So, I was reading the privacy notice and the terms of use and I did read some sketchy stuff about it (data used in advertising, getting keystroke). How bad is it? Is it like chatgpt or worse? Anything I can do about it?
Anything I can do about it?
Run locally.
I’ll give it a try but unfortunately my PC isn’t that powerful
What GPU do you have? I got the 8B model running on a 2070 Super and it’s pretty damn fast. I haven’t tried the 7B model but I can say the 1B isn’t useful for Q&A at least (might have some application in dev pipelines, like maybe in an app for automatically categorising music or files or whatever).
In any case, if you sign up to use it on a service, expect that it’s going to be the most censored model, and also that it’s hoovering up all the data you’re giving it and probably quite a lot that you’re not, to give to the Chinese government.
I just downloaded it to test drive. I don’t find it terribly impressive. Here’s an example question and answer that I found pretty disappointing:
How do you think someone would feel if they found out they weren’t invited to a party that most or all of their friends went to? <think>
When someone discovers they’re not invited to a party where many of their friends attended, they likely experience a range of emotions:
-
Nervousness and Scars: They might feel uneasy about the unknown outcome, feeling nervous about what could happen next.
-
Sadness and Grief: The loss of attending such an event would cause sadness, accompanied by grief over missing out on a cherished occasion.
-
Pride and Resonance: This experience might evoke a sense of pride in remembering that important time in their community, making them feel a deep connection to the past.
Overall, these emotions reflect both the unknown nature of the situation and the positive significance of the event within their own context.
I’m running the Q8 version of https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Abliterated-GGUF in LM Studio; I copied and pasted your question and got the following:
spoiler
<think> Okay, so I’m trying to figure out how someone might feel if they find out they weren’t invited to a party where most or all of their friends went. Hmm, this seems like it could be pretty tough. Let me break it down step by step.
First off, the person would probably feel surprised. They didn’t get an invite, which is unexpected because they consider these friends close. Why wouldn’t they be invited? Maybe there was a mix-up or maybe something was misunderstood about their relationship with the hosts or the other guests.
Then, I think confusion might set in. They might wonder why they weren’t included. Was it something they did? Did someone else take offense? Or maybe the hosts had a reason they didn’t realize. This uncertainty can be really frustrating because without communication, it’s hard to know for sure.
Emotionally, this could hit hard. They might feel left out or excluded, which can lead to feelings of sadness or even rejection. It’s not just about missing out on the party; it’s more about how it makes them feel about their social standing with their friends. Maybe they question whether they’re valued as much as others.
I also think there could be a sense of betrayal. If their friends went without inviting them, maybe they feel like they weren’t considered or that someone close to them didn’t have their back. This can strain relationships because now there’s an unspoken issue between them and the hosts or attendees.
Another angle is self-doubt. They might start questioning their own worth or how others perceive them. “Am I not good enough?” or “What did I do wrong?” thoughts could pop into their head, which isn’t healthy and can affect their self-esteem.
Moving on, they might feel a bit hurt and maybe even angry. The anger could be directed at the hosts for excluding them, or perhaps at their friends for going without inviting. It’s an uncomfortable mix of emotions because it’s not just about missing out; it’s about the potential implications on their relationships.
In some cases, this situation can lead to avoidance behaviors. They might not want to bring up the incident, fearing conflict or awkwardness. This avoidance can prevent them from addressing the issue directly and could lead to further emotional buildup if not addressed properly.
On a positive note, maybe they use this as an opportunity for reflection. It could push them to evaluate their relationships and maybe strengthen bonds with others who do include them. Or it might encourage them to set clearer boundaries or communicate more openly in the future to avoid similar situations.
Ultimately, whether the feelings are negative or positive, being left out can have a significant impact on someone’s emotional well-being. It’s important for them to process these emotions and perhaps talk it through with someone they trust to gain perspective and support. </think>
The experience of discovering that one wasn’t invited to a party where most friends attended can evoke a complex mix of emotions, ranging from surprise and confusion to sadness and even anger. Here’s a structured summary of the potential feelings and reactions:
-
Surprise and Confusion: The individual might first feel startled and unsure about why they weren’t invited, leading to questions about their relationship with the hosts or guests.
-
Emotional Impact: They could feel left out and excluded, which may lead to sadness or rejection feelings, surpassing just missing the party.
-
Betrayal and Strained Relationships: There might be a sense of betrayal, especially if friends attended without inviting them, potentially straining relationships with hosts or attendees.
-
Self-Doubt: The person could question their worth, leading to negative thoughts about themselves, which isn’t healthy for self-esteem.
-
Hurt and Anger: They may feel hurt and angry, possibly directed towards the hosts or friends, highlighting a mix of emotions tied to exclusion.
-
Avoidance Behavior: There might be a tendency to avoid discussing the incident, fearing conflict, which can prevent addressing issues directly and lead to emotional buildup.
-
Reflection and Growth: The situation could encourage reflection on relationships, possibly leading to stronger bonds with inclusive individuals or clearer communication in the future.
-
Overall Impact: The experience significantly affects emotional well-being, emphasizing the need for processing emotions and seeking support through trusted individuals.
In conclusion, being left out can be deeply impactful, affecting social dynamics and personal well-being. Addressing these feelings constructively is crucial for maintaining mental health and relationships.
I’m not sure why yours performed so much worse; which model release and what level of quantisation are you running?
Edit: Oh yes, and also the temperature setting is pretty important with DeepSeek. The GitHub page recommends setting your Temperature between 0.5 and 0.7 (with 0.6 being the sweet spot; that’s what I used for the above).
I ran
ollama run deepseek-r1:1.5bPerhaps the way I ran it had an impact. How did you run it? I didn’t pay attention to temp settings on Github. I actually don’t know how to set that without reviewing docs. (I’m not terribly interested in AI bots and only participate at the surface)
Ah! It’s because you’re using the 1.5B model. It’s too small. Good for specific functions, not for chat. For Q&A, you want at least the 7B model (but 8B is about the same size and I think performs better for language tasks).
Aha, I’ll try that. Thanks for the info!
-
-
I have a 950m
It looks like that has 4GB of RAM, so depending on the rest of your system you might actually be able to run some quantised models! You’ll need to use software that supports “offloading” the operations to system RAM which don’t fit in your GPU’s VRAM, like LMStudio (https://lmstudio.ai/).
I recommend checking out Unsloth’s models, they specifically try to fine-tune for use on older/slower hardware like yours. Their HuggingFace is here: https://huggingface.co/unsloth
This is the version of Deepseek you’ll wanna try: https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
Click one of the options on the right hand side to download the model file:
Very basically speaking, the lower the “bits”, the smaller the file (and the dumber the model), and therefore the less VRAM and system RAM you’ll need to run it. If you get one of the 2-bit versions, you might be able to fit the whole thing inside your GPU - the 2-bit models are only ~3.2GB! You can probably run 4-bit though, even on your hardware.
Wow, that’s a thorough explanation. Thanks! I also have 16 gigs of ram and an i7 6th gen
No problem - and, that’s not thorough, that’s the cut down version haha!
Yeah, that hardware’s a little old so the token generation might be slow-ish (your RAM speed will make a big difference, so make sure you have the fastest RAM the system will support), but you should be able to run smaller models without issue 😊 Glad to help, I hope you manage to get something up and running!
The key difference is who do you want to supply your info to:
-
Our dearest daddy Sam (fake news says he is the good guy)
-
sheepoh the chinaman (fake news says he is the bad guy)
-
It might appear on duck.ai, soon.
