GlasslessPizza
GlasslessPizza
After an afternoon of testing, I finally was able to determine why my outputs had color banding issues that weren't present in the original footage. In short, FFmpeg essentially defaults...
Pytube version: 15.0.0 (with [this workaround](https://github.com/pytube/pytube/issues/1707#issuecomment-1616464219) applied) Python version: 3.10.10 For some videos with alot of streams, PyTube only detects some of them. To Reproduce Calling `print(YouTube("https://www.youtube.com/watch?v=jCMAsVEFlfQ").streams)` has some streams...
If I quantize [this gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q8_0.gguf) with [this imatrix](https://huggingface.co/datasets/ikawrakow/imatrix-from-wiki-train/blob/main/mixtral-8x7b-instruct-v0.1.imatrix) using this command: ``` quantize.exe --allow-requantize --imatrix mixtral-8x7b-instruct-v0.1.imatrix mixtral-8x7b-instruct-v0.1.Q8_0.gguf mixtral-8x7b-instruct-v0.1.IQ3_XXS.gguf IQ3_XXS ``` and I calculate perplexity with this command: ``` perplexity.exe -f...
The `model_downloader.py` script doesn't list the recently supported phi 3.5 moe. I'd like to also know if it's ok to use the v0.3 release from Jul 6 as-is to run...
### Name and Version ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes version: 4458 (c3f9d257) built...
Using modern version of llama.cpp as backend, the "cancel" or "regenerate" buttons don't anymore stop generation. After clicking, GPU utilization remains maxed out until generation ends on its own eventually...
Using the latest version of mikupad, the show-on-hover top probabilities function seems broken, nothing is shown. I can reproduce with llama.cpp backend version b4365 onward, works fine until b4363. In...