Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
---
|
| 2 |
license: cc
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- code
|
| 8 |
+
- python
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
### CodePigeon
|
| 12 |
+
|
| 13 |
+
## Summary
|
| 14 |
+
|
| 15 |
+
Introducing "CodePigon", a new coding model, is it good enough; nah but its so much better than 'BrtGPT-1-PreCode'.
|
| 16 |
+
Also its a test model, not a full product. I will release the new, better, final model on 25 November 2026.
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
|Parameters|Architecture|Training Final Loss|Training Data|Training Language|Context Lenght|
|
| 21 |
+
|22~ Million|GPT-2 Arch.|1.6-1.8|22.000 QA Code Pairs|EN (English) + PY (Python)|256 Tokens -I know its very short for coding-
|
| 22 |
+
|
| 23 |
+
Model is trained on Google Colab for couple hours.
|
| 24 |
+
|
| 25 |
+
Model uses "```python" (3x back-quote) for codes
|
| 26 |
+
|
| 27 |
+
## Newer Models, Probable Risks
|
| 28 |
+
|
| 29 |
+
I'll train a new model with at least 3-4x more data and context lenght for so much better performance.
|
| 30 |
+
|
| 31 |
+
Also model is not super good in coding but its not censored, so it can generate harmfull or any other 'bad' content, ***USE WITH CAUTION***
|