Since you all love AI so much to kill someone
-
github.com/ggml-org/llama.cpp/…
Then find the right model depending on your RAM, these are guf files but this Phi 3 is hard to get as you need to log in in many ways trough git or on site or wget and curl return a 404. Don't ask me how I worked it around but then you have something like this after you build your script (Also all is in git how to's) make sure it listens to local host and taraa! then you have this . This model works with <[ ..]> brackets as system message
OK call it what it is no API and local network and easier then searching endlessly the web, there were AI is omnipresent and sold to Big Corps (your data)
So I integrated Vim (no extension but with bash) to see outputs code and added a Hallucination checker to it
then shift = v
then F5 to verify
Now tell me is this any slop?
-
System shared this topic
-
github.com/ggml-org/llama.cpp/…
Then find the right model depending on your RAM, these are guf files but this Phi 3 is hard to get as you need to log in in many ways trough git or on site or wget and curl return a 404. Don't ask me how I worked it around but then you have something like this after you build your script (Also all is in git how to's) make sure it listens to local host and taraa! then you have this . This model works with <[ ..]> brackets as system message
OK call it what it is no API and local network and easier then searching endlessly the web, there were AI is omnipresent and sold to Big Corps (your data)
So I integrated Vim (no extension but with bash) to see outputs code and added a Hallucination checker to it
then shift = v
then F5 to verify
Now tell me is this any slop?
No LLM can browse or fetch things from online. The process of training LLMs with data from online requires that you download the information yourself and then use it to train the LLM. Downloading this data can be a done via a bot or manually. The training process can done in many ways and I will not get into that here but if you ask your AI how to train it then it will tell you
.By the way a great place to get free public domain text files for training is Project Gutenberg. But, please do not use bots there as it can encumber their server, if you do use a bot then set it to pause for a decent duration between downloads.
-
No LLM can browse or fetch things from online. The process of training LLMs with data from online requires that you download the information yourself and then use it to train the LLM. Downloading this data can be a done via a bot or manually. The training process can done in many ways and I will not get into that here but if you ask your AI how to train it then it will tell you
.By the way a great place to get free public domain text files for training is Project Gutenberg. But, please do not use bots there as it can encumber their server, if you do use a bot then set it to pause for a decent duration between downloads.
@unusnemo Thanks bro ; )
