Simon Willison's Weblog
That model was trained in part utilizing their unreleased R1 "thinking" model. Today they have actually launched R1 itself, in addition to a whole household of new designs obtained from that base.
There's a whole lot of things in the new release.
DeepSeek-R1-Zero seems 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 comes across challenges such as limitless repetition, bad readability, and language blending." ... so they also released:
DeepSeek-R1-which "includes cold-start data before RL" and "attains efficiency comparable to OpenAI-o1 throughout math, code, and thinking jobs". That a person is likewise MIT certified, and is a comparable size.
I do not have the ability to run models larger than about 50GB (I have an M2 with 64GB of RAM), setiathome.berkeley.edu so neither of these 2 models are something I can easily have fun with myself. That's where the brand-new distilled designs are available in.
To support the research neighborhood, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and experienciacortazar.com.ar six dense designs distilled from DeepSeek-R1 based on Llama and Qwen.
This is a remarkable flex! They have actually models 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 models have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen models are Apache licensed so possibly MIT is OK?
(I likewise just noticed the MIT license files state "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 designs are fascinating monsters.
Running DeepSeek-R1-Distill-Llama-8B-GGUF
Quantized variations are already starting 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 fun 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 design utilizing Ollama itself:
This downloads around 8.5 GB of design data and forum.pinoo.com.tr starts an interactive chat user interface.
Once the model has been fetched, LLM can talk with it also. I choose using LLM for experiments because it logs everything to SQLite for later expedition.
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 generate the response. For "a joke about a pelican and a walrus who run a tea room 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 an intriguing combination. Let me think of how these 2 characters may communicate in a humorous circumstance.
First, let's consider their qualities. Pelicans are known for their long beaks and Webbed feet, often seen near the beach or water. Walruses have big teeth, thick fur, and they're usually discovered in chillier environments, like icebergs or snowy locations. So, combining these two into a tea room setting is already an image.
[...]
It then thought 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 bytes-the-dust.com a walrus choose to open a quaint little tea space together. The walrus, with its big size, struggles to find comfy chairs, so it sits on the table by mishap, knocking over the teapot. Meanwhile, the pelican, trying to assist, uses its beak to position saucers on the table, triggering a few spills.
After a series of comical accidents, the walrus looks up and states with a grin, "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 akropolistravel.com Walrus run a not likely tea room. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the circumstance ending up being less ridiculous. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and tea, making it humorous while fitting the theme.
So yeah, the joke is terrible. But the process of arriving was such a fascinating insight into how these new designs work.
This was a fairly small 8B model. I'm anticipating checking out the Llama 70B variation, which isn't yet available in a GGUF I can keep up Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class model that I've run on my own machine-I have high expectations.
Update 21st January 2025: I got this quantized version of that Llama 3.3 70B R1 distilled model working like this-a 34GB download:
Can it draw a pelican?
I attempted my timeless Generate an SVG of a pelican riding a bike prompt too. It did refrain from doing really well:
It aimed to me like it got the order of the elements wrong, bytes-the-dust.com so I followed up with:
the background wound up covering the remainder of the image
It thought some more and gave me this:
Just like the earlier joke, the chain of believed in the transcript was even more interesting than the end result.
Other methods to attempt DeepSeek-R1
If you desire to try the design out without setting up anything you can do so utilizing chat.deepseek.com-you'll need to produce an account (sign in with Google, utilize an email address or provide a Chinese +86 phone number) and after that pick the "DeepThink" option below the timely input box.
DeepSeek provide the model through their API, utilizing an OpenAI-imitating endpoint. You can access that via LLM by dropping this into your extra-openai-models. yaml setup file:
Then run llm keys set deepseek and paste in your API secret, then use llm -m deepseek-reasoner 'prompt' to run prompts.
This won't reveal you the reasoning tokens, regretfully. Those are provided by the API (example here) however LLM doesn't yet have a way to display them.