Model Card for Model ID

Model description

odiagenAI-bengali-lora-model-v1 is based on Llama-7b and finetuned with 252k Bengali instruction set. The instruction set is translated data from open-source resources, resulting in good Bengali instruction understanding and response generation capabilities.

The code of Bengali data generation and other detailed information can be found in our Github project repository: https://github.com/OdiaGenAI/GenerativeAI_and_LLM_Odia.

Training hyper-parameters

Parameter	Value
Batch size	128
Learning rate	3e-4
Epochs	5
Cutoff length	256
Weight_decay	0.001
Warmup_rate	0.1
LR_scheduler	linear
Lora r	16
Lora target modules	(q_proj, k_proj, v_proj, o_proj)

Instructions for running it can be found at https://github.com/OdiaGenAI/GenerativeAI_and_LLM_Odia.

Licensing Information

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Citation Information

If you find this helpful repository, please consider giving 👏 and citing:

@misc{OdiaGenAI-Bengali-LLM,
  author = {Shantipriya Parida and Sambit Sekhar and Guneet Singh Kohli and Arghyadeep Sen and Shashikanta Sahoo},
  title = {Bengali Instruction-Tuning Model},
  year = {2023},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/OdiaGenAI}},
}

Contributions

Shantipriya Parida
Sambit Sekhar
Guneet Singh Kohli
Arghyadeep Sen
Shashikanta Sahoo