Simon Willison s Weblog

Aus Vokipedia
Version vom 9. Februar 2025, 16:19 Uhr von Lawanna33Z (Diskussion | Beiträge)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu: Navigation, Suche


That model was trained in part using their unreleased R1 "reasoning" design. Today they've released R1 itself, in addition to a whole family of new designs obtained from that base.


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


DeepSeek-R1-Zero seems the base design. It's over 650GB in size and, like many of their other releases, is under a tidy MIT license. DeepSeek caution that "DeepSeek-R1-Zero comes across obstacles such as unlimited repetition, poor readability, and language blending." ... so they also launched:


DeepSeek-R1-which "integrates cold-start data before RL" and "attains performance equivalent to OpenAI-o1 across mathematics, code, and thinking jobs". That a person is likewise MIT certified, and is a comparable size.


I do not have the capability to run models larger than about 50GB (I have an M2 with 64GB of RAM), so neither of these two designs 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 thick models 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 designs have an MIT license attached, which I'm uncertain works with the underlying Llama license. Qwen designs are Apache certified so possibly MIT is OK?


(I likewise simply 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 interesting beasts.


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


Quantized versions are currently beginning to show up. Up until now I have actually attempted just one of those- unsloth/DeepSeek-R 1-Distill-Llama-8B-GGUF launched by Unsloth AI-and it's really enjoyable to have fun with.


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


First I fetched and ran the design using Ollama itself:


This downloads around 8.5 GB of design data and starts an interactive chat interface.


Once the design has been fetched, LLM can talk with it as well. I choose using LLM for experiments since it logs whatever to SQLite for later exploration.


I set up the plugin and ran it like this:


Each response begins with a ... pseudo-XML tag containing the chain of thought used to help produce the . For "a joke about a pelican and a walrus who run a tea room together" that began like this:


Okay, so I need to come up with a joke about a pelican and morphomics.science a walrus running a tea space together. Hmm, that's an intriguing combination. Let me think of how these two characters may engage in an amusing circumstance.


First, let's consider their qualities. Pelicans are understood for their long beaks and Webbed feet, typically seen near the beach or water. Walruses have big teeth, thick fur, and they're usually found in colder climates, like icebergs or snowy areas. So, integrating these 2 into a tea space setting is currently an amusing image.


[...]

It then thought for 20 paragraphs before outputting the joke! Here's the full transcript 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 room together. The walrus, with its huge size, struggles to discover comfortable chairs, so it rests on the table by accident, overturning the teapot. Meanwhile, the pelican, trying to help, trademarketclassifieds.com uses its beak to place dishes on the table, triggering a couple of spills.


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


Explanation:


- Setup: Pelican and Walrus run an unlikely tea space. Their sizes cause comedic chaos.
- Punchline: "This isn't so fishy anymore" is a pun on the scenario ending up being less unreasonable. The follow-up joke presents "krill," a play on words that ties into both marine life ("fish") and asteroidsathome.net tea, making it amusing while fitting the style.


So yeah, the joke is terrible. But the procedure of getting there was such an interesting insight into how these new designs work.


This was a fairly small 8B design. I'm looking forward to experimenting with the Llama 70B variation, which isn't yet available in a GGUF I can run with Ollama. Given the strength of Llama 3.3 70B-currently my favourite GPT-4 class model that I have actually worked 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 traditional Generate an SVG of a pelican riding a bike timely too. It did refrain from doing effectively:


It aimed to me like it got the order of the elements incorrect, so I followed up with:


the background wound up covering the remainder of the image


It thought some more and provided me this:


Just like the earlier joke, the chain of believed in the records was much more intriguing than the end outcome.


Other methods to attempt DeepSeek-R1


If you wish to try the model out without installing anything at all you can do so utilizing chat.deepseek.com-you'll need to produce an account (check in with Google, utilize an email address or provide a Chinese +86 phone number) and then choose the "DeepThink" alternative listed below the timely input box.


DeepSeek provide the design via their API, utilizing an OpenAI-imitating endpoint. You can access that by means of LLM by dropping this into your extra-openai-models. yaml setup file:


Then run llm secrets set deepseek and paste in your API key, then utilize llm -m deepseek-reasoner 'prompt' to run prompts.


This won't show you the reasoning tokens, regretfully. Those are dished out by the API (example here) but LLM doesn't yet have a method to display them.

Meine Werkzeuge
Namensräume

Varianten
Aktionen
Navigation
Werkzeuge