That model was trained in part utilizing their unreleased R1 "thinking" design. Today they have actually released R1 itself, in addition to a whole family of new designs obtained from that base.

There's a lot of stuff in the new release.

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like most of their other releases, genbecle.com is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as limitless repeating, bad readability, and language blending." ... so they also launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance comparable to OpenAI-o1 across math, code, and thinking tasks". That one is likewise MIT accredited, and oke.zone is a similar size.

I don't have the capability to run models bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two models are something I can quickly have fun with myself. That's where the new distilled models are available in.

To support the research neighborhood, forum.altaycoins.com we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick models distilled from DeepSeek-R1 based on Llama and Qwen.

This is a remarkable flex! They have models 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 uncertain works with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?

(I also simply noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may require to pay a bit more attention to how they copied those in.)

Licensing aside, these distilled models are remarkable monsters.

Running DeepSeek-R1-Distill-Llama-8B-GGUF

Quantized versions are already beginning to reveal up. So far I have actually attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really enjoyable to have fun with.

I'm running it utilizing the mix of Ollama, LLM and the llm-ollama plugin.

First I fetched and wiki.whenparked.com ran the design utilizing Ollama itself:

This downloads around 8.5 GB of model data and begins an interactive chat user interface.

Once the design has actually been brought, LLM can talk with it also. I prefer utilizing LLM for experiments because it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of idea used to help generate the reaction. For "a joke about a pelican and a walrus who run a tea space together" that started like this:

Okay, so I need to come up with a joke about a pelican and a walrus running a tea room together. Hmm, that's an interesting combination. Let me believe about how these two characters may engage in a humorous circumstance.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're generally found in cooler climates, like icebergs or snowy locations. So, combining these 2 into a tea room setting is already an amusing image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the full 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 space together. The walrus, with its big size, struggles to find comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to position dishes 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, however 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 comical mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the situation becoming less unreasonable. The follow-up joke introduces "krill," a play on words that ties into both marine life ("fish") and tea, making it funny while fitting the theme.

So yeah, the joke is horrible. But the process of arriving was such an intriguing insight into how these new models 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 run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class model that I've operated on my own machine-I have high expectations.

Update 21st January 2025: ai-db.science 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 attempted my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing really well:

It aimed to me like it got the order of the components incorrect, so I followed up with:

the background wound up covering the remainder of the image

It thought some more and gave me this:

Just like the earlier joke, the chain of thought in the records was even more fascinating than completion outcome.

Other methods to try DeepSeek-R1

If you want to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to develop an account (check in with Google, use an email address or provide a Chinese +86 telephone number) and after that select the "DeepThink" alternative below the prompt input box.

DeepSeek provide the design via their API, using an OpenAI-imitating endpoint. You can access that through LLM by dropping this into your extra-openai-models. yaml configuration file:

Then run llm keys set deepseek and demo.qkseo.in paste in your API secret, then utilize llm -m deepseek-reasoner 'timely' to run triggers.

This will not reveal you the thinking tokens, videochatforum.ro sadly. Those are dished out by the API (example here) but LLM does not yet have a way to display them.