Luciano

Hi everyone! I'm on a Mac. Thanks to this issue I got to the point where `add`, `csv` and individual column commands work fine. However if I do `kanban show`...

It's true that I am, but we never reach that line. I forgot to uncomment it for the PR, but before that, the program fails on the `ggml_graph_compute (ctx0, &gf);`...

input text On Tue, Mar 21, 2023 at 9:30 AM taher ***@***.***> wrote: > ***@***.**** commented on this pull request. > ------------------------------ > > In main.cpp > : > >...

The embeddings should be the output of the last attention layer, corresponding to the last token in the input. Say I input "I am a dog", the transformer should be...

Sorry, I don't get if those are assertions or questions. I understand we want for the whole input to go through all the attention layers, then we take the representation...

Okay, I think this is working well. I tested it with multiple inputs and the embeddings make a lot of sense. Just to clarify, what this is doing is: -...

Okay, merged with master again, moved everything to llama.cpp. I addressed both changes: now everywhere that makes sense, the boolean matches the console arguments (the test in the beginning for...

I tried multiple inputs and judged from the cosine similarities between semantically similar vs not-similar sentences. I am more than open to other tests if anyone can think of them....

I agree, normalizing would be lossy. I would assume e.g. GPT-3 API gives you normalized embeddings, but it's easy enough to normalize them on consumer end so I wouldn't sweat...

Hi ggerganov, Thank you for the instructions. I did steps 1, 2 and 4, but I am not sure what we want the final program to look like in step...