That model was trained in part utilizing their unreleased R1 "reasoning" model. Today they have actually launched 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 model. 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 comes across obstacles such as endless repeating, poor readability, and language mixing." ... so they also released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency similar to OpenAI-o1 throughout mathematics, code, and thinking tasks". That one is also MIT certified, and is a comparable size.
I do not have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily 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 dense designs distilled from DeepSeek-R1 based upon Llama and Qwen.
This is a fascinating 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 models have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?
(I also just discovered 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 designs are fascinating beasts.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already beginning to reveal up. Up until now I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually fun to play with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I fetched and ran the design using Ollama itself:
This downloads around 8.5 GB of design information and larsaluarna.se starts an interactive chat user interface.
Once the model has actually been brought, LLM can talk to it as well. I choose utilizing LLM for experiments because it logs everything to SQLite for later expedition.
I installed the plugin and ran it like this:
Each reaction begins with a ... pseudo-XML tag containing the chain of idea utilized to assist create the action. For "a joke about a pelican and a walrus who run a tea space together" that began like this:
Okay, so I need to come up with a joke about a pelican and a walrus running a tea space together. Hmm, that's a fascinating combination. Let me think of how these two characters may communicate in a humorous situation.
First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically discovered in chillier environments, like icebergs or snowy areas. So, integrating these two into a tea space setting is currently a funny 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 hb9lc.org a walrus decide to open a quaint little tea room together. The walrus, with its huge size, struggles to find comfortable chairs, setiathome.berkeley.edu so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, uses its beak to put dishes on the table, triggering a couple of spills.
After a series of funny incidents, the walrus searches for and says with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and forum.pinoo.com.tr Walrus run an unlikely tea room. Their sizes lead to comical turmoil.
- 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 connects into both marine life ("fish") and tea, pipewiki.org making it humorous while fitting the theme.
So yeah, the joke is terrible. But the procedure of arriving was such an intriguing insight into how these brand-new designs work.
This was a fairly little 8B design. I'm 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 design that I have actually operated on my own machine-I have high expectations.
Update 21st January 2025: I got this quantized version of that Llama 3.3 70B R1 distilled model working like this-a 34GB download:
Can it draw a pelican?
I tried my timeless Generate an SVG of a pelican riding a bike timely too. It did refrain from doing effectively:
It aimed to me like it got the order of the elements incorrect, so I followed up with:
the background wound up covering the remainder of the image
It believed some more and offered me this:
Similar to the earlier joke, the chain of believed in the records was far more intriguing than the end outcome.
Other methods to try DeepSeek-R1
If you wish to try the design out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to develop an account (sign in with Google, utilize an email address or supply a Chinese +86 telephone number) and after that select the "DeepThink" option listed below the prompt 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 utilize llm -m deepseek-reasoner 'timely' to run triggers.
This will not reveal you the thinking tokens, yogicentral.science sadly. Those are served up by the API (example here) however LLM does not yet have a method to display them.