カスタムチェックポイントのデプロイ

{
  "type": "service_account",
  "project_id": "example-project-id",
  "private_key_id": "example-private-key-id",
  "private_key": "-----BEGIN PRIVATE KEY-----\n<private key contents>\n-----END PRIVATE KEY-----\n",
  "client_email": "ss-artifacts-reader@example-project-id.iam.gserviceaccount.com",
  "client_id": "12345678901234567890",
  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
  "token_uri": "https://oauth2.googleapis.com/token",
  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/ss-artifacts-reader%40example-project-id.iam.gserviceaccount.com",
  "universe_domain": "googleapis.com"
}

gcloud storage buckets add-iam-policy-binding gs://<BUCKET_NAME> \
    --member="serviceAccount:<SERVICE_ACCOUNT_EMAIL>" \
    --role="roles/storage.objectViewer" \
    --project=<PROJECT_ID>

gcloud storage buckets get-iam-policy gs://<BUCKET_NAME> \
    --project=<PROJECT_ID>

bindings:
- members:
  - serviceAccount:<SERVICE_ACCOUNT_EMAIL>
  role: roles/storage.objectViewer

gcloud storage cp -r <LOCAL_CONVERTED_CHECKPOINT_DIR> gs://<BUCKET_NAME>/<DESTINATION_PREFIX>/

apiVersion: sambanova.ai/v1
kind: Model

metadata:
  name: my-custom-llama3.1-8b # kubernetes resource name. Note that this must be a valid Kubernetes resource name (lowercase alphanumeric characters and hyphens only).

spec:
  name: my-custom-llama3.1-8b # serving name used in the inference API
  owner: jane@doe.ai
  public: true

  aliases:
    - my-custom-llama3.1-8b # other aliases for the serving name used in the inference API
    - My-Custom-Llama3.1-8B

  metadata:
    name: "[optional]" # kubernetes name
    overview: "[optional description of the model]"
    architecture: "[optional]"
    category: "[optional]"
    status: active

    github_link: "[optional]"
    hf_link: "[optional]"

    languages:
      - "[optional]"

    license: "[optional]"
    vocabulary_size: "[optional]"

  price:
    input_tokens: "[optional]"
    output_tokens: "[optional]"

  tokenizer:
    endpointUrl: ""   # optional remote tokenizer endpoint
    path: ./Meta-Llama-3.1-8B-Instruct_tokenizer

tokenizer:
  endpointUrl: ''
  path: ./Meta-Llama-3.1-70B-Instruct_tokenizer

kubectl apply -f your_model_manifest_filename.yaml

apiVersion: sambanova.ai/v1alpha1
kind: Bundle
metadata:
  name: 8b-3dot1-full
spec:
  checkpoints:
    LLAMA3_8B_3_1_CKPT:
      source: gs://path/to/ckpt/in/gcs  # gs:// -> Google Cloud Storage
      toolSupport: true
    LLAMA3_70B_3_1_CKPT:
      source: nfs:///nfsdata/path/to/ckpt/in/nfs # nfs:// -> NFS path mounted in the serving pod
  models:
    Meta-Llama-3.1-8B-Instruct:
      checkpoint: LLAMA3_8B_3_1_CKPT
      template: Meta-Llama-3.1-8B-Instruct
    Meta-Llama-3.1-70B-Instruct:
      checkpoint: LLAMA3_70B_3_1_CKPT
      template: Meta-Llama-3.1-70B-Instruct
  secretNames:
  - sambanova-artifact-reader
  template: 8b-3dot1-full

checkpoints:
  CUSTOM_CHECKPOINT_ALIAS:
    source: nfs:///nfsdata/path/to/custom/ckpt/dir
    toolSupport: false

models:
  My-Custom-Llama3.1-8B:
    checkpoint: CUSTOM_CHECKPOINT_ALIAS
    template: Meta-Llama-3.1-8B-Instruct

kubectl apply -f your_bundle_filename.yaml