Commit
•
837acef
1
Parent(s):
6e81cd4
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ Base model: CorticalStack/gemma-7b-ultrachat-sft
|
|
| 5 |
|
| 6 |
This is finetuned from above base model and to be used for multi-turn chat based use-cases.
|
| 7 |
Unlike our AryaBhatta-GemmaOrca model which is skilled in science, literature and finetuned on Orca datasets, this model is fine-tuned on Ultra-Chat datasets. And show improved performance over AryaBhatta-GemmaOrca on Hellaswag datasets and in multi-turn conversations.
|
|
|
|
| 8 |
|
| 9 |
Benchmarked on Indic LLM leaderboard:
|
| 10 |
https://huggingface.co/spaces/Cognitive-Lab/indic_llm_leaderboard
|
|
|
|
| 5 |
|
| 6 |
This is finetuned from above base model and to be used for multi-turn chat based use-cases.
|
| 7 |
Unlike our AryaBhatta-GemmaOrca model which is skilled in science, literature and finetuned on Orca datasets, this model is fine-tuned on Ultra-Chat datasets. And show improved performance over AryaBhatta-GemmaOrca on Hellaswag datasets and in multi-turn conversations.
|
| 8 |
+
It is finetuned on 9 Indian languages (Hindi, Tamil, Punjabi, Bengali, Gujarati, Oriya, Telugu, Kannada, Malayalam) plus English.
|
| 9 |
|
| 10 |
Benchmarked on Indic LLM leaderboard:
|
| 11 |
https://huggingface.co/spaces/Cognitive-Lab/indic_llm_leaderboard
|