That model was trained in part utilizing their unreleased R1 "reasoning" design. Today they have actually released R1 itself, along with an entire family of brand-new designs obtained from that base.

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

DeepSeek-R1-Zero appears to be the base design. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences difficulties such as endless repetition, poor readability, and language mixing." ... so they also launched:

DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and reasoning jobs". That one is also MIT accredited, 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 two designs are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.

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

This is an interesting 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 models have an MIT license connected, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?

(I likewise just saw the MIT license files state "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 models are fascinating beasts.

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

Quantized versions are currently beginning to appear. So far I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and wavedream.wiki it's actually enjoyable to play with.

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

First I fetched and ran the model using 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 speak to it too. I choose using LLM for experiments since it logs whatever to SQLite for later expedition.

I installed the plugin and ran it like this:

Each action starts with a ... pseudo-XML tag containing the chain of idea utilized to assist generate the reaction. For "a joke about a pelican and a walrus who run a tea space 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, tandme.co.uk that's a fascinating mix. Let me consider how these 2 characters may connect in an amusing situation.

First, let's consider their attributes. Pelicans are understood for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, wiki.woge.or.at and forum.pinoo.com.tr they're normally discovered in colder environments, like icebergs or snowy locations. So, combining these two into a tea space setting is currently an amusing 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 huge size, has a hard time to discover comfortable chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to help, uses its beak to place dishes on the table, a couple of spills.

After a series of funny incidents, the walrus looks up and states with a grin, "This isn't so fishy any longer." The pelican smirks and remarks, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea space. Their sizes cause comical chaos.

• Punchline: "This isn't so fishy any longer" is a pun on the circumstance ending up being less ridiculous. 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 process of arriving was such an intriguing insight into how these new models work.
  
  This was a fairly small 8B design. I'm looking forward to experimenting with the Llama 70B variation, pipewiki.org 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: I got this quantized variation of that Llama 3.3 70B R1 distilled design working like this-a 34GB download:
  
  Can it draw a pelican?
  
  I attempted my classic Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing effectively:
  
  It aimed to me like it got the order of the aspects incorrect, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It believed some more and offered me this:
  
  Just like the earlier joke, wiki.philipphudek.de the chain of believed in the records was even more interesting than the end result.
  
  Other ways to try DeepSeek-R1
  
  If you want to attempt the design out without installing anything you can do so utilizing chat.deepseek.com-you'll need to produce an account (check in with Google, use an email address or supply a Chinese +86 phone number) and after that pick the "DeepThink" choice below the timely input box.
  
  DeepSeek use the design by means of their API, using an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
  
  Then run llm keys set deepseek and paste in your API secret, coastalplainplants.org then use llm -m deepseek-reasoner 'prompt' to run triggers.
  
  This won't show you the reasoning tokens, unfortunately. Those are provided by the API (example here) however LLM doesn't yet have a method to show them.