That model was trained in part using their unreleased R1 "reasoning" design. Today they've launched R1 itself, along with an entire family of new designs obtained from that base.
There's an entire 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, yewiki.org is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language blending." ... so they likewise launched:
DeepSeek-R1-which "integrates cold-start information before RL" and "attains performance similar to OpenAI-o1 across mathematics, code, and reasoning tasks". That one is also MIT accredited, and is a comparable size.
I do not 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 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 six thick designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable flex! They have 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, utahsyardsale.com which I'm uncertain is suitable with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?
(I likewise just noticed 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 interesting monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized versions are currently beginning to reveal up. So far I've attempted simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to play with.
I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.
First I brought and ran the model utilizing Ollama itself:
This downloads around 8.5 GB of design data and starts an interactive chat interface.
Once the model has actually been fetched, akropolistravel.com LLM can speak to it also. I prefer using LLM for experiments since 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 generate the action. 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 a walrus running a tea room together. Hmm, that's an interesting mix. Let me believe about how these 2 characters might interact in an amusing scenario.
First, wiki.rrtn.org let's consider their attributes. Pelicans are known for their long beaks and wiki.rolandradio.net Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in chillier environments, like icebergs or snowy locations. So, combining these 2 into a tea space setting is currently a funny image.
[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full 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 find comfy chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to place saucers on the table, triggering a few spills.
After a series of comical mishaps, the walrus searches for and annunciogratis.net states with a smile, "This isn't so fishy any longer." The pelican smirks and wiki.fablabbcn.org remarks, "Maybe not, however we do have a lot of krill in our tea!"
Explanation:
- Setup: Pelican and Walrus run an unlikely tea room. Their sizes cause comical chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less unreasonable. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it amusing while fitting the theme.
So yeah, the joke is dreadful. But the procedure of arriving was such an interesting insight into how these brand-new designs work.
This was a fairly little 8B model. I'm looking forward to trying out 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 preferred GPT-4 class model that I've run 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 design working like this-a 34GB download:
Can it draw a pelican?
I tried my traditional Generate an SVG of a pelican riding a bicycle timely too. It did refrain from doing really well:
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 thought some more and offered 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 try 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 require to produce an account (check in with Google, use an email address or offer a Chinese +86 phone number) and then choose the "DeepThink" option listed below the timely input box.
DeepSeek use the model through their API, utilizing 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 secret, then use llm -m deepseek-reasoner 'timely' to run prompts.
This won't show you the thinking tokens, unfortunately. Those are served up by the API (example here) however LLM does not yet have a way to display them.
