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.
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.
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.
Have you compared it with the regular qwen? It was also very good
The main difference is speed and memory usage. Qwen is a full-sized, high-parameter model while qwen-distill is a smaller model created using knowledge distillation to mimic qwen’s outputs. If you have the resources to run qwen fast then I’d just go with that.
I think you’re confusing the two. I’m talking about the regular qwen before it was finetuned by deep seek, not the regular deepseek
I haven’t actually used that one, but doesn’t the same point apply here too? The whole point of DeepSeek is in distillation that makes runtime requirements smaller.
No cause I was already running regular (non-deepseek) qwen 14B, admittedly a heavily quantized and uncensored version, so I was just curious if it would be any better
The big difference with R1 at least is that it is trained using reinforcement learning, and it gives you an explanation of how it arrived at a solution. I find the thinking bit is really fascinating cause it really reads like a train of thought. Here’s an example of what it outputs when I ask it to write a react component with a text input and a button:
<think> Alright, the user asked for a React component that includes a text input and a button. I need to write this in a way that’s clear and functional.
First, I’ll start by setting up the basic structure of a React component. I’ll import React and useState since we’ll need state management for the input value.
Next, I’ll create a functional component called TextInputButton. Inside this component, I’ll use the useState hook to manage the text input’s value. The initial state can be an empty string.
Then, I’ll define a handler function, handleChange, that updates the state whenever the user types into the input. This function will take the event object and set the new value using setTextInputValue.
I also need a function to handle the button click. For now, I’ll use handleClick with an alert message as a placeholder. The actual functionality can be added later based on requirements.
In the return statement, I’ll structure the JSX. I’ll include an input element of type text, binding its value to the state variable and attaching the handleChange function to the onChange event. This ensures that the state always reflects the current input value.
Below the input, I’ll add a button element. On clicking this button, it will trigger handleClick. I’ll also give it a class for styling purposes, like ‘button’ which can be styled with CSS if needed.
Finally, I’ll export the component so it can be used elsewhere in the application. I’ll make sure to include comments explaining each part for clarity. </think>
Here’s a simple React component with a text input and a button:
This component:
You can use this component in your application like:
The input value is controlled through the
text
state variable, and you can access it usingtext
. When the button is clicked, thehandleClick
function will execute whatever logic you need.