Edit model card

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


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:"""
Downloads last month
11
Safetensors
Model size
8.03B params
Tensor type
FP16
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Hemanth-thunder/tamil-llama3-8B-open-instruct-v1-SFT-test

Space using Hemanth-thunder/tamil-llama3-8B-open-instruct-v1-SFT-test 1