GB
GB
I am using fam/ui/app.py with the defaults it sets, it seems to be trying to use a decimal, yet I can't see how to fix that anywhere.
I'm seeing this now after getting past the past issues, this is on mps m2 ultra, guessing it can't install the flash-attn module hence the part of it that would...
> > I also realized that there is already a PR open for docker support in #17. We should probably join forces over there? > > Yes, please! Definitely agree,...
> Are you thinking about ASS as output and/or input format? Output format would be an easier first step since the internal model might not (today) support all the ASS...
Any pointers to know for when I have some time, about how the input is architected. I looked at the SRT one, it seems like going SRT and basic ASS...
Will this be merged soon? I'm seeing that this would help me be able to use this tool without waiting too long.
I made a diff of what I have done to use mps although I am not 100% sure it is actually using the GPU on my M2 or using it...
Curious what the path is to get the quality working better? Is it known piece of work TODO or more research TODO before knowing? I can poke and dig more,...
Ah so the model keeps context actually? I keep context but it does feel like what you are saying is probably occurring. I guess this is something lower level to...
I did this and suspect it will allow me to have a clean slate each run? ``` diff --git a/src/candle_gemma.rs b/src/candle_gemma.rs index 913bd24..b02b2d1 100644 --- a/src/candle_gemma.rs +++ b/src/candle_gemma.rs @@ -59,6...