That model was trained in part using their unreleased R1 "thinking" model. Today they have actually released R1 itself, together with an entire family of brand-new models obtained from that base.
There's a lot of stuff in the new release.
DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, dokuwiki.stream like many of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences difficulties such as limitless repeating, poor readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 throughout math, code, and thinking tasks". That one is also MIT licensed, and is a similar size.
I do not have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), menwiki.men so neither of these 2 models are something I can quickly have fun with myself. That's where the brand-new distilled models are available in.
To support the research study 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 an interesting flex! They have models based on Qwen 2.5 (14B, 32B, Math 1.5 B and oke.zone 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 compatible with the underlying Llama license. Qwen models are Apache licensed so maybe MIT is OK?
(I also simply discovered the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require 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 variations are currently beginning to show up. 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 enjoyable to play with.
I'm running it utilizing the combination of Ollama, LLM and utahsyardsale.com the llm-ollama plugin.
First I fetched and ran the model using Ollama itself:
This downloads around 8.5 GB of model information and starts an interactive chat user interface.
Once the design has actually been brought, LLM can talk with it as well. I prefer using LLM for experiments because it logs whatever to SQLite for later expedition.
I installed the plugin and ran it like this:
Each response starts with a ... pseudo-XML tag containing the chain of thought utilized to assist create the response. For "a joke about a pelican and a walrus who run a tea room together" that began like this:
Okay, so I require to come up with a joke about a pelican and socialeconomy4ces-wiki.auth.gr a walrus running a tea space together. Hmm, that's a fascinating combination. Let me think about how these 2 characters might engage in a funny scenario.
First, let's consider their attributes. 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 generally discovered in colder climates, like icebergs or snowy locations. So, combining these 2 into a tea space setting is currently 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 space together. The walrus, with its huge size, struggles to find comfortable chairs, funsilo.date so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to position saucers on the table, causing a couple of spills.
After a series of comical accidents, the walrus searches for and states with a smile, "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 a not likely tea space. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the situation ending up being less ridiculous. The follow-up joke presents "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 process of arriving was such a fascinating insight into how these new models work.
This was a fairly little 8B design. I'm looking forward to trying out the Llama 70B version, 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 have actually run 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 traditional 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 elements wrong, so I followed up with:
the background ended up covering the remainder of the image
It believed some more and provided me this:
Similar to the earlier joke, the chain of believed in the records was much more intriguing than completion result.
Other ways to try DeepSeek-R1
If you want to attempt the model out without setting up anything you can do so using chat.deepseek.com-you'll need to develop an account (check in with Google, use an email address or supply a Chinese +86 telephone number) and then pick the "DeepThink" choice listed below the prompt input box.
DeepSeek offer the model through their API, using an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm secrets set deepseek and users.atw.hu paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.
This won't show you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a method to display them.
