commit notebook

notebooks/HuggingFace-Inference.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "2e6b851c",
+   "id": "15908f0e",
    "metadata": {},
    "source": [
     "## Import Packages"
@@ -10,54 +10,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "32d8be79",
+   "execution_count": null,
+   "id": "94f0ccef",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2023-06-09 21:59:52.885485: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA\n",
-      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
-      "2023-06-09 21:59:53.039141: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2023-06-09 21:59:53.827918: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n",
-      "2023-06-09 21:59:53.828006: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n",
-      "2023-06-09 21:59:53.828014: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "===================================BUG REPORT===================================\n",
-      "Welcome to bitsandbytes. For bug reports, please run\n",
-      "\n",
-      "python -m bitsandbytes\n",
-      "\n",
-      " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
-      "================================================================================\n",
-      "bin /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/bitsandbytes/libbitsandbytes_cuda113_nocublaslt.so\n",
-      "CUDA SETUP: CUDA runtime path found: /opt/conda/envs/media-reco-env-3-8/lib/libcudart.so\n",
-      "CUDA SETUP: Highest compute capability among GPUs detected: 7.0\n",
-      "CUDA SETUP: Detected CUDA version 113\n",
-      "CUDA SETUP: Loading binary /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/bitsandbytes/libbitsandbytes_cuda113_nocublaslt.so...\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] files: {PosixPath('/opt/conda/envs/media-reco-env-3-8/lib/libcudart.so'), PosixPath('/opt/conda/envs/media-reco-env-3-8/lib/libcudart.so.11.0')}.. We'll flip a coin and try one of these, in order to fail forward.\n",
-      "Either way, this might cause trouble in the future:\n",
-      "If you get `CUDA error: invalid device function` errors, the above might be the cause and the solution is to make sure only one ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] in the paths that we search based on your env.\n",
-      "  warn(msg)\n",
-      "/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: Compute capability < 7.5 detected! Only slow 8-bit matmul is supported for your GPU!\n",
-      "  warn(msg)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import os\n",
     "os.chdir(\"..\")\n",
@@ -69,7 +25,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "76b3d3ff",
+   "id": "58b927f4",
    "metadata": {},
    "source": [
     "## Utilities"
@@ -77,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "9837afb7",
    "metadata": {},
    "outputs": [],
@@ -104,7 +60,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0d3b0d75",
+   "id": "b37f5f57",
    "metadata": {},
    "source": [
     "## Configs"
@@ -112,8 +68,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "fb3cba34",
+   "execution_count": null,
+   "id": "b53f6c18",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -124,7 +80,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8dc85b3d",
+   "id": "ec8111a9",
    "metadata": {},
    "source": [
     "## Load Model & Tokenizer"
@@ -132,32 +88,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "1cb5103c",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f11486f431fd48799d91ef69e586e410",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/33 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "config = PeftConfig.from_pretrained(MODEL_NAME)\n",
     "\n",
@@ -177,7 +111,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3bb51813",
+   "id": "d265647e",
    "metadata": {},
    "source": [
     "## Generation Examples"
@@ -185,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "10372ae3",
    "metadata": {},
    "outputs": [],
@@ -202,7 +136,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "153062cf",
+   "id": "1f6e7df1",
    "metadata": {},
    "source": [
     "### Example 1"
@@ -210,25 +144,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "a84a4f9e",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\n",
-      "\n",
-      "### Response:\n",
-      "I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\n",
-      "I have two pieces of\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -251,7 +170,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a4642cdb",
+   "id": "8143ca1f",
    "metadata": {},
    "source": [
     "### Example 2"
@@ -259,25 +178,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "65117ac7",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "What is the capital city of Greece and with which countries does Greece border?\n",
-      "\n",
-      "### Response:\n",
-      "The capital city of Greece is Athens and it borders Turkey, Bulgaria, Macedonia, Albania, and the Aegean Sea.\n",
-      "\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"What is the capital city of Greece and with which countries does Greece border?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -300,7 +204,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "79fc59d2",
