From 95db0fe42de4f7e4e80eded48c6aeab8ed4c4d1f Mon Sep 17 00:00:00 2001
From: Sanyam Bhutani <sanyambhutani@meta.com>
Date: Fri, 25 Oct 2024 15:30:36 -0700
Subject: [PATCH] Address PR Comments
---
.../Step-1 PDF-Pre-Processing-Logic.ipynb | 4 ++--
.../NotebookLlama/Step-2-Transcript-Writer.ipynb | 4 ++--
.../NotebookLlama/Step-3-Re-Writer.ipynb | 6 +++---
.../NotebookLlama/Step-4-TTS-Workflow.ipynb | 8 +++++---
recipes/quickstart/NotebookLlama/requirements.txt | 15 +++++++++++++++
5 files changed, 27 insertions(+), 10 deletions(-)
create mode 100644 recipes/quickstart/NotebookLlama/requirements.txt
diff --git a/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb b/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb
index 6f128be3..107ce482 100644
--- a/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb
+++ b/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb
@@ -59,7 +59,7 @@
"metadata": {},
"outputs": [],
"source": [
- "pdf_path = './2402.13116v3.pdf'\n",
+ "pdf_path = './resources/2402.13116v3.pdf'\n",
"DEFAULT_MODEL = \"meta-llama/Llama-3.2-1B-Instruct\""
]
},
@@ -469,7 +469,7 @@
"metadata": {},
"outputs": [],
"source": [
- "INPUT_FILE = \"./extracted_text.txt\" # Replace with your file path\n",
+ "INPUT_FILE = \"./resources/extracted_text.txt\" # Replace with your file path\n",
"CHUNK_SIZE = 1000 # Adjust chunk size if needed\n",
"\n",
"chunks = create_word_bounded_chunks(text, CHUNK_SIZE)\n",
diff --git a/recipes/quickstart/NotebookLlama/Step-2-Transcript-Writer.ipynb b/recipes/quickstart/NotebookLlama/Step-2-Transcript-Writer.ipynb
index 5c9388d0..ea25940b 100644
--- a/recipes/quickstart/NotebookLlama/Step-2-Transcript-Writer.ipynb
+++ b/recipes/quickstart/NotebookLlama/Step-2-Transcript-Writer.ipynb
@@ -162,7 +162,7 @@
"metadata": {},
"outputs": [],
"source": [
- "INPUT_PROMPT = read_file_to_string('./clean_extracted_text.txt')"
+ "INPUT_PROMPT = read_file_to_string('./resources/clean_extracted_text.txt')"
]
},
{
@@ -298,7 +298,7 @@
"metadata": {},
"outputs": [],
"source": [
- "with open('data.pkl', 'wb') as file:\n",
+ "with open('./resources/data.pkl', 'wb') as file:\n",
" pickle.dump(save_string_pkl, file)"
]
},
diff --git a/recipes/quickstart/NotebookLlama/Step-3-Re-Writer.ipynb b/recipes/quickstart/NotebookLlama/Step-3-Re-Writer.ipynb
index 111e6505..035d2b1a 100644
--- a/recipes/quickstart/NotebookLlama/Step-3-Re-Writer.ipynb
+++ b/recipes/quickstart/NotebookLlama/Step-3-Re-Writer.ipynb
@@ -146,7 +146,7 @@
"source": [
"import pickle\n",
"\n",
- "with open('data.pkl', 'rb') as file:\n",
+ "with open('./resources/data.pkl', 'rb') as file:\n",
" INPUT_PROMPT = pickle.load(file)"
]
},
@@ -191,7 +191,7 @@
" \"text-generation\",\n",
" model=MODEL,\n",
" model_kwargs={\"torch_dtype\": torch.bfloat16},\n",
- " device_map=\"cuda:7\",\n",
+ " device_map=\"auto\",\n",
")\n",
"\n",
"messages = [\n",
@@ -249,7 +249,7 @@
"metadata": {},
"outputs": [],
"source": [
- "with open('podcast_ready_data.pkl', 'wb') as file:\n",
+ "with open('./resources/podcast_ready_data.pkl', 'wb') as file:\n",
" pickle.dump(save_string_pkl, file)"
]
},
diff --git a/recipes/quickstart/NotebookLlama/Step-4-TTS-Workflow.ipynb b/recipes/quickstart/NotebookLlama/Step-4-TTS-Workflow.ipynb
index 711996ee..a55ec8e2 100644
--- a/recipes/quickstart/NotebookLlama/Step-4-TTS-Workflow.ipynb
+++ b/recipes/quickstart/NotebookLlama/Step-4-TTS-Workflow.ipynb
@@ -119,7 +119,9 @@
"source": [
"Generally in life, you set your device to \"cuda\" and are happy. \n",
"\n",
- "However, sometimes you want to compensate for things and set it to `cuda:7` to tell the system but even more-so the world that you have 8 GPUS:"
+ "However, sometimes you want to compensate for things and set it to `cuda:7` to tell the system but even more-so the world that you have 8 GPUS.\n",
+ "\n",
+ "Jokes aside please set `device = \"cuda\"` below if you're using a single GPU node."
]
},
{
@@ -289,7 +291,7 @@
"source": [
"import pickle\n",
"\n",
- "with open('./podcast_ready_data.pkl', 'rb') as file:\n",
+ "with open('./resources/podcast_ready_data.pkl', 'rb') as file:\n",
" PODCAST_TEXT = pickle.load(file)"
]
},
@@ -631,7 +633,7 @@
}
],
"source": [
- "final_audio.export(\"_podcast.mp3\", \n",
+ "final_audio.export(\"./resources/_podcast.mp3\", \n",
" format=\"mp3\", \n",
" bitrate=\"192k\",\n",
" parameters=[\"-q:a\", \"0\"])"
diff --git a/recipes/quickstart/NotebookLlama/requirements.txt b/recipes/quickstart/NotebookLlama/requirements.txt
new file mode 100644
index 00000000..34a27dc8
--- /dev/null
+++ b/recipes/quickstart/NotebookLlama/requirements.txt
@@ -0,0 +1,15 @@
+# Core dependencies
+PyPDF2>=3.0.0
+torch>=2.0.0
+transformers>=4.46.0
+accelerate>=0.27.0
+rich>=13.0.0
+ipywidgets>=8.0.0
+tqdm>=4.66.0
+
+# Optional but recommended
+jupyter>=1.0.0
+ipykernel>=6.0.0
+
+# Warning handling
+warnings>=0.1.0
\ No newline at end of file
--
GitLab