Update lengths.ipynb

Author: linhduongtuan

lengths.ipynb

@@ -19,16 +19,16 @@
    ],
    "source": [
     "from datasets import load_dataset\n",
-    "from transformers import LlamaTokenizer\n",
+    "from transformers import BloomTokenizerFast\n",
     "\n",
     "\n",
-    "tokenizer = LlamaTokenizer.from_pretrained(\n",
-    "    \"decapoda-research/llama-7b-hf\", add_eos_token=True\n",
+    "tokenizer = BloomTokenizerFast.from_pretrained(\n",
+    "    \"bigscience/bloom\", add_eos_token=True\n",
     ")\n",
     "tokenizer.pad_token = tokenizer.eos_token\n",
     "tokenizer.pad_token_id = tokenizer.eos_token_id\n",
     "\n",
-    "data = load_dataset(\"json\", data_files=\"alpaca_data.json\")\n",
+    "data = load_dataset(\"json\", data_files=\"chatdoctor-200k.json\")\n",
     "\n",
     "\n",
     "def generate_prompt(data_point):\n",