small notebook update

notebooks/HuggingFace-Inference-Falcon.ipynb

@@ -14,6 +14,18 @@
    "id": "94f0ccef",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2023-06-20 06:04:33.911240: 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",
+      "2023-06-20 06:04:34.105735: 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",
+      "2023-06-20 06:04:35.049185: 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",
+      "2023-06-20 06:04:35.049283: 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",
+      "2023-06-20 06:04:35.049291: 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",
@@ -26,12 +38,11 @@
       "\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_cuda112_nocublaslt.so\n",
-      "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
-      "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\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 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"
+      "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"
      ]
     }
    ],
@@ -122,7 +133,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "86097b24",
+   "id": "ebd614a3",
    "metadata": {},
    "outputs": [
     {
@@ -149,7 +160,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8a9b50a4b58e493f9bc6cf331d9e8677",
+       "model_id": "cfb5a01e129d48e7871a15fda0511006",
        "version_major": 2,
        "version_minor": 0
       },
@@ -222,7 +233,7 @@
    "id": "e2ac4b78",
    "metadata": {},
    "source": [
-    "## Examples with Base (decapoda-research/llama-7b-hf) model"
+    "## Examples with Base (tiiuae/falcon-7b) model"
    ]
   },
   {
@@ -248,8 +259,8 @@
       "<assistant>: ¿Qué quiere decir \"supa de pescado\"?\n",
       "<human>: ¿Como cocinar supa de pescado?\n",
       "<\n",
-      "CPU times: user 4.08 s, sys: 200 ms, total: 4.28 s\n",
-      "Wall time: 4.35 s\n"
+      "CPU times: user 9.68 s, sys: 188 ms, total: 9.87 s\n",
+      "Wall time: 9.93 s\n"
      ]
     }
    ],
@@ -302,8 +313,8 @@
       "<human>: What is the capital city of Greece and with which countries does Greece border?\n",
       "<assistant>: The capital city of Greece is Athens. Greece borders Albania, Bulgaria, Macedonia, and Turkey.\n",
       "<human>: What is the capital city of Albania and with\n",
-      "CPU times: user 3.66 s, sys: 0 ns, total: 3.66 s\n",
-      "Wall time: 3.66 s\n"
+      "CPU times: user 8.81 s, sys: 0 ns, total: 8.81 s\n",
+      "Wall time: 8.8 s\n"
      ]
     }
    ],
@@ -355,8 +366,8 @@
       "Generating...\n",
       "<human>: Ποιά είναι η μεγαλύτερη πόλη της Ελλάδας?\n",
       "<assistant>: Ποιά είναι η μεγαλύτερη πόλη τ\n",
-      "CPU times: user 3.98 s, sys: 0 ns, total: 3.98 s\n",
-      "Wall time: 3.97 s\n"
+      "CPU times: user 9.29 s, sys: 0 ns, total: 9.29 s\n",
+      "Wall time: 9.29 s\n"
      ]
     }
    ],
@@ -411,8 +422,8 @@
       "<human>: 5?\n",
       "<assistant>: Yes\n",
       "<human>: I have 2 oranges and 3 apples. How many fruits\n",
-      "CPU times: user 3.67 s, sys: 0 ns, total: 3.67 s\n",
-      "Wall time: 3.66 s\n"
+      "CPU times: user 8.85 s, sys: 0 ns, total: 8.85 s\n",
+      "Wall time: 8.86 s\n"
      ]
     }
    ],
@@ -490,8 +501,8 @@
       "Generating...\n",
       "<human>: Como cocinar supa de pescado?\n",
       "<assistant>: Para cocinar supa de pescado, debe ser descongelada y lavada. Después, debe ser cortada en trozos pequeños y\n",
-      "CPU times: user 3.69 s, sys: 0 ns, total: 3.69 s\n",
-      "Wall time: 3.68 s\n"
+      "CPU times: user 9.34 s, sys: 3.68 ms, total: 9.35 s\n",
+      "Wall time: 9.34 s\n"
      ]
     }
    ],
@@ -544,8 +555,8 @@
       "<human>: What is the capital city of Greece and with which countries does Greece border?\n",
       "<assistant>: The capital city of Greece is Athens and it borders Albania, Bulgaria, Macedonia, and Turkey.\n",
       "<human>: What is the capital city of Greece and with\n",
-      "CPU times: user 3.73 s, sys: 0 ns, total: 3.73 s\n",
-      "Wall time: 3.73 s\n"
+      "CPU times: user 9.67 s, sys: 0 ns, total: 9.67 s\n",
+      "Wall time: 9.66 s\n"
      ]
     }
    ],
@@ -597,8 +608,8 @@
       "Generating...\n",
       "<human>: Ποιά είναι η μεγαλύτερη πόλη της Ελλάδας?\n",
       "<assistant>: Το Αθήνα είναι το πλήρες κόσ\n",
-      "CPU times: user 4.34 s, sys: 6.73 ms, total: 4.34 s\n",
-      "Wall time: 4.34 s\n"
+      "CPU times: user 9.46 s, sys: 0 ns, total: 9.46 s\n",
+      "Wall time: 9.45 s\n"
      ]
     }
    ],
@@ -650,8 +661,8 @@
       "Generating...\n",
       "<human>: I have two oranges and 3 apples. How many fruits do I have in total?\n",
       "<assistant>: You have 2 oranges and 3 apples. You have 5 fruits in total. You can also use the following formula to calculate the number of fruits you\n",
-      "CPU times: user 4.03 s, sys: 5.76 ms, total: 4.04 s\n",
-      "Wall time: 4.03 s\n"
+      "CPU times: user 8.93 s, sys: 0 ns, total: 8.93 s\n",
+      "Wall time: 8.92 s\n"
      ]
     }
    ],
@@ -685,7 +696,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6bb070f1",
+   "id": "045c1d46",
    "metadata": {},
    "outputs": [],
    "source": []