Text Classification
Transformers
Safetensors
English
bert
prompt-compression
dependency-detection
referential-dangling
research
text-embeddings-inference
Instructions to use JusperLee/referential-dangling-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JusperLee/referential-dangling-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="JusperLee/referential-dangling-detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("JusperLee/referential-dangling-detector") model = AutoModelForSequenceClassification.from_pretrained("JusperLee/referential-dangling-detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add paper and project page links
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
library_name: transformers
|
|
|
|
| 6 |
pipeline_tag: text-classification
|
| 7 |
-
base_model: google-bert/bert-base-uncased
|
| 8 |
-
datasets:
|
| 9 |
-
- hotpotqa/hotpot_qa
|
| 10 |
tags:
|
| 11 |
- prompt-compression
|
| 12 |
- dependency-detection
|
|
@@ -20,6 +20,10 @@ This is the sentence-pair dependency detector released with **Relevant but
|
|
| 20 |
Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard
|
| 21 |
Prompt Compression**.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
The model scores whether a candidate sentence supplies a necessary dependency
|
| 24 |
for a retained sentence, conditioned on the question. It is used by the
|
| 25 |
repository's automatic context-restoration experiments.
|
|
@@ -97,4 +101,4 @@ languages, or substantially different compression settings without evaluation.
|
|
| 97 |
author={Zhengpei Hu and Kai Li and Dapeng Fu and Xuechao Zou and Yuanhao Tang and Yue Li and Tengfei Cao and Jianqiang Huang},
|
| 98 |
note={Research code and model release}
|
| 99 |
}
|
| 100 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: google-bert/bert-base-uncased
|
| 3 |
+
datasets:
|
| 4 |
+
- hotpotqa/hotpot_qa
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
library_name: transformers
|
| 8 |
+
license: apache-2.0
|
| 9 |
pipeline_tag: text-classification
|
|
|
|
|
|
|
|
|
|
| 10 |
tags:
|
| 11 |
- prompt-compression
|
| 12 |
- dependency-detection
|
|
|
|
| 20 |
Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard
|
| 21 |
Prompt Compression**.
|
| 22 |
|
| 23 |
+
**Paper:** [Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression](https://huggingface.co/papers/2608.04569)
|
| 24 |
+
|
| 25 |
+
**Project page:** [https://cslikai.cn/Referential-Dangling/](https://cslikai.cn/Referential-Dangling/)
|
| 26 |
+
|
| 27 |
The model scores whether a candidate sentence supplies a necessary dependency
|
| 28 |
for a retained sentence, conditioned on the question. It is used by the
|
| 29 |
repository's automatic context-restoration experiments.
|
|
|
|
| 101 |
author={Zhengpei Hu and Kai Li and Dapeng Fu and Xuechao Zou and Yuanhao Tang and Yue Li and Tengfei Cao and Jianqiang Huang},
|
| 102 |
note={Research code and model release}
|
| 103 |
}
|
| 104 |
+
```
|