download all files in specific folder from hugging face model

 refer to code:

.

# Download all files from the IP-Adapter/sdxl_models folder

from huggingface_hub import snapshot_download

# Download the sdxl_models folder and its contents

snapshot_download(

repo_id="h94/IP-Adapter",

repo_type="model",

local_dir="./IP-Adapter_sdxl_models",

allow_patterns=["sdxl_models/*"]

)

..

It download all files under the sdxl_models folder.

Thank you.

Download specific model from hugging face

 refer to code

.

import os

import shutil

from huggingface_hub import hf_hub_download

# Repository name

repo_id = "h94/IP-Adapter"

# Directory to save the downloaded files

local_directory = "./models/image_encoder"

# Ensure the local directory exists

os.makedirs(local_directory, exist_ok=True)

# List of files to download

files_to_download = [

"models/image_encoder/config.json",

"models/image_encoder/model.safetensors",

"models/image_encoder/pytorch_model.bin"

]

# Download each file and move it to the desired directory

for file in files_to_download:

file_path = hf_hub_download(repo_id=repo_id, filename=file)

# Construct the destination path

dest_path = os.path.join(local_directory, os.path.basename(file))

# Move the file to the destination path

shutil.move(file_path, dest_path)

print(f"Downloaded and moved to {dest_path}")

..

Thank you.

other option is

file_path = hf_hub_download(repo_id=repo_id, filename=file, cache_dir=local_directory, force_download=True)

draw image as grid on notebook

simply check below code and example result.

.

def image_grid(imgs, rows, cols):

assert len(imgs) == rows*cols

w, h = imgs[0].size

grid = Image.new('RGB', size=(cols*w, rows*h))

grid_w, grid_h = grid.size

for i, img in enumerate(imgs):

grid.paste(img, box=(i%cols*w, i//cols*h))

return grid

# read image prompt

image = Image.open("assets/images/statue.png")

depth_map = Image.open("assets/structure_controls/depth.png")

image_grid([image.resize((256, 256)), depth_map.resize((256, 256))], 1, 2)

..

Thank you.

Unknown parameter in retrievalConfiguration.vectorSearchConfiguration: "overrideSearchType", must be one of: numberOfResults

 Error in AWS bedrock like:

Unknown parameter in retrievalConfiguration.vectorSearchConfiguration: "overrideSearchType", must be one of: numberOfResults

Solution 

Update boto3 sdk as latest one.

The parameters changed on 2024-03-27.

refer to here: https://awsapichanges.com/archive/changes/cd42c1-bedrock-agent-runtime.html

Thank you!