Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- Kamisori-daijin/email-datasets-20k
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- small
|
| 9 |
+
- cpu
|
| 10 |
+
- email
|
| 11 |
+
- mail
|
| 12 |
+
- e-mail
|
| 13 |
+
- tiny
|
| 14 |
+
- nanogpt
|
| 15 |
+
- gpt
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# Welcome to eMail-LM
|
| 19 |
+
This is a 44.64M parameter GPT model which generates E-Mails.
|
| 20 |
+
|
| 21 |
+
## How to use
|
| 22 |
+
To use this model, download `model.pt` and `use.py` from this repo and run `use.py`.
|
| 23 |
+
|
| 24 |
+
## Sample
|
| 25 |
+
Input: `Write an email to my boss about a server outage.`
|
| 26 |
+
Output:
|
| 27 |
+
```plaintext
|
| 28 |
+
SUBJECT: Regarding the Server Outage - Seriously?
|
| 29 |
+
BODY:
|
| 30 |
+
[Name],
|
| 31 |
+
Let's be blunt. The server went down last night, and now a bad timing – on a Friday night. Frankly, it was unacceptable. I'm not going to sugarcoat it.
|
| 32 |
+
I'm not interested in excuses about how this happened, and I'm fixing it. I expect a full report by [Time] today.
|
| 33 |
+
|
| 34 |
+
[Your Name]
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## Training code
|
| 38 |
+
The full training code can be found as `train.ipynb` in this repo. Have fun :D
|
| 39 |
+
|
| 40 |
+
## Limitations
|
| 41 |
+
As this is a very small model and it wasn't trained for a really long time, it still generates garbage - but always emails. It's definetely more for research purposes.
|