GitLab

That design was trained in part using their unreleased R1 "thinking" design. Today they've released R1 itself, together with an entire family of new designs obtained from that base.

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

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero experiences difficulties such as limitless repetition, bad readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across math, code, and reasoning tasks". That a person is likewise MIT accredited, and is a similar 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 two designs are something I can easily play with myself. That's where the brand-new distilled models are available in.

To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and akropolistravel.com six thick models 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache accredited so perhaps MIT is OK?

(I also just noticed the MIT license files state "Copyright (c) 2023 DeepSeek" so they may 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 show up. So far I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's truly enjoyable to play with.

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

First I and ran the model using Ollama itself:

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

Once the model has actually been brought, LLM can speak with it as well. I choose utilizing LLM for experiments since it logs whatever to SQLite for later expedition.

I set up the plugin and ran it like this:

Each response starts with a ... pseudo-XML tag containing the chain of idea used to assist produce the response. For "a joke about a pelican and a walrus who run a tea space 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 about how these two characters might connect in a funny circumstance.

First, let's consider their attributes. Pelicans are known for genbecle.com their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're typically found in cooler climates, like icebergs or snowy areas. So, integrating these two into a tea space setting is already 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 choose to open a quaint little tea room together. The walrus, with its big size, struggles to find comfy chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put dishes on the table, triggering a few spills.

After a series of funny mishaps, the walrus looks up and says with a smile, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, however we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes cause comical chaos.

• Punchline: "This isn't so fishy anymore" 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, making it funny while fitting the theme.
  
  So yeah, wiki.myamens.com the joke is horrible. But the process of getting there was such a fascinating insight into how these brand-new models work.
  
  This was a fairly small 8B model. I'm eagerly anticipating checking 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 favourite GPT-4 class design that I have actually worked 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 model working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted my classic Generate an SVG of a pelican riding a bicycle 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 thought some more and provided me this:
  
  Just like the earlier joke, the chain of thought in the records was much more fascinating than completion result.
  
  Other ways to attempt DeepSeek-R1
  
  If you want to try the design out without setting up anything at all you can do so utilizing chat.deepseek.com-you'll need to produce an account (sign in with Google, utilize an email address or provide a Chinese +86 phone number) and after that pick the "DeepThink" option listed below the timely input box.
  
  DeepSeek use the design via their API, utilizing 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 paste in your API secret, then use llm -m deepseek-reasoner 'timely' to run triggers.
  
  This won't show you the thinking tokens, unfortunately. Those are dished out by the API (example here) but LLM does not yet have a way to display them.