That model was trained in part using their unreleased R1 "reasoning" model. Today they have actually released R1 itself, together with a whole family of new obtained from that base.
There's a whole lot of things in the brand-new release.
DeepSeek-R1-Zero appears to be the base design. 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 obstacles such as unlimited repeating, poor readability, and language mixing." ... so they likewise launched:
DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That one is also 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 play with myself. That's where the brand-new distilled models are available in.
To support the research study community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable flex! They have models based upon 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 models are Apache certified so possibly MIT is OK?
(I also just observed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may require to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are remarkable monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently beginning to appear. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to play with.
I'm running it utilizing the combination of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design data and starts an interactive chat user interface.
Once the model has been fetched, LLM can speak to it also. I choose using 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 thought utilized to help generate the response. For "a joke about a pelican and a walrus who run a tea room together" that started like this:
Okay, so I need 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 2 characters might interact in a humorous scenario.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're normally discovered in colder climates, like icebergs or snowy areas. So, combining these 2 into a tea room setting is already a funny image.
[...]
It then believed for 20 paragraphs before outputting the joke! Here's the complete 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, struggles to discover comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put saucers on the table, triggering a couple of spills.
After a series of funny accidents, the walrus searches for and states with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea space. Their sizes cause comedic turmoil.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance 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, bytes-the-dust.com the joke is awful. But the procedure of arriving was such an intriguing insight into how these brand-new designs work.
This was a fairly small 8B model. I'm looking forward to attempting 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 preferred GPT-4 class model 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 model working like this-a 34GB download:
Can it draw a pelican?
I attempted my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing extremely well:
It aimed to me like it got the order of the aspects wrong, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and wiki.asexuality.org provided me this:
Just like the earlier joke, the chain of thought in the records was much more intriguing than the end result.
Other methods to attempt DeepSeek-R1
If you wish to attempt the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or offer a Chinese +86 phone number) and after that select the "DeepThink" alternative below the prompt input box.
DeepSeek use the model via their API, using an OpenAI-imitating endpoint. 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 secret, then utilize llm -m deepseek-reasoner 'timely' to run prompts.
This will not show you the reasoning tokens, sadly. Those are provided by the API (example here) however LLM doesn't yet have a method to show them.