1 Simon Willison's Weblog
Abigail Staley editou esta página 1 semana atrás


That model was trained in part using their unreleased R1 “reasoning” model. Today they have actually released R1 itself, together with an entire household of brand-new designs obtained from that base.

There’s an entire lot of things in the new release.

DeepSeek-R1-Zero seems the base model. It’s over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek warn that “DeepSeek-R1-Zero comes across obstacles such as limitless repetition, poor readability, and language mixing.” ... so they also launched:

DeepSeek-R1-which “incorporates cold-start data before RL” and “attains efficiency comparable to OpenAI-o1 throughout math, code, and reasoning jobs”. That a person is likewise MIT licensed, and is a comparable size.

I don’t have the ability to run designs bigger than about 50GB (I have an M2 with 64GB of RAM), so neither of these 2 designs are something I can easily have fun with myself. That’s where the brand-new distilled models are available in.

To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and 6 thick designs distilled from DeepSeek-R1 based on Llama and Qwen.

This is an interesting flex! They have actually designs based on Qwen 2.5 (14B, 32B, Math 1.5 B and Math 7B) and fishtanklive.wiki 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 accredited so perhaps MIT is OK?

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

Licensing aside, these distilled designs are remarkable beasts.

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

Quantized versions are currently beginning to appear. Up until now I have actually attempted just among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it’s really fun to play with.

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

First I fetched and ran the design using Ollama itself:

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

Once the design has been fetched, LLM can speak to it as well. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each reaction starts with a ... pseudo-XML tag containing the chain of thought utilized to help create the reaction. For “a joke about a pelican and a walrus who run a tea room 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, that’s an intriguing mix. Let me think about how these two characters might in a funny scenario.

First, let’s consider their qualities. Pelicans are known for their long beaks and Webbed feet, annunciogratis.net often seen near the beach or water. Walruses have big teeth, thick fur, and they’re typically discovered in cooler environments, like icebergs or 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 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, with its big size, has a hard time to find comfy chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to assist, uses its beak to put dishes on the table, triggering a few spills.

After a series of humorous accidents, 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 great deal of krill in our tea!“

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes result in comical turmoil.

  • Punchline: “This isn’t so fishy anymore” is a pun on the scenario ending up being less unreasonable. 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 awful. But the procedure of getting there was such a fascinating insight into how these brand-new models work.

    This was a fairly small 8B design. I’m looking forward to 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 have actually 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 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 wiki.snooze-hotelsoftware.de provided me this:

    As with the earlier joke, the chain of thought in the transcript was even more fascinating than completion outcome.

    Other methods to attempt DeepSeek-R1

    If you wish to try the model out without setting up anything you can do so using chat.deepseek.com-you’ll require to create an account (indication in with Google, utilize an email address or supply a Chinese +86 contact number) and then pick the “DeepThink” choice listed below the prompt input box.

    DeepSeek offer the model via their API, utilizing 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 key, then utilize llm -m deepseek-reasoner ‘timely’ to run prompts.

    This will not show you the reasoning tokens, regretfully. Those are dished out by the API (example here) but LLM doesn’t yet have a way to show them.