Commit
•
b942023
1
Parent(s):
b6e5e3e
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,9 +2,11 @@
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
|
| 5 |
-
This model is finetuned from HuggingFaceH4/zephyr-7b-gemma-v0.1 and is finetuned on 9 Indian languages (Hindi, Tamil, Punjabi, Bengali, Gujarati, Oriya, Telugu, Kannada, Malayalam) plus English.
|
| 6 |
To improve the resoning and maths skills, we first SFT tune the gemma on Microsoft's Orca datasets.
|
| 7 |
|
|
|
|
|
|
|
| 8 |
We utilize Orca maths Hindi dataset: GenVRadmin/Aryabhatta-Orca-Maths-Hindi \
|
| 9 |
And original Orca maths dataset: microsoft/orca-math-word-problems-200k
|
| 10 |
|
|
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
|
| 5 |
+
This model is a part of two model series, AryaBhatta-1 and AryaBhatta-2 and is finetuned from HuggingFaceH4/zephyr-7b-gemma-v0.1 or Google/gemma and is finetuned on 9 Indian languages (Hindi, Tamil, Punjabi, Bengali, Gujarati, Oriya, Telugu, Kannada, Malayalam) plus English.
|
| 6 |
To improve the resoning and maths skills, we first SFT tune the gemma on Microsoft's Orca datasets.
|
| 7 |
|
| 8 |
+
There are two models. One finetuned on Google's Gemma and one fine-tuned on Zephyr's Gemma base. Repo for other one (Zephyr one): GenVRadmin/AryaBhatta-GemmaOrca-2-Merged
|
| 9 |
+
|
| 10 |
We utilize Orca maths Hindi dataset: GenVRadmin/Aryabhatta-Orca-Maths-Hindi \
|
| 11 |
And original Orca maths dataset: microsoft/orca-math-word-problems-200k
|
| 12 |
|