Article: https://proton.me/blog/deepseek
Calls it “Deepsneak”, failing to make it clear that the reason people love Deepseek is that you can download and it run it securely on any of your own private devices or servers - unlike most of the competing SOTA AIs.
I can’t speak for Proton, but the last couple weeks are showing some very clear biases coming out.
To be fair, most people can’t actually self-host Deepseek, but there already are other providers offering API access to it.
There are plenty of step-by-step guides to run Deepseek locally. Hell, someone even had it running on a Raspberry Pi. It seems to be much more efficient than other current alternatives.
That’s about as openly available to self host as you can get without a 1-button installer.
You can run an imitation of the DeepSeek R1 model, but not the actual one unless you literally buy a dozen of whatever NVIDIA’s top GPU is at the moment.
I saw posts about people running it well enough for testing purposes on an NVMe.
A server grade CPU with a lot of RAM and memory bandwidth would work reasonable well, and cost “only” ~$10k rather than 100k+…
Those are not deepseek R1. They are unrelated models like llama3 from Meta or Qwen from Alibaba “distilled” by deepseek.
This is a common method to smarten a smaller model from a larger one.
Ollama should have never labelled them deepseek:8B/32B. Way too many people misunderstood that.
The 1.5B/7B/8B/13B/32B/70B models are all officially DeepSeek R1 models, that is what DeepSeek themselves refer to those models as. It is DeepSeek themselves who produced those models and released them to the public and gave them their names. And their names are correct, it is just factually false to say they are not DeepSeek R1 models. They are.
The “R1” in the name means “reasoning version one” because it does not just spit out an answer but reasons through it with an internal monologue. For example, here is a simple query I asked DeepSeek R1 13B:
However, on top of its answer, I can expand an option to see its internal monologue it went through before generating the answer, which you can find the internal monologue here because it’s too long to paste.
What makes these consumer-oriented models different is that that rather than being trained on raw data, they are trained on synthetic data from pre-existing models. That’s what the “Qwen” or “Llama” parts mean in the name. The 7B model is trained on synthetic data produced by Qwen, so it is effectively a compressed version of Qen. However, neither Qwen nor Llama can “reason,” they do not have an internal monologue. This is why it is just incorrect to claim that something like DeepSeek R1 7B Qwen Distill has no relevance to DeepSeek R1 but is just a Qwen model. If it’s supposedly a Qwen model, why is it that it can do something that Qwen cannot do but only DeepSeek R1 can? It’s because, again, it is a DeepSeek R1 model, they add the R1 reasoning to it during the distillation process as part of its training. (I think they use the original R1 to produce the data related to the internal monologue which it is learns to copy.)
I’m running deepseek-r1:14b-qwen-distill-fp16 locally and it produces really good results I find. Like yeah it’s a reduced version of the online one, but it’s still far better than anything else I’ve tried running locally.
Its so cute when chinese is sprinkled in randomly hehe my little bilingual robot in my pc