commit updated notebook

notebooks/HuggingFace-Inference.ipynb

@@ -13,6 +13,20 @@
    "execution_count": 1,
    "id": "94f0ccef",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.chdir(\"..\")\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7e2e61ae",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -33,44 +47,8 @@
       "CUDA SETUP: Detected CUDA version 112\n",
       "CUDA SETUP: Loading binary /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/bitsandbytes/libbitsandbytes_cuda112_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: /opt/conda/envs/media-reco-env-3-8 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\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: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib'), PosixPath('/usr/local/nvidia/lib64')}\n",
-      "  warn(msg)\n",
-      "/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\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: The following directories listed in your path were found to be non-existent: {PosixPath('//162.21.251.11'), PosixPath('http'), PosixPath('8080')}\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: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
-      "  warn(msg)\n",
-      "/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('/usr/local/cuda/lib64/libcudart.so'), PosixPath('/usr/local/cuda/lib64/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"
-     ]
     }
    ],
-   "source": [
-    "import os\n",
-    "os.chdir(\"..\")\n",
-    "\n",
-    "import warnings\n",
-    "warnings.filterwarnings(\"ignore\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b050e999",
-   "metadata": {},
-   "outputs": [],
    "source": [
     "import torch\n",
     "from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM\n",
@@ -87,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "9837afb7",
    "metadata": {},
    "outputs": [],
@@ -122,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "b53f6c18",
    "metadata": {},
    "outputs": [],
@@ -142,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "1cb5103c",
    "metadata": {},
    "outputs": [
@@ -156,7 +134,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "255acd69c62c4f15b19acd43c4bc4aad",
+       "model_id": "019658e0378b45cf90c892cec7fa9446",
        "version_major": 2,
        "version_minor": 0
       },
@@ -195,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "10372ae3",
    "metadata": {},
    "outputs": [],
@@ -205,7 +183,7 @@
     "    top_p=0.95,\n",
     "    top_k=40,\n",
     "    num_beams=4,\n",
-    "    max_new_tokens=40,\n",
+    "    max_new_tokens=50,\n",
     "    repetition_penalty=1.7,\n",
     ")"
    ]
@@ -228,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "a84a4f9e",
    "metadata": {},
    "outputs": [
@@ -275,7 +253,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "65117ac7",
    "metadata": {},
    "outputs": [
@@ -293,7 +271,11 @@
       "## See also\n",
       "\n",
       "* Natural language processing\n",
-      "* Question answering\n"
+      "* Question answering\n",
+      "\n",
+      "## External links\n",
+      "\n",
+      "* Official website\n"
      ]
     }
    ],
@@ -327,7 +309,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "2ff7a5e5",
    "metadata": {},
    "outputs": [
@@ -346,10 +328,7 @@
       "## See also\n",
       "\n",
       "* Spanish orthography\n",
-      "* Spanish phonology\n",
-      "\n",
-      "## External links\n",
-      "\n"
+      "* Spanish phonology\n"
      ]
     }
    ],
@@ -383,7 +362,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "4073cb6d",
    "metadata": {},
    "outputs": [
@@ -396,7 +375,7 @@
       "### 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: 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\n"
+      "### Response: 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\n"
      ]
     }
    ],
@@ -430,7 +409,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "a22ffa72",
    "metadata": {},
    "outputs": [
@@ -446,7 +425,7 @@
       "### Response: The largest city in Greece is Thessaloniki.\n",
       "\n",
       "### Instruction:\n",
-      "Ποιά είναι η μεγαλύτ\n"
+      "Ποιά είναι η μεγαλύτερη πόλη τ\n"
      ]
     }
    ],
@@ -488,7 +467,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "9cba7db1",
    "metadata": {},
    "outputs": [],
@@ -506,7 +485,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "af3a477a",
    "metadata": {},
    "outputs": [
@@ -519,7 +498,7 @@
       "### Instruction:\n",
       "I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\n",
       "\n",
-      "### Response: depends on what you mean by \"pieces\". If you mean slices, then you have 5 pieces of fruits. If you mean individual fruits, then you have 5 fruits\n"
+      "### Response: depends on what you mean by \"pieces of fruits\". If you mean individual pieces of fruit, then you have 5 pieces of fruit (2 apples and 3 oranges). If you mean slices of fruit, then you have\n"
      ]
     }
    ],
@@ -553,7 +532,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "eab112ae",
    "metadata": {},
    "outputs": [
@@ -566,9 +545,7 @@
       "### Instruction:\n",
       "What is the capital city of Greece and with which countries does Greece border?\n",
       "\n",
-      "### Response:'Athens is the capital city of Greece. Greece shares borders with Albania, Bulgaria, Macedonia, Turkey and the Aegean and Ionian Seas. '\n",
-      "\n",
-      "\n"
+      "### Response:'Athens is the capital city of Greece. Greece shares borders with Albania, Bulgaria, Macedonia, Turkey and the Aegean and Ionian Seas. '\n"
      ]
     }
    ],
@@ -602,7 +579,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "df571d56",
    "metadata": {},
    "outputs": [
@@ -615,7 +592,7 @@
       "### Instruction:\n",
       "Como cocinar supa de pescado?\n",
       "\n",
-      "### Response:ambos tipos de supa de pescado pueden ser cocinados en el horno o en una olla de cocina. Para preparar la supa de pesc\n"
+      "### Response:ambos tipos de supa de pescado pueden ser cocinados en el horno o en una olla de cocina. Para preparar la supa de pescado en el horno, simplemente col\n"
      ]
     }
    ],
@@ -649,7 +626,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "4975198b",
    "metadata": {},
    "outputs": [
@@ -662,7 +639,9 @@
       "### 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: is a news article about the Russo-Ukrainian War. It was published on February 24, 2022, by The New York Times. Here are the tags\n"
+      "### Response: is a news article about the Russo-Ukrainian War. It was published on February 24, 2022, by The New York Times. Here are the tags of the article:\n",
+      "\n",
+      "### Instruction\n"
      ]
     }
    ],
@@ -696,7 +675,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "id": "86bc95a9",
    "metadata": {},
    "outputs": [
@@ -710,7 +689,7 @@
       "Ποιά είναι η μεγαλύτερη πόλη της Ελλάδας?\n",
       "\n",
       "### Response:'\n",
-      "Η Αθήνα είναι η μεγαλύτερη πόλη της Ελ\n"
+      "Η Αθήνα είναι η μεγαλύτερη πόλη της Ελλάδας και \n"
      ]
     }
    ],