Update README.md
Browse files
README.md
CHANGED
@@ -374,24 +374,23 @@ Each JSONL file in the dataset follows a structured format with the following fi
|
|
374 |
- `task`: The specific task type.
|
375 |
- `lang`: The language of the input text.
|
376 |
- `instructions`: A brief set of instructions describing how the text should be labeled.
|
377 |
-
- `text`: A formatted structure including instructions and response for the task in a conversation format between the system, user, and assistant, showing the decision process.
|
378 |
|
379 |
|
380 |
**Example entry in JSONL file:**
|
381 |
|
382 |
```
|
383 |
{
|
384 |
-
"id": "
|
385 |
-
"original_id":
|
386 |
-
"input": "
|
387 |
-
"output": "
|
388 |
-
"dataset": "
|
389 |
-
"task": "
|
390 |
"lang": "en",
|
391 |
-
"instructions": "
|
392 |
-
"text": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are a social media expert providing accurate analysis and insights.<|eot_id|><|start_header_id|>user<|end_header_id|>Analyze the given text and label it as 'checkworthy' if it includes a factual statement that is significant or relevant to verify, or 'not_checkworthy' if it's not worth checking. Return only the label without any explanation, justification or additional text.\ninput: You know, I saw a movie - \"Crocodile Dundee.\"\nlabel: <|eot_id|><|start_header_id|>assistant<|end_header_id|>not_checkworthy<|eot_id|><|end_of_text|>"
|
393 |
}
|
394 |
|
|
|
395 |
```
|
396 |
## Model
|
397 |
[**LlamaLens on Hugging Face**](https://huggingface.co/QCRI/LlamaLens)
|
|
|
374 |
- `task`: The specific task type.
|
375 |
- `lang`: The language of the input text.
|
376 |
- `instructions`: A brief set of instructions describing how the text should be labeled.
|
|
|
377 |
|
378 |
|
379 |
**Example entry in JSONL file:**
|
380 |
|
381 |
```
|
382 |
{
|
383 |
+
"id": "fb6dd1bb-2ab4-4402-adaa-9be9eea6ca18",
|
384 |
+
"original_id": null,
|
385 |
+
"input": "I feel that worldviews that lack the divine tend toward the solipsistic.",
|
386 |
+
"output": "joy",
|
387 |
+
"dataset": "Emotion",
|
388 |
+
"task": "Emotion",
|
389 |
"lang": "en",
|
390 |
+
"instructions": "Identify if the given text expresses an emotion and specify whether it is joy, love, fear, anger, sadness, or surprise. Return only the label without any explanation, justification, or additional text."
|
|
|
391 |
}
|
392 |
|
393 |
+
|
394 |
```
|
395 |
## Model
|
396 |
[**LlamaLens on Hugging Face**](https://huggingface.co/QCRI/LlamaLens)
|