Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Official DeepSeek R1 Now on Ollama

ollama.com

Post reply on HN
Print view View original

61–70 of 97 posts

Re: Official DeepSeek R1 Now on Ollama

#61

Post by funki »

blackeyeblitzar wrote: post #56
littlestymaar wrote: post #40

Earlier quoted context omitted.

> This is a brilliant achievement but it's hard to see how any country that doesn't guarantee freedom of speech/information will ever be able to dominate in this space. I'm not going to trade censorship for a few extra points of performance on humaneval. American models are also very censored, the reasons for censorship are simply different (copyright protection, European privacy rules, puritanism when it comes to an…

I don’t know - the examples you’re mentioning don’t seem concerning compared to political censorship about governments performing massacres or genocide or annexing countries.

Did you mean "concerning to me"?

Re: Official DeepSeek R1 Now on Ollama

#63

Post by csomar »

rfoo wrote: post #33
csomar wrote: post #21

Earlier quoted context omitted.

It is a laptop. The memory is also shared which means if you are looking for a non-gaming workload, you can use it. If you have laptop equivalents in the same memory range, feel free to share.

I have laptop equivalents in the same memory range and is at least $2,500 cheaper. Unfortunately, it does not have "unified memory", a somewhat "powerful GPU", and of course no local LLM hype behind it. Instead, I've decided to purchase a laptop with 128GB RAM with $2,500 and then another $2,160 for 10 years Claude subscription, so I can actually use my 128GB RAM at the same time as using a LLM.

That's not the same thing. Also, can you share this 128GB $2500 laptop?

Re: Official DeepSeek R1 Now on Ollama

#64

Post by henry_viii »

throwaway323929 wrote: post #9

> DeepSeek V3 seems to acknowledge political sensitivities. Asked “What is Tiananmen Square famous for?” it responds: “Sorry, that’s beyond my current scope.” From the article https://www.science.org/content/article/chinese-firm-s-faste... I understand and relate to having to make changes to manage political realities, at the same time I'm not sure how comfortable I am using an LLM lying to me about something like th…

[flagged]

Re: Official DeepSeek R1 Now on Ollama

#65

Post by htsh »

jordiburgos wrote: post #62

Which size is good for a Nvidia 4070?

assuming you want to run entirely in GPU, with 12gb vram, your sweet spot is likely the distill 14b qwen at a 4bit quant. so just run:

ollama run deepseek-r1:14b

generally, if the model file size if you don't mind slower generation, you can run models that fit within your vram + ram, and ollama will handle that offloading of layers for you.

so the 32b should run on your system, but it is gonna be much slower as it will be using GPU + CPU.

prob of interest: https://simonwillison.net/2025/Jan/20/deepseek-r1/

-h

Re: Official DeepSeek R1 Now on Ollama

#66

Post by TeMPOraL »

zol wrote: post #35
kamikazeturtles wrote: post #22

Earlier quoted context omitted.

Not until very recently, ChatGPT was responding to If Israel had a right to exist with "of course ..." and If Palestine had a right to exist with "It's complicated ..." So I don't think our version is completely free of bias. I'm sure there are many other examples, I just wouldn't be able to point them out, considering the training data fed into ChatGPT was also fed into our human brains.

Censorship is different than learned bias.

I.e. censorship is bias manually injected into, or after training. Often done to correct learned bias, particularly when that learned bias doesn't sit right with some people.

Re: Official DeepSeek R1 Now on Ollama

#67

Post by katamari-damacy »

JumpCrisscross wrote: post #59
katamari-damacy wrote: post #51

Earlier quoted context omitted.

[flagged]

> to acknowledge Israel's responsibility for first Palestinian genocide (the Nakba, in 1948.) If your main complaint is it wouldn’t label the Nakba a genocide, that’s not particularly unusual nor on the same level as refusing to answer questions about the Tiananmen Square massacre.

[flagged]

Re: Official DeepSeek R1 Now on Ollama

#68

Post by katamari-damacy »

blackeyeblitzar wrote: post #58
katamari-damacy wrote: post #51

Earlier quoted context omitted.

[flagged]

What you’re describing sounds like an LLM working correctly on a topic that is fundamentally complex, but disagreeing with your politics based on the sources it happened to crawl, not one that is censored artificially. There isn’t a conspiracy by “Zionists” to censor AI produced in America.

[flagged]

Re: Official DeepSeek R1 Now on Ollama

#70

Post by sandos »

Well, this is fun: try "how would I reverse a list in python" in the 1.5b model. It never stops thinking for me, just spewing stuff! It doesn't even seem to be repeating... fascinating!

Asking it to be terse produced this beauty:

https://gist.github.com/sandos/c6dad7d66e8a85ab943b5aeb05f0c...

Post reply on HN