Update README.md
Browse files
README.md
CHANGED
|
@@ -23,8 +23,6 @@ The task is to predict the relation between the premise and the hypothesis, whic
|
|
| 23 |
- `contradiction`: hypothesis contradicts the premise,
|
| 24 |
- `neutral`: hypothesis and premise are unrelated.
|
| 25 |
|
| 26 |
-
The MNLI task is to take two sentences referred to as the hypothesis and the premise as input and decide if the sentences entail (support), are neutral (cover different subjects) or contradict each other.
|
| 27 |
-
|
| 28 |
We finetune the model as a Causal Language Model (CLM): given a sequence of tokens, the task is to predict the next token.
|
| 29 |
To achieve this, we create a stylised prompt string, following the approach of [T5 paper](https://arxiv.org/pdf/1910.10683.pdf).
|
| 30 |
```shell
|
|
|
|
| 23 |
- `contradiction`: hypothesis contradicts the premise,
|
| 24 |
- `neutral`: hypothesis and premise are unrelated.
|
| 25 |
|
|
|
|
|
|
|
| 26 |
We finetune the model as a Causal Language Model (CLM): given a sequence of tokens, the task is to predict the next token.
|
| 27 |
To achieve this, we create a stylised prompt string, following the approach of [T5 paper](https://arxiv.org/pdf/1910.10683.pdf).
|
| 28 |
```shell
|