1 Simon Willison's Weblog
Adam Tjalkabota bu sayfayı düzenledi 1 hafta önce


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

There’s a whole lot of things in the new release.

DeepSeek-R1-Zero seems the base model. It’s over 650GB in size and, genbecle.com like many of their other releases, is under a tidy MIT license. DeepSeek warn that “DeepSeek-R1-Zero comes across challenges such as limitless repetition, bad readability, and language blending.” ... so they likewise released:

DeepSeek-R1-which “includes cold-start information before RL” and “attains performance comparable to OpenAI-o1 across math, code, and reasoning tasks”. That a person is likewise MIT licensed, and ratemywifey.com is a comparable size.

I do not have the capability 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 new distilled designs are available in.

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

This is a remarkable flex! They have models based upon 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 models are Apache licensed so possibly MIT is OK?

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

Licensing aside, trade-britanica.trade these distilled designs are interesting monsters.

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

Quantized versions are currently starting to show up. Up until now I have actually tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it’s actually enjoyable to play with.

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

First I brought and ran the design utilizing Ollama itself:

This downloads around 8.5 GB of model information and starts an interactive chat interface.

Once the design has actually been fetched, LLM can speak to it too. I choose utilizing LLM for experiments due to the fact that 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 thought used to help produce the action. 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 space together. Hmm, asteroidsathome.net that’s an intriguing mix. Let me think of how these 2 characters may connect in a funny circumstance.

First, let’s consider their characteristics. Pelicans are understood for their long beaks and Webbed feet, often seen near the beach or water. Walruses have huge teeth, thick fur, and they’re typically found in cooler environments, like icebergs or snowy areas. So, integrating these two into a tea space setting is currently an amusing image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here’s the full 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 room together. The walrus, with its huge size, has a hard time to discover comfortable chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to place dishes on the table, triggering a few spills.

After a series of humorous mishaps, the walrus searches for and states with a smile, “This isn’t so fishy anymore.” The pelican smirks and says, “Maybe not, however we do have a lot of krill in our tea!“

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes lead to comical turmoil.

  • Punchline: “This isn’t so fishy anymore” is a pun on the scenario becoming less ridiculous. The follow-up joke introduces “krill,” a play on words that ties into both marine life (“fish”) and tea, making it humorous while fitting the theme.

    So yeah, the joke is awful. But the procedure of getting there was such an interesting insight into how these new models work.

    This was a fairly little 8B model. I’m eagerly anticipating experimenting with the Llama 70B variation, which isn’t yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my preferred GPT-4 class model that I have actually operated 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 tried my classic Generate an SVG of a pelican riding a bicycle prompt too. It did refrain from doing very well:

    It aimed to me like it got the order of the components wrong, higgledy-piggledy.xyz 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, utahsyardsale.com the chain of thought in the records was far more fascinating than completion outcome.

    Other methods to attempt DeepSeek-R1

    If you want 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 (indication in with Google, use an email address or provide a Chinese +86 contact number) and after that pick the “DeepThink” choice below the timely input box.

    DeepSeek offer the design through their API, using an . 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, then use llm -m deepseek-reasoner ‘timely’ to run triggers.

    This won’t reveal you the thinking tokens, unfortunately. Those are served up by the API (example here) however LLM does not yet have a method to show them.