1 Simon Willison's Weblog
Alphonso Escalante edited this page 2025-02-09 17:13:50 +01:00


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

There's an entire lot of stuff in the new release.

DeepSeek-R1-Zero appears to be the base model. 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 experiences challenges such as endless repetition, poor readability, and language blending." ... so they likewise launched:

DeepSeek-R1-which "includes cold-start data before RL" and "attains performance comparable to OpenAI-o1 across math, code, and reasoning tasks". That a person is likewise MIT licensed, and is a similar size.

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

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

This is a remarkable flex! They have actually designs based on 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 designs are Apache certified so maybe MIT is OK?

(I likewise just noticed the MIT license files say "Copyright (c) 2023 DeepSeek" so they may require to pay a little bit more attention to how they copied those in.)

Licensing aside, these distilled designs are interesting monsters.

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

Quantized versions are already starting to appear. Up until now I've tried simply one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF released by Unsloth AI-and it's truly fun to play with.

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

First I fetched and ran the model utilizing Ollama itself:

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

Once the model has been fetched, LLM can talk with it also. I choose utilizing LLM for experiments because it logs everything to SQLite for later exploration.

I set up the plugin and ran it like this:

Each action begins with a ... pseudo-XML tag containing the chain of idea utilized to help create the response. For "a joke about a pelican and a walrus who run a tea space together" that started like this:

Okay, so I need 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 might engage in an amusing situation.

First, let's consider their characteristics. Pelicans are known for their long beaks and Webbed feet, frequently seen near the beach or water. Walruses have big teeth, thick fur, and they're usually discovered in cooler environments, like icebergs or snowy locations. So, integrating these two into a tea room setting is currently an amusing image.

[...]
It then thought for 20 paragraphs before outputting the joke! Here's the complete 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 huge size, has a hard time to find comfy chairs, so it sits on the table by accident, overturning the teapot. Meanwhile, the pelican, attempting to assist, utilizes its beak to position saucers on the table, triggering a couple of spills.

After a series of comical mishaps, the walrus searches for and states with a grin, "This isn't so fishy any longer." 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 cause comical turmoil.