1 Simon Willison's Weblog
sharronritchar edited this page 2025-02-09 23:06:03 +08:00


That model was trained in part using their unreleased R1 "thinking" model. Today they have actually launched R1 itself, in addition to an entire household of new designs obtained from that base.

There's a whole lot of stuff in the new release.

DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like the majority of their other releases, is under a clean MIT license. DeepSeek alert that "DeepSeek-R1-Zero comes across difficulties such as limitless repetition, bad readability, and language mixing." ... so they likewise released:

DeepSeek-R1-which "includes cold-start information before RL" and "attains efficiency equivalent to OpenAI-o1 throughout mathematics, code, and thinking jobs". That a person is also MIT certified, and systemcheck-wiki.de is a similar size.

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

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

This is an interesting flex! They have designs based upon Qwen 2.5 (14B, 32B, Math 1.5 B and garagesale.es Math 7B) and Llama 3 (Llama-3.1 8B and Llama 3.3 70B Instruct).

Weirdly those Llama designs have an MIT license connected, gdprhub.eu which I'm uncertain works with the underlying Llama license. Qwen designs are Apache licensed so maybe MIT is OK?

(I likewise just discovered the MIT license files state "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 interesting monsters.

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

Quantized variations are currently beginning to appear. So far I've attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and yogaasanas.science it's actually enjoyable to have fun with.

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

First I brought and ran the model using Ollama itself:

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

Once the model has been brought, LLM can speak to it too. I choose using LLM for experiments due to the fact that it logs everything to SQLite for later expedition.

I installed the plugin and ran it like this:

Each action starts with a ... pseudo-XML tag containing the chain of thought utilized to assist create the action. For "a joke about a pelican and a walrus who run a tea space together" that began 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 a fascinating combination. Let me think about how these two characters may connect in an amusing scenario.

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, and they're typically discovered in colder climates, like icebergs or snowy locations. 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 full 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, struggles to find comfortable chairs, so it sits on the table by accident, knocking over the teapot. Meanwhile, the pelican, attempting to help, uses its beak to place saucers on the table, triggering a few spills.

After a series of funny accidents, the for and states with a smile, "This isn't so fishy anymore." The pelican smirks and mentions, "Maybe not, but we do have a lot of krill in our tea!"

Explanation:

- Setup: Pelican and Walrus run an unlikely tea room. Their sizes result in comedic mayhem.