kuida0r3
Joined 14 years ago
Karma
198
Submissions
68
Member since
Jul 17
Recent submissions
Comment · 3 years ago
Not an expert but my understanding is retrieval+vector db enables accurate information retrieval, whereas finetuning is more focused on specific task performance and generating coherent text (maybe in a different style) generally.
Comment · 3 years ago
Andrew Ng's deeplearning.ai just released a course on this yesterday https://www.deeplearning.ai/short-courses/finetuning-large-l... - at a high level it lets one put more data into the model than fits into the prompt.
And yes your use case of a large private knowledge base is one of the prime examples she used in the course. Scenarios that are domain-specific or privacy conscious probably makes more sense for finetuning as opposed to prompting.
Comment · 3 years ago
From the jupyter notebook in the repo [0], the output is in .ply or polygon file format which is used by some 3D scanners and can be converted to STL supported by most 3D printers.
0-https://github.com/openai/shap-e/blob/main/shap_e/examples/s...
Comment · 4 years ago
Does the scaffold you use become dissolved during processing, or are edible and incorporated into a final product?
Comment · 11 years ago
From the EPA news release [0], your 2015 Q5 TDI seems to be safe: "on September 25th EPA initiated testing of all 2015 and 2016 light duty diesel models available in the U.S using updated testing procedures specifically designed to detect potential defeat devices".
It's also possible that EPA just hasn't finished testing all of the vehicles yet and your particular car may get added to the list. Sorry about that. I actually test drove the Touraeg TDI that shares the same engine and almost bought one a couple of years ago...
0 - http://yosemite.epa.gov/opa/admpress.nsf/0/4A45A5661216E66C8...