+   "id": "447f75f9",
    "metadata": {},
    "source": [
     "### Example 3"
@@ -308,24 +212,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "2ff7a5e5",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "How can I cook Adobo?\n",
-      "\n",
-      "### Response:\n",
-      "You can cook Adobo by adding garlic, soy sauce, vinegar, bay leaves, peppercorns, and water\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"How can I cook Adobo?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -348,7 +238,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3080312d",
+   "id": "c0f1fc51",
    "metadata": {},
    "source": [
     "### Example 4"
@@ -356,24 +246,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "b0e4b6f5",
+   "execution_count": null,
+   "id": "4073cb6d",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "Which are the tags of the following article: 'A year ago, Russia invaded Ukraine in a major escalation of the Russo-Ukrainian War, which had begun in 2014. The invasion has resulted in thousands of deaths, and instigated Europe's largest refugee crisis since World War II.'?\n",
-      "\n",
-      "### Response:\n",
-      "The tags of the following article: 'A year ago, Russia invaded Ukraine in a major escalation of the Russo-Ukrainian\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"Which are the tags of the following article: 'A year ago, Russia invaded Ukraine in a major escalation of the Russo-Ukrainian War, which had begun in 2014. The invasion has resulted in thousands of deaths, and instigated Europe's largest refugee crisis since World War II.'?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -396,7 +272,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c6c7a56b",
+   "id": "df08ac5a",
    "metadata": {},
    "source": [
     "## Let's Load the Fine-Tuned version"
@@ -404,7 +280,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "id": "9cba7db1",
    "metadata": {},
    "outputs": [],
@@ -414,7 +290,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5d664394",
+   "id": "5bc70c31",
    "metadata": {},
    "source": [
     "### Example 1"
@@ -422,26 +298,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "id": "af3a477a",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\n",
-      "\n",
-      "### Response:\n",
-      "If you have 2 pieces of apples and 3 pieces of oranges, then you have 5 pieces of fruits.\n",
-      "\n",
-      "###\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -464,7 +324,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a07d76da",
+   "id": "622b3c0a",
    "metadata": {},
    "source": [
     "### Example 2"
@@ -472,24 +332,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
-   "id": "5f59b3f4",
+   "execution_count": null,
+   "id": "eab112ae",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "What is the capital city of Greece and with which countries does Greece border?\n",
-      "\n",
-      "### Response:\n",
-      "Greece borders Albania, Bulgaria, Turkey, Macedonia, and the Aegean Sea. The capital of Greece is Athens.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"What is the capital city of Greece and with which countries does Greece border?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -512,7 +358,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ecdb6550",
+   "id": "fb0e6d9e",
    "metadata": {},
    "source": [
     "### Example 3"
@@ -520,30 +366,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
-   "id": "5ac57290",
+   "execution_count": null,
+   "id": "df571d56",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "How can I cook Adobo?\n",
-      "\n",
-      "### Response:\n",
-      "Here's a recipe for adobo:\n",
-      "\n",
-      "\\begin{code}\n",
-      "\n",
-      "\\begin{pre}\n",
-      "\n",
-      "\\end{code\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"How can I cook Adobo?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",
@@ -566,7 +392,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "00859e35",
+   "id": "8d3aa375",
    "metadata": {},
    "source": [
     "### Example 4"
@@ -574,26 +400,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
-   "id": "801165b6",
+   "execution_count": null,
+   "id": "4975198b",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
-      "\n",
-      "### Instruction:\n",
-      "Which are the tags of the following article: 'A year ago, Russia invaded Ukraine in a major escalation of the Russo-Ukrainian War, which had begun in 2014. The invasion has resulted in thousands of deaths, and instigated Europe's largest refugee crisis since World War II.'?\n",
-      "\n",
-      "### Response:\n",
-      "\n",
-      "### Instruction:\n",
-      "Which are the tags of the following article: 'A year ago, Russia invaded Ukraine in a major escal\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "instruction = \"Which are the tags of the following article: 'A year ago, Russia invaded Ukraine in a major escalation of the Russo-Ukrainian War, which had begun in 2014. The invasion has resulted in thousands of deaths, and instigated Europe's largest refugee crisis since World War II.'?\"\n",
     "input_ctxt = None  # For some tasks, you can provide an input context to help the model generate a better response.\n",