update library
Browse files
README.md
CHANGED
|
@@ -1,16 +1,17 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
-
|
| 5 |
base_model:
|
| 6 |
-
|
| 7 |
-
|
|
|
|
| 8 |
tags:
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
---
|
| 15 |
|
| 16 |
# SmartBERT V3 CodeBERT
|
|
@@ -21,7 +22,7 @@ tags:
|
|
| 21 |
|
| 22 |
**SmartBERT V3** is a pre-trained programming language model, initialized with **[CodeBERT-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm)**. It has been further trained on [SmartBERT V2](https://huggingface.co/web3se/SmartBERT-v2) with an additional **64,000** smart contracts, to enhance its robustness in representing smart contract code at the _function_ level.
|
| 23 |
|
| 24 |
-
- **Training Data:** Trained on a total of **80,000** smart contracts, including **16,000** from [SmartBERT V2](https://huggingface.co/web3se/SmartBERT-v2) and **64,000** (starts from 30001) new contracts.
|
| 25 |
- **Hardware:** Utilized 2 Nvidia A100 80G GPUs.
|
| 26 |
- **Training Duration:** Over 30 hours.
|
| 27 |
- **Evaluation Data:** Evaluated on **1,500** (starts from 96425) smart contracts.
|
|
@@ -62,4 +63,4 @@ To train and deploy the SmartBERT V3 model for Web API services, please refer to
|
|
| 62 |
## Sponsors
|
| 63 |
|
| 64 |
- [Institute of Intelligent Computing Technology, Suzhou, CAS](http://iict.ac.cn/)
|
| 65 |
-
- CAS Mino (中科劢诺)
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
+
- en
|
| 5 |
base_model:
|
| 6 |
+
- microsoft/codebert-base-mlm
|
| 7 |
+
- web3se/SmartBERT-v2
|
| 8 |
+
pipeline_tag: fill-mask
|
| 9 |
tags:
|
| 10 |
+
- smart-contract
|
| 11 |
+
- web3
|
| 12 |
+
- software-engineering
|
| 13 |
+
- embedding
|
| 14 |
+
- codebert
|
| 15 |
---
|
| 16 |
|
| 17 |
# SmartBERT V3 CodeBERT
|
|
|
|
| 22 |
|
| 23 |
**SmartBERT V3** is a pre-trained programming language model, initialized with **[CodeBERT-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm)**. It has been further trained on [SmartBERT V2](https://huggingface.co/web3se/SmartBERT-v2) with an additional **64,000** smart contracts, to enhance its robustness in representing smart contract code at the _function_ level.
|
| 24 |
|
| 25 |
+
- **Training Data:** Trained on a total of **80,000** smart contracts, including **16,000** from **[SmartBERT V2](https://huggingface.co/web3se/SmartBERT-v2)** and **64,000** (starts from 30001) new contracts.
|
| 26 |
- **Hardware:** Utilized 2 Nvidia A100 80G GPUs.
|
| 27 |
- **Training Duration:** Over 30 hours.
|
| 28 |
- **Evaluation Data:** Evaluated on **1,500** (starts from 96425) smart contracts.
|
|
|
|
| 63 |
## Sponsors
|
| 64 |
|
| 65 |
- [Institute of Intelligent Computing Technology, Suzhou, CAS](http://iict.ac.cn/)
|
| 66 |
+
- CAS Mino (中科劢诺)
|