Merge branch 'main' into main

helenzusa1 · May 20, 2024 · aa0ba55 · aa0ba55
2 parents 7fb5771 + 5f95c8a
commit aa0ba55
Showing 1 changed file with 27 additions and 2 deletions.
diff --git a/sdk/python/foundation-models/system/finetune/chat-completion/chat-completion.ipynb b/sdk/python/foundation-models/system/finetune/chat-completion/chat-completion.ipynb
@@ -368,7 +368,9 @@
     "Optimization parameters help in optimizing the GPU memory and effectively using the compute resources. Below are few of the parameters that belong to this category. _The optimization parameters differs for each model and are packaged with the model to handle these variations._\n",
     "1. enable the deepspeed and LoRA\n",
     "2. enable mixed precision training\n",
-    "2. enable multi-node training "
+    "2. enable multi-node training \n",
+    "\n",
+    "Note: Supervised finetuning may result in loosing alignment or catastrophic forgetting. We recommend checking for this issue and running an alignment stage after you finetune."
    ]
   },
   {
@@ -625,12 +627,35 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import ast\n",
+    "\n",
+    "instance_type = \"Standard_NC6s_v3\"\n",
+    "\n",
+    "# Inference compute allow list that supports deployment\n",
+    "if \"inference_compute_allow_list\" in foundation_model.tags:\n",
+    "    inference_computes_allow_list = ast.literal_eval(\n",
+    "        foundation_model.tags[\"inference_compute_allow_list\"]\n",
+    "    )  # convert string to python list\n",
+    "    print(f\"Please create a compute from the above list - {computes_allow_list}\")\n",
+    "else:\n",
+    "    inference_computes_allow_list = None\n",
+    "    print(\"`inference_compute_allow_list` is not part of model tags\")\n",
+    "\n",
+    "# Check if the compute is in the allow listed computes\n",
+    "if (\n",
+    "    inference_computes_allow_list is not None\n",
+    "    and instance_type not in inference_computes_allow_list\n",
+    "):\n",
+    "    print(\n",
+    "        f\"`instance_type` is not in the allow listed compute. Please select a value from {inference_computes_allow_list}\"\n",
+    "    )\n",
+    "\n",
     "# create a deployment\n",
     "demo_deployment = ManagedOnlineDeployment(\n",
     "    name=\"demo\",\n",
     "    endpoint_name=online_endpoint_name,\n",
     "    model=registered_model.id,\n",
-    "    instance_type=\"Standard_E8s_v3\",\n",
+    "    instance_type=instance_type,\n",
     "    instance_count=1,\n",
     "    liveness_probe=ProbeSettings(initial_delay=600),\n",
     "    request_settings=OnlineRequestSettings(request_timeout_ms=90000),\n",