Use instance tokenizer (#116)

* Use instance tokenizer

* consistency updates

---------

Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
This commit is contained in:
James Holcombe
2024-04-10 21:16:19 -04:00
committed by GitHub
parent 028a346498
commit 05718c6b94
11 changed files with 14 additions and 14 deletions

View File

@@ -256,7 +256,7 @@
" self.target_ids = []\n",
"\n",
" # Tokenize the entire text\n",
" token_ids = tokenizer.encode(txt)\n",
" token_ids = self.tokenizer.encode(txt)\n",
"\n",
" # Use a sliding window to chunk the book into overlapping sequences of max_length\n",
" for i in range(0, len(token_ids) - max_length, stride):\n",
@@ -377,7 +377,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
"version": "3.10.10"
}
},
"nbformat": 4,