Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Rollback breaking change #3703

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Rollback breaking change #3703

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 16 additions & 10 deletions notebooks/community/model_garden/model_garden_pytorch_llama3_1_deployment.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,6 +135,7 @@
"import datetime\n",
"import importlib\n",
"import os\n",
"import re\n",
"import uuid\n",
"from typing import Tuple\n",
"\n",
Expand Down Expand Up @@ -215,7 +216,21 @@
"VERTEX_AI_MODEL_GARDEN_LLAMA_3_1 = \"\" # @param {type:\"string\", isTemplate:true}\n",
"assert (\n",
" VERTEX_AI_MODEL_GARDEN_LLAMA_3_1\n",
"), \"Click the agreement of Llama 3.1 in Vertex AI Model Garden, and get the GCS path of Llama 3.1 model artifacts.\""
"), \"Click the agreement of Llama 3.1 in Vertex AI Model Garden, and get the GCS path of Llama 3.1 model artifacts.\"\n",
"parsed_gcs_url = re.search(\"gs://.*?(?=[ ]|$)\", VERTEX_AI_MODEL_GARDEN_LLAMA_3_1)\n",
"if parsed_gcs_url:\n",
" VERTEX_AI_MODEL_GARDEN_LLAMA_3_1 = parsed_gcs_url.group()\n",
"assert VERTEX_AI_MODEL_GARDEN_LLAMA_3_1.startswith(\n",
" \"gs://\"\n",
"), \"VERTEX_AI_MODEL_GARDEN_LLAMA_3_1 is expected to be a GCS URI and must start with `gs://`.\"\n",
"print(\n",
" \"Copying LLaMA3 model artifacts from\",\n",
" VERTEX_AI_MODEL_GARDEN_LLAMA_3_1,\n",
" \"to \",\n",
" MODEL_BUCKET,\n",
")\n",
"\n",
"! gsutil -m cp -R $VERTEX_AI_MODEL_GARDEN_LLAMA_3_1/* $MODEL_BUCKET"
]
},
{
Expand Down Expand Up @@ -247,9 +262,6 @@
"# @markdown Select one of the four model variations. More model variants will be supported by Hex-LLM in the future.\n",
"MODEL_ID = \"Meta-Llama-3.1-8B\" # @param [\"Meta-Llama-3.1-8B\", \"Meta-Llama-3.1-8B-Instruct\", \"Meta-Llama-3.1-70B\", \"Meta-Llama-3.1-70B-Instruct\"] {allow-input: true, isTemplate: true}\n",
"TPU_DEPLOYMENT_REGION = \"us-west1\" # @param [\"us-west1\"] {isTemplate:true}\n",
"common_util.copy_model_artifacts(\n",
" MODEL_ID, VERTEX_AI_MODEL_GARDEN_LLAMA_3_1, MODEL_BUCKET\n",
")\n",
"model_id = os.path.join(MODEL_BUCKET, MODEL_ID)\n",
"hf_model_id = \"meta-llama/\" + MODEL_ID\n",
"\n",
Expand Down Expand Up @@ -562,9 +574,6 @@
"\n",
"base_model_name = \"Meta-Llama-3.1-8B\" # @param [\"Meta-Llama-3.1-8B\", \"Meta-Llama-3.1-8B-Instruct\", \"Meta-Llama-3.1-70B\", \"Meta-Llama-3.1-70B-Instruct\", \"Meta-Llama-3.1-405B-FP8\", \"Meta-Llama-3.1-405B-Instruct-FP8\"] {isTemplate:true}\n",
"model_id = os.path.join(MODEL_BUCKET, base_model_name)\n",
"common_util.copy_model_artifacts(\n",
" base_model_name, VERTEX_AI_MODEL_GARDEN_LLAMA_3_1, MODEL_BUCKET\n",
")\n",
"hf_model_id = \"meta-llama/\" + base_model_name\n",
"\n",
"# The pre-built serving docker images.\n",
Expand Down Expand Up @@ -870,9 +879,6 @@
"\n",
"base_model_name = \"Meta-Llama-3.1-8B\" # @param [\"Meta-Llama-3.1-8B\", \"Meta-Llama-3.1-8B-Instruct\", \"Meta-Llama-3.1-70B\", \"Meta-Llama-3.1-70B-Instruct\"] {isTemplate:true}\n",
"model_id = os.path.join(MODEL_BUCKET, base_model_name)\n",
"common_util.copy_model_artifacts(\n",
" base_model_name, VERTEX_AI_MODEL_GARDEN_LLAMA_3_1, MODEL_BUCKET\n",
")\n",
"hf_model_id = \"meta-llama/\" + base_model_name\n",
"\n",
"# The pre-built serving docker images.\n",
Expand Down