Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,10 @@ pipeline_tag: summarization
|
|
| 8 |
tags:
|
| 9 |
- Meeting
|
| 10 |
- Summarization
|
| 11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
tags:
|
| 9 |
- Meeting
|
| 10 |
- Summarization
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# MeetPEFT: Parameter Efficient Fine-Tuning on LLMs for Long Meeting Summarization
|
| 14 |
+
|
| 15 |
+
We use quantized LongLoRA to fine-tune a Llama-2-7b model and extend the context length from 4k to 16k.
|
| 16 |
+
|
| 17 |
+
The model is fine-tuned on MeetingBank and QMSum datasets.
|