That design was trained in part using their unreleased R1 "thinking" design. Today they have actually released R1 itself, together with a whole family of new designs obtained from that base.
There's a great deal of things in the new release.
DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across challenges such as unlimited repetition, bad readability, and language mixing." ... so they also launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency similar to OpenAI-o1 across math, code, and thinking jobs". That a person is likewise MIT accredited, and is a similar 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 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 community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models 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 connected, which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache accredited so possibly MIT is OK?
(I likewise just noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)
Licensing aside, these distilled models are fascinating monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently starting to appear. Up until now I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and photorum.eclat-mauve.fr it's actually enjoyable to play with.
I'm running it using 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 design information and begins an interactive chat interface.
Once the model has been fetched, LLM can speak with it too. I prefer using LLM for experiments since it logs everything to SQLite for later exploration.
I installed the plugin and ran it like this:
Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to help create the action. 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, that's a fascinating combination. Let me think about how these 2 characters might engage in a humorous situation.
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 usually discovered in cooler climates, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is currently a funny image.
[...]
It then believed 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 space together. The walrus, library.kemu.ac.ke with its huge size, has a hard time to discover comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to position saucers on the table, causing a couple of spills.
After a series of comical incidents, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, but we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea space. Their sizes lead to comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance 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 amusing while fitting the style.
So yeah, the joke is horrible. But the procedure of getting there was such an intriguing insight into how these new designs work.
This was a fairly small 8B model. I'm looking forward to trying out 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 design that I've worked 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 attempted my classic Generate an SVG of a pelican riding a bike timely too. It did refrain from doing very well:
It aimed to me like it got the order of the aspects incorrect, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and offered me this:
Just like the earlier joke, the chain of believed in the records was even more intriguing than completion outcome.
Other methods to attempt DeepSeek-R1
If you desire to attempt the design out without installing anything at all you can do so using chat.deepseek.com-you'll need to produce an account (check in with Google, use an or offer a Chinese +86 phone number) and after that select the "DeepThink" option listed below the timely input box.
DeepSeek offer the model through 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 prompts.
This will not reveal you the thinking tokens, sadly. Those are dished out by the API (example here) however LLM does not yet have a method to display them.