Skip to content

GitLab

Open
Created by Aliza Flinn@alizaflinn3888Maintainer

Simon Willison's Weblog


That model was trained in part utilizing their unreleased R1 "thinking" model. Today they've launched R1 itself, together with an entire household of brand-new designs obtained from that base.

There's a great deal of stuff in the 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 comes across obstacles such as endless repeating, bad readability, and language blending." ... so they also launched:

DeepSeek-R1-which "integrates cold-start information before RL" and "attains efficiency comparable to OpenAI-o1 across math, code, and reasoning jobs". That one is also MIT accredited, and is a similar size.

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

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

This is an interesting flex! They have designs 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache accredited so perhaps MIT is OK?

(I also simply saw the MIT license files say "Copyright (c) 2023 DeepSeek" so they may need to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled models are remarkable monsters.

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

are currently beginning to reveal up. So far I've tried simply among those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's really fun to have fun with.

I'm running it using the combination 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 model information and starts an interactive chat interface.

Once the model has been fetched, LLM can talk to it as well. I choose utilizing LLM for experiments since it logs whatever to SQLite for orcz.com later exploration.

I set up the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to help create 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 space together. Hmm, that's an interesting combination. Let me consider how these 2 characters may engage in a funny scenario.

First, let's consider their characteristics. 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 typically discovered in cooler environments, like icebergs or snowy areas. So, combining these 2 into a tea space setting is already an amusing image.

[...]
It then thought 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 choose to open a quaint little tea room together. The walrus, with its big size, struggles to find comfortable chairs, so it rests on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to help, uses its beak to put dishes on the table, causing a few spills.

After a series of humorous mishaps, the walrus searches for and says with a grin, "This isn't so fishy anymore." The pelican smirks and remarks, "Maybe not, but we do have a great deal of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run a not likely tea room. Their sizes lead to comedic chaos.