1 Simon Willison's Weblog
karisorell8608 edited this page 2025-02-10 01:10:03 +08:00


That model was trained in part utilizing their unreleased R1 "thinking" design. Today they've launched R1 itself, together with a whole family of new designs obtained from that base.

There's a great deal of stuff in the brand-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 clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero encounters difficulties such as unlimited repeating, poor readability, and language blending." ... so they likewise released:

DeepSeek-R1-which "includes cold-start information before RL" and "attains performance similar to OpenAI-o1 throughout math, code, and thinking jobs". That a person is likewise MIT accredited, and is a similar size.

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

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

This is a fascinating 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 is compatible with the underlying Llama license. Qwen models are Apache certified so perhaps MIT is OK?

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

Licensing aside, these distilled models are fascinating monsters.

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

Quantized variations are currently beginning to appear. Up until now I have actually attempted simply among 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 mix of Ollama, LLM and the llm-ollama plugin.

First I brought and ran the design using Ollama itself:

This downloads around 8.5 GB of model data and begins an interactive chat interface.

Once the design has been brought, LLM can talk with it as well. I prefer using LLM for experiments since it logs whatever 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 produce the response. For "a joke about a pelican and a walrus who run a tea space together" that started 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 a fascinating combination. Let me consider how these two characters might communicate in a funny 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 big teeth, thick fur, disgaeawiki.info and they're typically found in chillier climates, like icebergs or snowy locations. So, integrating these two into a tea room setting is currently 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 room together. The walrus, with its huge size, has a hard time to find comfy chairs, so it rests on the table by mishap, knocking over the teapot. Meanwhile, the pelican, attempting to help, uses its beak to put dishes on the table, triggering a few spills.

After a series of humorous mishaps, the walrus searches for vokipedia.de and states with a grin, "This isn't so fishy any longer." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

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