Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,30 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
emoji: 📊
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: red
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Konkani LLM
|
| 3 |
emoji: 📊
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: red
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
+
license: apache-2.0
|
| 9 |
---
|
| 10 |
+
# Konkani LLM
|
| 11 |
|
| 12 |
+
A suite of large language models fine-tuned to support **Konkani** in **Devanagari, Roman, and Kannada scripts**.
|
| 13 |
+
These models focus on **translation, transliteration, question answering, and conversational tasks** in Konkani.
|
| 14 |
+
|
| 15 |
+
## Key Features
|
| 16 |
+
- Multiscript Support (Devanagari, Roman, Kannada)
|
| 17 |
+
- Translation: Konkani ↔ English, Hindi, Portuguese
|
| 18 |
+
- Question Answering and Dialogue
|
| 19 |
+
- Script-aware Tokenization for Improved Efficiency
|
| 20 |
+
|
| 21 |
+
## License
|
| 22 |
+
The base model is derived from **Meta’s LLaMA / Google’s Gemma**,
|
| 23 |
+
and thus this project is distributed under their respective license terms.
|
| 24 |
+
Please review:
|
| 25 |
+
- [LLaMA Community License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
|
| 26 |
+
- [Gemma License](https://ai.google.dev/gemma/terms)
|
| 27 |
+
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
_Developed by Reuben for advancing AI support in low-resource Indian languages._
|