More troubleshooting and setup tips, and some improvements to flagship Week 8 project
This commit is contained in:
@@ -11,7 +11,7 @@
|
||||
"\n",
|
||||
"We'll move at a faster pace than usual, particularly as you're becoming proficient LLM engineers.\n",
|
||||
"\n",
|
||||
"One quick admin thing: I've added a number of packages to the environment.yml file during September. To make sure you have the latest repo with the latest code, it's worth doing this from the `llm_engineering` project folder:\n",
|
||||
"One quick admin thing: I've added a number of packages to the environment.yml file during Sep and Oct. To make sure you have the latest repo with the latest code, it's worth doing this from the `llm_engineering` project folder:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"git pull\n",
|
||||
@@ -206,6 +206,26 @@
|
||||
"print(reply)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9c1b1451-6249-4462-bf2d-5937c059926c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Optional: Keeping Modal warm\n",
|
||||
"\n",
|
||||
"## A way to improve the speed of the Modal pricer service\n",
|
||||
"\n",
|
||||
"A student mentioned to me that he was concerned by how slow Modal seems to be. The reason is that Modal puts our service to sleep if we don't use it, and then it takes 2.5 minutes to spin back up.\n",
|
||||
"\n",
|
||||
"I've added a utility called `keep_warm.py` that will keep our Modal warm by pinging it every 30 seconds.\n",
|
||||
"\n",
|
||||
"To use the utliity, bring up a new Terminal (Mac) or Anaconda prompt (Windows), ensure the environment is activated with `conda activate llms\\\n",
|
||||
"\n",
|
||||
"Then run: `python keep_warm.py` from within the week8 drectory.\n",
|
||||
"\n",
|
||||
"Remember to press ctrl+C or exit the window when you no longer need Modal running.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3754cfdd-ae28-47c8-91f2-6e060e2c91b3",
|
||||
|
||||
Reference in New Issue
Block a user