Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,8 @@ We introduce the Bloomz-3b-NLI model, fine-tuned on the [Bloomz-3b-dpo-chat](htt
|
|
| 13 |
|
| 14 |
## Zero-shot Classification
|
| 15 |
The primary appeal of training such models lies in their zero-shot classification performance. This means the model is capable of classifying any text with any label without specific training. What sets the Bloomz-3b-NLI LLMs apart in this realm is their ability to model and extract information from significantly more complex and lengthy test structures compared to models like BERT, RoBERTa, or CamemBERT.
|
| 16 |
-
|
|
|
|
| 17 |
$$P(hypothesis=i\in\mathcal{C}|premise)=\frac{e^{P(premise=entailment\vert hypothesis=i)}}{\sum_{j\in\mathcal{C}}e^{P(premise=entailment\vert hypothesis=j)}}$$
|
| 18 |
With *i* representing a hypothesis composed of a template (for example, "This text is about {}.") and candidate labels ("cinema", "politics", etc.), the set of hypotheses comprises {"This text is about cinema.", "This text is about politics.", ...}. It is these hypotheses that we will measure against the premise, which is the sentence we aim to classify.
|
| 19 |
|
|
|
|
| 13 |
|
| 14 |
## Zero-shot Classification
|
| 15 |
The primary appeal of training such models lies in their zero-shot classification performance. This means the model is capable of classifying any text with any label without specific training. What sets the Bloomz-3b-NLI LLMs apart in this realm is their ability to model and extract information from significantly more complex and lengthy test structures compared to models like BERT, RoBERTa, or CamemBERT.
|
| 16 |
+
|
| 17 |
+
The zero-shot classification task can be summarized by:
|
| 18 |
$$P(hypothesis=i\in\mathcal{C}|premise)=\frac{e^{P(premise=entailment\vert hypothesis=i)}}{\sum_{j\in\mathcal{C}}e^{P(premise=entailment\vert hypothesis=j)}}$$
|
| 19 |
With *i* representing a hypothesis composed of a template (for example, "This text is about {}.") and candidate labels ("cinema", "politics", etc.), the set of hypotheses comprises {"This text is about cinema.", "This text is about politics.", ...}. It is these hypotheses that we will measure against the premise, which is the sentence we aim to classify.
|
| 20 |
|