Scaricare un modello di fondazione personalizzato e impostare l'archiviazione

Caricare il modello su IBM Cloud Object Storage utilizzando l'IBM Aspera Transfer SDK

Prerequisiti:

• Scaricare il IBM Aspera Transfer SDK. Fate clic su questo link.
• Impostare queste variabili d'ambiente:
  • Percorso di IBM Aspera Transfer SDK come path-to-aspera
  • Percorso della cartella con il modello come path-to-model-folder
  • Nome del secchio in cui trasferire il modello come bucket-name
  • La chiave API per l'archiviazione degli oggetti nel cloud come api-key
  • L'ID dell'istanza del servizio di cloud object storage come cos-service-instance-id
  • L'endpoint del servizio di memorizzazione degli oggetti nel cloud come cos-service-endpoint

Utilizzate questo script per caricare il vostro modello su IBM Cloud Object Storage utilizzando il IBM Aspera Transfer SDK:

import grpc
import sys
import time, subprocess
import json
import os.path
import os.environ

import transfer_pb2 as transfer_manager
import transfer_pb2_grpc as transfer_manager_grpc

path_to_aspera = os.environ['path-to-aspera']
sys.path.append(f'{path_to_aspera}/connectors/python')

def start_aspera_daemon():
    config_path = f'/{path_to_aspera}/config/asperatransferd.json'
    daemon_path = f'/{path_to_aspera}/bin/asperatransferd'

    # Start the daemon
    process = subprocess.Popen([daemon_path, '--config', config_path])
    print(f"Started Aspera Transfer SDK daemon with PID {process.pid}")
    time.sleep(5)  # Increased wait time for the daemon to start properly

    return process

def run():
    try:
        # create a connection to the transfer manager daemon
        client = transfer_manager_grpc.TransferServiceStub(grpc.insecure_channel('localhost:55002'))

        # create transfer spec
        transfer_spec = {
            "session_initiation":{
                "icos":{
                    "bucket": os.environ['bucket-name'],
                    "api_key": os.environ['cos-api-key'],
                    "ibm_service_instance_id": os.environ['cos-service-instance-id'],
                    "ibm_service_endpoint": os.environ['cos-service-endpoint'] # example: https://s3.us-south.cloud-object-storage.appdomain.cloud
                }
            },
            "direction": "send",
            "title": "COS Upload",
            "assets": {
                "destination_root": "/model",
                "paths": [
                    {
                        "source": os.environ['path-to-model-folder']
                    }
                ]
            }
        }
        transfer_spec = json.dumps(transfer_spec)

        # create a transfer request
        transfer_request = transfer_manager.TransferRequest(
            transferType=transfer_manager.FILE_REGULAR,
            config=transfer_manager.TransferConfig(),
            transferSpec=transfer_spec
        )

        # send start transfer request to transfer manager daemon
        try:
            transfer_response = client.StartTransfer(transfer_request)
            transfer_id = transfer_response.transferId
            print(f"Transfer started with id {transfer_id}")
        except grpc.RpcError as e:
            print(f"Error starting transfer: {e.code()}: {e.details()}")
            return
        # monitor transfer status
        try:
            # Monitor transfer status
            while True:
                response = client.MonitorTransfers(
                    transfer_manager.RegistrationRequest(
                        filters=[transfer_manager.RegistrationFilter(
                            transferId=[transfer_id]
                        )]))
                for transfer_info in response:
                    print(f"Transfer info: {transfer_info}")

                    # Check transfer status in response
                    status = transfer_info.status
                    if status == transfer_manager.FAILED or status == transfer_manager.COMPLETED:
                        print(f"Transfer finished with status {status}")
                        return

                # Wait before polling again
                time.sleep(5)
        except grpc.RpcError as e:
            print(f"Error monitoring transfer: {e.code()}: {e.details()}")
    except Exception as e:
        print(f"Unexpected error: {str(e)}", file=sys.stderr)


if __name__ == '__main__':
    # Start the Aspera Transfer SDK daemon
    daemon_process = start_aspera_daemon()

    # Run the file transfer
    run()

    # Optionally, stop the Aspera daemon after transfer
    daemon_process.terminate()
    print("Aspera Transfer SDK daemon stopped")

Caricare il modello su IBM Cloud Object Storage utilizzando strumenti forniti da terze parti

È possibile utilizzare software di terze parti per caricare il modello su IBM Cloud Object Storage.

Seguite questi passi di esempio per caricare il vostro modello su IBM Cloud Object Storage usando l'interfaccia a riga di comando Amazon Web Services:

1. Installare l'interfaccia a riga di comando Amazon Web Services con pip:

   pip install awscli
   

2. Impostare le variabili d'ambiente richieste:

   export AWS_ACCESS_KEY_ID="<your access key>"
   export AWS_SECRET_ACCESS_KEY="<your secret access key>"
   export ENDPOINT="<s3 endpoint URL>"
   export BUCKET_NAME="<name of the bucket to upload the model>"
   MODEL_FOLDER=${MODEL_NAME//\//-} # The name of the created folder is based on model name.
   export MODEL_FOLDER=${MODEL_FOLDER//./-} # Just in case, we're removing slashes and dots from it.
   

3. Aggiungere il modello al bucket IBM Cloud Object Storage utilizzando l'interfaccia a riga di comando Amazon Web Services:

   aws --endpoint-url ${ENDPOINT} s3 cp ${MODEL_DIR} s3://${BUCKET_NAME}/${MODEL_FOLDER}/ --recursive --follow-symlinks