Instructions to use binwang/InstructDS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use binwang/InstructDS with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("binwang/InstructDS") model = AutoModelForSeq2SeqLM.from_pretrained("binwang/InstructDS", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Clarify InstructDS research release, companion data and initialization checkpoint
Browse files
README.md
CHANGED
|
@@ -2,9 +2,15 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
|
|
|
|
| 7 |
|
| 8 |
-
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
# InstructDS — Research Release (EMNLP 2023)
|
| 6 |
|
| 7 |
+
**Historical research artifact. No longer actively maintained. Retained for reproducibility of the original work.**
|
| 8 |
|
| 9 |
+
This repository hosts the InstructDS model for *Instructive Dialogue Summarization with Query Aggregations* (EMNLP 2023).
|
| 10 |
|
| 11 |
+
- [Paper](https://arxiv.org/abs/2310.10981)
|
| 12 |
+
- [Code and reproduction instructions](https://github.com/BinWang28/InstructDS)
|
| 13 |
+
- [Companion datasets](https://huggingface.co/datasets/binwang/InstructDS_datasets)
|
| 14 |
+
- [Initialization checkpoint: flan-t5-xl-own](https://huggingface.co/binwang/flan-t5-xl-own)
|
| 15 |
+
|
| 16 |
+
The initialization checkpoint is a separate artifact used by the original experiments. Use the linked project instructions to identify the appropriate checkpoint and dataset for reproduction.
|