Kristijan Jankoski
Kristijan Jankoski
Facing the same issue as of yesterday.
In my case, we're using https://huggingface.co/ausboss/llama-30b-supercot Initially we had the issue with https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor however with a restart it was working miraculously..
> Hmm the `check_file_size` is pretty rough sanitation, the file might actually be OK but it's hard to tell without looking at the file. > > You can try deactivating...
To reproduce the safetensors error with supercot: ```shell git lfs install git clone https://huggingface.co/ausboss/llama-30b-supercot docker run -v ./llama-30b-supercot:/usr/src/llama-30b-supercot --gpus all --rm ghcr.io/huggingface/text-generation-inference:sha-5ce8905 --model-id "/usr/src/llama-30b-supercot" --quantize bitsandbytes --trust-remote-code ``` Note that...
Can you do some backtracking and see which values differ?
Check the outputs of: ``` kp1, des1 = get_descriptors(img1) kp2, des2 = get_descriptors(img2) matches = sorted(bf.match(des1, des2), key= lambda match:match.distance) ``` If the descriptors do not match, check these: ```...
> The outputs of > kp1, des1 = get_descriptors(img1) > kp2, des2 = get_descriptors(img2) > matches = sorted(bf.match(des1, des2), key= lambda match:match.distance) > > is different. > i printed out...
Are you sure the harris_normalized matrices are the same?
The keypoints are the same. This means that the output of ORB is different on both platforms. I suggest opening an issue @ OpenCV.
> Can you open an issue and tag me too? No.