Skip to content

armgit / txtai

Public Imported from GitHub
0

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Update notebook

davidmezzettid1bcdc591f8d
diff --git a/examples/17_Train_without_labels.ipynb b/examples/17_Train_without_labels.ipynb
index 7ebc81d9..2ee5d8fa 100644
--- a/examples/17_Train_without_labels.ipynb
+++ b/examples/17_Train_without_labels.ipynb
@@ -22,9 +22,11 @@
"source": [
"# Train without labels\n",
"\n",
- "Almost all data available is unlabeled. Labeled data takes effort to manually review and/or takes time to collect. Zero-shot classification takes existing large language models and runs a similarity comparision between candidate text and a list of labels. This has been shown to perform surprisingly well.\n",
+ "Almost all data available is unlabeled. Labeled data takes effort to manually review and/or takes time to collect. Zero-shot classification takes existing large language models and runs a similarity comparison between candidate text and a list of labels. This has been shown to perform surprisingly well.\n",
"\n",
- "The problem with zero-shot classifiers is that they need to have a large number of parameters (400M+) to perform well against general tasks. This notebook explores using zero-shot classifiers to build training sets to train smaller models. A simple form of [knowledge distillation](https://en.wikipedia.org/wiki/Knowledge_distillation). "
+ "The problem with zero-shot classifiers is that they need to have a large number of parameters (400M+) to perform well against general tasks, which comes with sizable hardware requirements.\n",
+ "\n",
+ "This notebook explores using zero-shot classifiers to build training data for smaller models. A simple form of [knowledge distillation](https://en.wikipedia.org/wiki/Knowledge_distillation). "
]
},
{