Improve model card: Correct pipeline tag and add paper/Github links
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
@@ -1,16 +1,18 @@
|
|
1 |
---
|
2 |
-
library_name: transformers
|
3 |
-
license: apache-2.0
|
4 |
-
language:
|
5 |
-
- en
|
6 |
base_model:
|
7 |
- answerdotai/ModernBERT-large
|
|
|
|
|
|
|
|
|
8 |
pipeline_tag: text-classification
|
9 |
author: Shreyan C (@thethinkmachine)
|
10 |
---
|
11 |
|
12 |
# Maxwell Task Complexity Scorer-v0.2
|
13 |
|
|
|
|
|
14 |
Maxwell-TCS-v0.2 is a task/instruction complexity score annotator based on the ModernBERT-Large and trained on a large dataset of English instructions. It is designed to be fast, efficient and accurate for scoring/annotation related tasks.
|
15 |
## Model Details
|
16 |
|
@@ -24,6 +26,7 @@ Maxwell-TCS can be used in a variety of downstreaming tasks such as prompt diffi
|
|
24 |
- **Model type:** Bidirectional Encoder Representations from Transformers, based on the ModernBERT-Large architecture.
|
25 |
- **Language(s) (NLP):** English (en)
|
26 |
- **License:** Apache License, Version 2.0
|
|
|
27 |
- **Finetuned from model**: ModernBERT-Large
|
28 |
|
29 |
### Recommendations
|
@@ -157,6 +160,6 @@ For any queries, suggestions or feedback, please contact Shreyan C at *shreyan(a
|
|
157 |
## References
|
158 |
|
159 |
- [[2312.15685] What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning](https://arxiv.org/abs/2312.15685)
|
160 |
-
- [[2404.02948] PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://
|
161 |
- [DEITA-Complexity](https://huggingface.co/datasets/BhabhaAI/DEITA-Complexity)
|
162 |
- [ModernBERT-Large](https://huggingface.co/answerdotai/ModernBERT-large)
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
base_model:
|
3 |
- answerdotai/ModernBERT-large
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
library_name: transformers
|
7 |
+
license: apache-2.0
|
8 |
pipeline_tag: text-classification
|
9 |
author: Shreyan C (@thethinkmachine)
|
10 |
---
|
11 |
|
12 |
# Maxwell Task Complexity Scorer-v0.2
|
13 |
|
14 |
+
This repository contains the model from the [PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://huggingface.co/papers/2404.02948) paper.
|
15 |
+
|
16 |
Maxwell-TCS-v0.2 is a task/instruction complexity score annotator based on the ModernBERT-Large and trained on a large dataset of English instructions. It is designed to be fast, efficient and accurate for scoring/annotation related tasks.
|
17 |
## Model Details
|
18 |
|
|
|
26 |
- **Model type:** Bidirectional Encoder Representations from Transformers, based on the ModernBERT-Large architecture.
|
27 |
- **Language(s) (NLP):** English (en)
|
28 |
- **License:** Apache License, Version 2.0
|
29 |
+
- **Code:** [https://github.com/thethinkmachine/Maxwell-Task-Complexity-Scorer](https://github.com/thethinkmachine/Maxwell-Task-Complexity-Scorer)
|
30 |
- **Finetuned from model**: ModernBERT-Large
|
31 |
|
32 |
### Recommendations
|
|
|
160 |
## References
|
161 |
|
162 |
- [[2312.15685] What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning](https://arxiv.org/abs/2312.15685)
|
163 |
+
- [[2404.02948] PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models](https://huggingface.co/papers/2404.02948)
|
164 |
- [DEITA-Complexity](https://huggingface.co/datasets/BhabhaAI/DEITA-Complexity)
|
165 |
- [ModernBERT-Large](https://huggingface.co/answerdotai/ModernBERT-large)
|