Simon Willison's Weblog
Abigail Grayson 于 4 月之前 修改了此页面


That model was trained in part using their unreleased R1 "thinking" model. Today they've released R1 itself, along with an entire household of brand-new models obtained from that base.

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

DeepSeek-R1-Zero appears to be the base model. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek warn that "DeepSeek-R1-Zero experiences challenges such as endless repeating, bad readability, and language mixing." ... so they also released:

DeepSeek-R1-which "incorporates cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout math, code, and thinking jobs". That a person is also MIT licensed, and is a comparable size.

I do not have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), photorum.eclat-mauve.fr so neither of these two models are something I can quickly 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 six thick designs distilled from DeepSeek-R1 based upon Llama and Qwen.

This is a fascinating 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 wavedream.wiki Llama 3.3 70B Instruct).

Weirdly those Llama models have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so possibly MIT is OK?

(I also simply saw 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, these distilled models are interesting beasts.

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

Quantized versions are currently 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 have fun with.

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

First I brought and ran the model utilizing Ollama itself:

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

Once the design has actually been brought, LLM can talk to it too. I choose utilizing LLM for experiments since it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of thought used to assist generate the response. 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, that's an interesting combination. Let me believe about how these 2 characters might interact in a funny circumstance.

First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have huge teeth, thick fur, and they're typically found in cooler climates, like icebergs or wiki.rrtn.org snowy locations. So, combining these 2 into a tea space setting is already a funny image.

[...]
It then believed for 20 paragraphs before outputting the joke! Here's the full transcript 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 space together. The walrus, with its big size, has a hard time to discover comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to position saucers on the table, causing a few spills.

After a series of comical accidents, the walrus looks up and states with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "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 result in comedic chaos.

  • Punchline: "This isn't so fishy anymore" 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 terrible. But the procedure of arriving was such an intriguing insight into how these new models work.

    This was a fairly little 8B model. I'm anticipating trying the Llama 70B variation, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70 my favourite GPT-4 class design that I've run on my own machine-I have high expectations.

    Update 21st January 2025: photorum.eclat-mauve.fr 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 tried 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 aspects wrong, 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, the chain of thought in the transcript was even more interesting than the end outcome.

    Other ways to try DeepSeek-R1

    If you desire to try the model out without installing anything you can do so using chat.deepseek.com-you'll require to develop an account (check in with Google, kigalilife.co.rw utilize an email address or provide a Chinese +86 phone number) and then choose the "DeepThink" alternative listed below the prompt input box.

    DeepSeek provide 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 setup 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 show you the thinking tokens, regretfully. Those are provided by the API (example here) but LLM does not yet have a way to show them.