply a Chinese +86 phone number) and then choose the "DeepThink" option listed below the timely input box.
DeepSeek offer the design via their API, using an OpenAI-imitating endpoint. You can access that via 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 'timely' to run prompts.
This won't show you the thinking tokens, sadly. Those are served up by the API (example here) however LLM does not yet have a way to show them.