GitLab

That model was trained in part using their unreleased R1 "reasoning" model. Today they have actually released R1 itself, along with a whole family of brand-new models obtained from that base.

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

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as limitless repetition, 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 throughout mathematics, code, and thinking jobs". That one is also MIT licensed, and is a similar size.

I do not have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two 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 study neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense designs distilled from DeepSeek-R1 based on 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 is suitable with the underlying Llama license. Qwen designs are Apache licensed so possibly MIT is OK?

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

Licensing aside, these distilled models are fascinating monsters.

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

Quantized versions are currently starting to appear. Up until now I have actually tried just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released 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 brought and ran the design using Ollama itself:

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

Once the model has actually been fetched, LLM can speak with it also. I choose using LLM for experiments since 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 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 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 of how these two characters may interact in an amusing circumstance.

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, and they're usually discovered in chillier climates, like icebergs or snowy areas. 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 complete 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, pl.velo.wiki with its big size, struggles to find comfy chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, uses its beak to place saucers on the table, causing a few spills.

After a series of comical mishaps, the walrus looks up and says with a grin, "This isn't so fishy anymore." 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 result in comical turmoil.

• Punchline: "This isn't so fishy anymore" is a pun on the scenario becoming less absurd. The follow-up joke introduces "krill," a play on words that connects into both marine life ("fish") and users.atw.hu tea, making it amusing while fitting the theme.
  
  So yeah, the joke is terrible. But the procedure of arriving was such an intriguing insight into how these brand-new designs work.
  
  This was a fairly small 8B model. I'm trying 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 preferred GPT-4 class model that I've worked 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 attempted my timeless Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing effectively:
  
  It aimed to me like it got the order of the elements wrong, so I followed up with:
  
  the background ended up covering the remainder of the image
  
  It thought some more and offered me this:
  
  Similar to the earlier joke, the chain of believed in the transcript was much more fascinating than completion result.
  
  Other methods to try DeepSeek-R1
  
  If you wish to attempt the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll require to create an account (indication in with Google, utilize an email address or galgbtqhistoryproject.org offer a Chinese +86 contact number) and then pick the "DeepThink" alternative below the prompt input box.
  
  DeepSeek offer the design via 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 key, then use llm -m deepseek-reasoner 'prompt' to run prompts.
  
  This will not show you the reasoning tokens, regretfully. Those are provided by the API (example here) however LLM does not yet have a method to display them.