Hemanth-thunder's picture
Update README.md
71eccb0 verified
---
library_name: transformers
license: apache-2.0
language:
- ta
datasets:
- Hemanth-thunder/tamil-open-instruct-v1
---
# Model Card for Model ID
Tamil Llama 3 8B Test SFT, With existing BytePair tokenizer
Training with NVIDIA L40 45GB
## GitHub Link
https://github.com/Hemanthkumar2112/Llama3-8B-Finetune-and-RAG/blob/main/tamil_llama3-SFT_test_existing_tokenizer.ipynb
```python
prompt_template_wo_input="""சரியான பதிலுடன் வேலையை வெற்றிகரமாக முடிக்க, தேவையான தகவலை உள்ளிடவும்.
### Instruction:
{}
### Response:"""
# with Input
prompt_template_input="""சரியான பதிலுடன் வேலையை வெற்றிகரமாக முடிக்க, வழங்கப்பட்ட வழிகாட்டுதல்களைப் பின்பற்றி, தேவையான தகவலை உள்ளிடவும்.
### Instruction:
{}
### Input:
{}
### Response:"""
```