LostGoatOnHill

joined 10 months ago
sorted by: new top controversial old
2
Best option for fqdn to lan PCs, VMs, and services (alien.top)
 

Welcome suggestions on best option for being able to use fqdn in place of ip:port for lan PCs, VMs, and services. Not looking yet to expose anything externally to internet. Thanks

1
FQDNs for lan bare metal PCs, proxmox VMs and services (alien.top)
 

Hi,

Have a bunch of PCs, VMs, and services like pihole self-hosted. Still using their IP:port to reference. Obviously would prefer to use FQDNs. Understand something like pihole DNS server could be used for IPs, but doesn’t allow for unique FQDNS for IP:port combos.

Suggestions for simple, lightweight solution most welcome, thanks

1
Any good guides on building own datasets to then fine tune Mistral-based or similar models for completion? (alien.top)
 

Looking to move on in the next step of my LLM learning journey and:

a) generate a q&A dataset, say with GPT-4

b) use the dataset to instruction fine tune a 7B variant of mistral and evaluate

The Q might be to give me a sumamrised history of a company, with the dataset answer generated by GPT-4, to fine-tune the instruction fine tuned mistral 7B model.

If you know of any good guides for this, I’d highly appreciate, thank-you

​

EDIT: Reposted to fix title, god damn iPad auto complete!

Why are you running local models? What are you doing with them? in c/localllama@poweruser.forum
[–] LostGoatOnHill@alien.top 1 points 10 months ago

Love your post and ambitions, very inspiring. Looking to do similar, with family engaging assistant connecting to home automation and private data. Look forward to seeing more on what you build, anywhere in particular you share aside from here?

What kind of performance should we expect? in c/localllama@poweruser.forum
[–] LostGoatOnHill@alien.top 1 points 10 months ago

Sounds like you are executing that with CPU. when you do nvidia-smi, do you see memory and GPU consumption?