That model was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, in addition to an entire household of new designs obtained from that base.
There's a lot of things in the new release.
DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like the majority of their other releases, is under a tidy MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences challenges such as limitless repetition, poor readability, and language mixing." ... so they also launched:
DeepSeek-R1-which "incorporates cold-start data before RL" and "attains performance similar to OpenAI-o1 throughout mathematics, code, and thinking jobs". That a person is also MIT certified, and is a comparable size.
I don't have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 models are something I can easily play with myself. That's where the brand-new distilled designs 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 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, surgiteams.com which I'm uncertain is compatible with the underlying Llama license. Qwen designs are Apache certified so perhaps MIT is OK?
(I likewise just saw the MIT license files state "Copyright (c) 2023 DeepSeek" so they might need to pay a bit more attention to how they copied those in.)
Licensing aside, these distilled models are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are currently beginning to show up. Up until now I have actually attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and garagesale.es it's really enjoyable 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 information and begins an interactive chat interface.
Once the design has actually been brought, LLM can talk with it also. I prefer using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.
I set up the plugin and ran it like this:
Each action begins with a ... pseudo-XML tag containing the chain of thought used to help create the reaction. For "a joke about a pelican and a walrus who run a tea room together" that started 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 2 characters might interact in a funny scenario.
First, let's consider their characteristics. Pelicans are understood for their long beaks and valetinowiki.racing Webbed feet, frequently seen near the beach or pipewiki.org water. Walruses have huge teeth, thick fur, and they're generally found in colder environments, like icebergs or snowy areas. So, integrating these two into a tea space setting is currently a funny image.
[...]
It then believed 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 decide to open a quaint little tea room together. The walrus, with its big size, struggles to discover comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to place saucers on the table, causing a few spills.
After a series of humorous mishaps, the walrus looks up and says with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "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 lead to comedic chaos.
- 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 connects into both marine life ("fish") and tea, making it funny while fitting the theme.
So yeah, the joke is horrible. But the process of getting there was such an interesting insight into how these new designs work.
This was a fairly small 8B design. I'm eagerly anticipating experimenting with 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 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 my classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing very well:
It aimed to me like it got the order of the components wrong, so I followed up with:
the background wound up covering the remainder of the image
It thought some more and suvenir51.ru gave me this:
Just like the earlier joke, the chain of believed in the records was much more intriguing than the end result.
Other methods to try DeepSeek-R1
If you desire to try the design out without setting up anything you can do so utilizing chat.deepseek.com-you'll require to develop an account (sign in with Google, use an email address or provide a Chinese +86 telephone number) and after that choose the "DeepThink" alternative below the prompt input box.
DeepSeek provide the model through their API, utilizing 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 paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run triggers.
This won't show you the thinking tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a way to display them.