That model was trained in part using their unreleased R1 "reasoning" design. Today they have actually launched R1 itself, together with a whole family of brand-new models obtained from that base.
There's a lot of things in the 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 tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences difficulties such as endless repetition, bad readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "includes cold-start information before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and reasoning jobs". That one is likewise MIT certified, and is a similar size.
I don't have the ability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can quickly play with myself. That's where the brand-new distilled models are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick models distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a remarkable flex! They have actually designs 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 works with the underlying Llama license. Qwen models are Apache accredited so possibly MIT is OK?
(I also just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they may need to pay a 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 currently starting to appear. Up until now I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's actually fun to play with.
I'm running it utilizing the mix of Ollama, forum.pinoo.com.tr LLM and the llm-ollama plugin.
First I brought and ran the design using Ollama itself:
This downloads around 8.5 GB of design data and utahsyardsale.com begins an interactive chat user interface.
Once the design has actually been fetched, LLM can speak to it also. I choose utilizing LLM for experiments since it logs whatever to SQLite for later expedition.
I set up the plugin and mediawiki.hcah.in ran it like this:
Each action starts with a ... pseudo-XML tag containing the chain of thought utilized to help create the response. For "a joke about a pelican and a walrus who run a tea space together" that began 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 intriguing combination. Let me think of how these two 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 big teeth, wiki.dulovic.tech thick fur, and they're usually discovered in cooler climates, like icebergs or snowy locations. So, combining these 2 into a tea space setting is currently an amusing 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 huge size, has a hard time to discover comfy chairs, so it rests on the table by accident, knocking over the teapot. Meanwhile, the pelican, archmageriseswiki.com trying to assist, uses its beak to put dishes on the table, causing a few 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 mentions, "Maybe not, however we do have a great deal of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run a not likely tea room. Their sizes lead to comical mayhem.
- Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less ridiculous. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and setiathome.berkeley.edu tea, making it amusing while fitting the theme.
So yeah, the joke is awful. But the procedure of getting there was such an intriguing insight into how these new designs work.
This was a fairly small 8B design. I'm anticipating trying the Llama 70B variation, which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class design 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 attempted my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing very well:
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 thought some more and offered me this:
Just like the earlier joke, the chain of believed in the transcript was far more intriguing than the end outcome.
Other methods to attempt DeepSeek-R1
If you want to attempt the design out without setting up anything at all you can do so using chat.deepseek.com-you'll need to create an account (indication in with Google, use an email address or offer a Chinese +86 contact number) and then select the "DeepThink" choice listed below the prompt input box.
DeepSeek provide the model through their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml configuration file:
Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not show you the reasoning tokens, sadly. Those are dished out by the API (example here) but LLM does not yet have a method to show them.