|  Post Reply

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

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

DeepSeek-R1-Zero seems the base model. It's over 650GB in size and, like most of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences obstacles such as unlimited repeating, bad readability, and language mixing." ... so they likewise released:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and thinking jobs". That a person is likewise MIT licensed, 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 designs are something I can quickly have fun with myself. That's where the brand-new distilled designs are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is an interesting flex! They have actually 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 models have an MIT license connected, which I'm uncertain is compatible with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?

(I likewise just discovered the MIT license files say "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 designs are interesting beasts.

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

Quantized variations are already beginning to show up. Up until now I've attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly fun to play with.

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

First I brought and championsleage.review ran the design using Ollama itself:

This downloads around 8.5 GB of design data and disgaeawiki.info starts an interactive chat user interface.

Once the model has been brought, LLM can speak to it too. I choose using LLM for experiments because it logs everything to SQLite for later expedition.

I set up the plugin and ran it like this:

Each response begins with a ... pseudo-XML tag containing the chain of idea used to assist produce the reaction. For "a joke about a pelican and a walrus who run a tea room 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 intriguing combination. Let me think of how these two characters may engage in a humorous situation.

First, let's consider their attributes. Pelicans are known for their long beaks and wiki.vst.hs-furtwangen.de Webbed feet, often 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 2 into a tea space setting is already a funny image.

[...]

It then thought for 20 paragraphs before outputting the joke! Here's the complete records 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 huge size, struggles to discover comfy chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to help, utilizes its beak to place saucers on the table, triggering a couple of spills.

After a series of humorous incidents, ratemywifey.com the walrus looks up and says with a grin, "This isn't so fishy any longer." The pelican smirks and says, "Maybe not, but we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and thatswhathappened.wiki Walrus run an unlikely tea space. Their sizes lead to comedic mayhem.
- Punchline: "This isn't so fishy any longer" is a pun on the circumstance becoming less ridiculous. The follow-up joke presents "krill," a play on words that connects into both marine life ("fish") and tea, tandme.co.uk making it humorous while fitting the style.

So yeah, the joke is awful. But the process of arriving was such a fascinating insight into how these brand-new designs work.

This was a fairly little 8B model. 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'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 model working like this-a 34GB download:

Can it draw a pelican?

I attempted 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 wrong, 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 transcript was far more interesting than the end outcome.

Other methods to try DeepSeek-R1

If you wish to attempt the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll require to produce an account (sign in with Google, utilize an email address or provide a Chinese +86 telephone number) and orcz.com after that pick the "DeepThink" option below the prompt input box.

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

Then run llm keys set deepseek and paste in your API secret, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.

This will not reveal you the thinking tokens, unfortunately. Those are served up by the API (example here) however LLM doesn't yet have a way to show them.

Add comment

INDEXING JOURNAL: