ipfans
ipfans
@njouanin hi, can we release a minor version to fix this issue?
I still no idea to support new platform. E.g. I want to add support for STM32F107, so which file should I modify?
@andreasvc thx for your comment. It works now: ``` ➜ ~ export CFLAGS='-std=c++11' ➜ ~ pip install re2 Collecting re2 Using cached re2-0.2.22.tar.gz Building wheels for collected packages: re2 Running...
It seems like still fallback to CPU when I run ollam powered by zluda: ``` >zluda.exe -- %UserProfile%/AppData/Local/Programs/Ollama/ollama.exe serve time=2024-02-29T09:31:02.916+08:00 level=INFO source=images.go:710 msg="total blobs: 5" time=2024-02-29T09:31:02.928+08:00 level=INFO source=images.go:717 msg="total unused...
@Inokinoki Thanks for you explanation. Could you also share the file/line that we can change?
Thanks a lot for your works. I just tried https://github.com/dhiltgen/ollama/releases for rocm support, but I found it will be failed when using mixtral model. Here is a log for this...
@trim21 Hmm, I almost forgot this. Maybe we can send a PR first.
I tried to test it and chose to use two examples images: musk_resize.jpeg and post2.jpeg(in this repo) the parameters: ```python controlnet_conditioning_scale=0.8, strength=mask_strength, ip_adapter_scale=0.3, # keep it low ``` the generated...
@zhao1012 this is an issue tracking for Ollama, please stay on topic. For issues of MiniCPM-2B, please contact @ShengdingHu or open an issue in the MiniCPM repository to learn how...
我想这些问题不了解也可以解决部分，比如，善用工具 https://www.robustperception.io/optimising-go-allocations-using-pprof/