1 Simon Willison's Weblog
seanpereira26 edited this page 2025-02-11 06:37:58 +01:00


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

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

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like most of their other releases, is under a clean MIT license. DeepSeek caution that "DeepSeek-R1-Zero experiences challenges such as unlimited repeating, poor readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout mathematics, code, and reasoning tasks". That a person is also MIT certified, and is a similar size.

I do not have the capability 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 quickly play with myself. That's where the new distilled designs are available in.

To support the research study 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 a remarkable 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 have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?

(I likewise just saw the MIT license files say "Copyright (c) 2023 DeepSeek" so they might need to pay a little 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 variations are currently beginning to appear. So far I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's actually enjoyable to play with.

I'm running it utilizing 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 model information and starts an interactive chat user interface.

Once the design has been brought, LLM can speak to it also. I choose utilizing LLM for experiments because it logs everything to SQLite for later exploration.

I installed the plugin and ran it like this:

Each reaction begins with a ... pseudo-XML tag containing the chain of thought utilized to assist generate 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 room together. Hmm, that's an interesting mix. Let me think about how these 2 characters may interact in a humorous situation.

First, let's consider their attributes. 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 usually found in cooler climates, like icebergs or snowy areas. So, combining these two into a tea space setting is currently an amusing 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 decide to open a quaint little tea space together. The walrus, with its huge size, struggles to discover comfy chairs, so it sits on the table by mishap, overturning the teapot. Meanwhile, the pelican, trying to assist, utilizes its beak to position dishes on the table, triggering a few spills.

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

Explanation:

- Setup: Pelican and Walrus run a not likely tea space. Their sizes cause comedic turmoil.