From 5d7395e1b55a9b4b308ab0a4b0df818152148514 Mon Sep 17 00:00:00 2001
From: Alexander Borzunov <borzunov.alexander@gmail.com>
Date: Tue, 24 Jan 2023 10:01:31 +0400
Subject: [PATCH] Prompt-tuning notebooks: suggest to use a smaller model for
 faster prototyping (#234)

---
 README.md                                |  4 ++--
 examples/prompt-tuning-personachat.ipynb | 16 +++++++++++++---
 examples/prompt-tuning-sst2.ipynb        | 16 +++++++++++++---
 3 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 7988473..0341fe5 100644
--- a/README.md
+++ b/README.md
@@ -61,8 +61,8 @@ You can also host [BLOOMZ](https://huggingface.co/bigscience/bloomz), a version
 Basic tutorials:
 
 - Getting started: [tutorial](https://colab.research.google.com/drive/1Ervk6HPNS6AYVr3xVdQnY5a-TjjmLCdQ?usp=sharing)
-- Fine-tune BLOOM to be a personified chatbot: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-personachat.ipynb)
-- Fine-tune BLOOM for text semantic classification: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-sst2.ipynb)
+- Prompt-tune BLOOM to create a personified chatbot: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-personachat.ipynb)
+- Prompt-tune BLOOM for text semantic classification: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-sst2.ipynb)
 
 Example apps built with Petals:
 
diff --git a/examples/prompt-tuning-personachat.ipynb b/examples/prompt-tuning-personachat.ipynb
index 943bb61..bd4d2ae 100644
--- a/examples/prompt-tuning-personachat.ipynb
+++ b/examples/prompt-tuning-personachat.ipynb
@@ -75,7 +75,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "MODEL_NAME = \"bigscience/bloom-petals\" # select model you like\n",
+    "# Choose a model you'd like to prompt-tune. We recommend starting with\n",
+    "# the smaller 7.1B version of BLOOM (bigscience/bloom-7b1-petals) for faster prototyping.\n",
+    "# Once your code is ready, you can switch to full-scale\n",
+    "# 176B-parameter BLOOM (bigscience/bloom-petals) or BLOOMZ (bigscience/bloomz-petals).\n",
+    "MODEL_NAME = \"bigscience/bloom-7b1-petals\"\n",
+    "\n",
+    "# Choose a prompt-tuning mode ('ptune' or 'deep_ptune').\n",
+    "# The latter fine-tunes separate prefixes for each transformer block,\n",
+    "# so prompt-tuning will take more time but yield better results.\n",
+    "# See this paper for details of how it works: https://arxiv.org/pdf/2110.07602.pdf\n",
+    "TUNING_MODE = 'ptune'\n",
+    "\n",
     "NUM_PREFIX_TOKENS = 16\n",
     "DEVICE = 'cuda'\n",
     "BATCH_SIZE = 8\n",
@@ -83,8 +94,7 @@
     "WEIGHT_DECAY = 0.0\n",
     "NUM_SAMPLES = 1000\n",
     "SEED = 42\n",
-    "MODEL_MAX_LENGTH = 256\n",
-    "TUNING_MODE = 'ptune' # choose between ['ptune', 'deep_ptune'] "
+    "MODEL_MAX_LENGTH = 256"
    ]
   },
   {
diff --git a/examples/prompt-tuning-sst2.ipynb b/examples/prompt-tuning-sst2.ipynb
index 5bcb0c9..05938b0 100644
--- a/examples/prompt-tuning-sst2.ipynb
+++ b/examples/prompt-tuning-sst2.ipynb
@@ -77,7 +77,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "MODEL_NAME = \"bigscience/bloom-petals\" # select model you like\n",
+    "# Choose a model you'd like to prompt-tune. We recommend starting with\n",
+    "# the smaller 7.1B version of BLOOM (bigscience/bloom-7b1-petals) for faster prototyping.\n",
+    "# Once your code is ready, you can switch to full-scale\n",
+    "# 176B-parameter BLOOM (bigscience/bloom-petals) or BLOOMZ (bigscience/bloomz-petals).\n",
+    "MODEL_NAME = \"bigscience/bloom-7b1-petals\"\n",
+    "\n",
+    "# Choose a prompt-tuning mode ('ptune' or 'deep_ptune').\n",
+    "# The latter fine-tunes separate prefixes for each transformer block,\n",
+    "# so prompt-tuning will take more time but yield better results.\n",
+    "# See this paper for details of how it works: https://arxiv.org/pdf/2110.07602.pdf\n",
+    "TUNING_MODE = 'ptune'\n",
+    "\n",
     "NUM_PREFIX_TOKENS = 16\n",
     "DEVICE = 'cuda'\n",
     "BATCH_SIZE = 16\n",
@@ -85,8 +96,7 @@
     "WEIGHT_DECAY = 0.0\n",
     "NUM_EPOCHS = 3\n",
     "SEED = 42\n",
-    "MODEL_MAX_LENGTH = 64\n",
-    "TUNING_MODE = 'ptune' # choose between ['ptune', 'deep_ptune'] "
+    "MODEL_MAX_LENGTH = 64"
    ]
   },
   {