xzuyn

Results 10 comments of xzuyn

my "fix" for this currently is disabling FreeSync (for TABG game only in radeon settings), but that just ignores the problem.

what does ai or blockchain have to do with a crosshair? its not even on april fools. kinda makes me not trust this software now

it does, but like I said in my second comment, that kinda just avoids the problem. if its a problem with electron itself, I get that you have no power...

> ran into the following runtime error with the `euler_scale_model_input` submodel: Yea, I noticed that too. It would work fine with 512x512, but 768x768 would break. DEIS and some others...

I should have asked you sooner: What issues are you experiencing when trying to run with AMD? Is it on Windows, or is it not supported by ROCm? As far...

> Couldn't reproduce this with rocm-6.0.0 and gfx100 (7900XTX). Bitsandbytes had errors (even trying to do a simple import on interactive python) and axolotl would not run anything. I downgraded...

any progress on this? we've been using onnx for a while with good results. I can personally get to 1088x1088 (or 876x1344) with my rx 480 8gb using max attention...

after you've installed the extension, open up inspect element and go to the network tab. after that play whatever vod you want and search for `.m3u8` in the network tab....

That wouldn't explain this though. > It's like it's hardcoded to set to 32001 and to 32000 even if that's not what the model uses. ![Screenshot_from_2024-05-13_21-21-54](https://github.com/ggerganov/llama.cpp/assets/16216325/60422554-1f79-4535-bb09-c729baf86382) My model also was...

> The link to your model is 404 not found. Sorry, I unprivated it. > Anyway, did you check if `added_tokens.json` is set correctly? (The JSON you posted above is...