Gerson Fabian Buenahora Ormaza commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,54 @@ pipeline_tag: text-generation
|
|
| 10 |
library_name: transformers
|
| 11 |
tags:
|
| 12 |
- code
|
| 13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
library_name: transformers
|
| 11 |
tags:
|
| 12 |
- code
|
| 13 |
+
---
|
| 14 |
+
# Model Card
|
| 15 |
+
|
| 16 |
+
GPT2Coder is a language model that uses openAI's GPT2 model architecture,
|
| 17 |
+
the model was pre-trained on multiple code data focused on python and languages
|
| 18 |
+
such as Spanish and English. The pretrained model was finely tuned to handle
|
| 19 |
+
the task of receiving textual input in the form of a code request and generating
|
| 20 |
+
a code output.
|
| 21 |
+
|
| 22 |
+
## Model Details
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** BueormAI
|
| 26 |
+
- **Shared by:** BueormLLC
|
| 27 |
+
- **Model type:** Transformer
|
| 28 |
+
- **Language(s) (NLP):** English (en), Spanish (es)
|
| 29 |
+
- **License:** MiT
|
| 30 |
+
- **Finetuned from model:** GPT2 Architecture
|
| 31 |
+
|
| 32 |
+
## Bias, Risks, and Limitations
|
| 33 |
+
|
| 34 |
+
The model can generate unexpected code and output, in addition to offensive texts and non-functional code.
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
### Recommendations
|
| 38 |
+
|
| 39 |
+
We recommend using the model with caution and handling its outputs with discretion as they may turn out to be non-functional outputs and harmful and dangerous code.
|
| 40 |
+
|
| 41 |
+
## Training Details
|
| 42 |
+
|
| 43 |
+
### Training Hyperparameters
|
| 44 |
+
|
| 45 |
+
- **Training regime:** fp16 mixed precision
|
| 46 |
+
- **Max_lenght:** 1024 tokens
|
| 47 |
+
- **pretrain epochs:** 1 epochs
|
| 48 |
+
- **finetuning epochs:** 2 epochs
|
| 49 |
+
|
| 50 |
+
## Environmental Impact
|
| 51 |
+
|
| 52 |
+
- **Hardware Type:** GPU P100
|
| 53 |
+
- **Hours used:** 18 hours
|
| 54 |
+
- **Cloud Provider:** Kaggle
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
# By Bueorm
|
| 58 |
+
Thanks to all the people who download and support our projects
|
| 59 |
+
and manage a vision towards the future with AI, we hope you will support
|
| 60 |
+
us to continue advancing and launching more followed models.
|
| 61 |
+
|
| 62 |
+
- [Paypal Donations](https://paypal.me/bueorm)
|
| 63 |
+
- [Patreon Subscription](https//patreon.com/bueorm)
|