RichardErkhov/l3cube-pune_-_marathi-gpt-gemma-2b-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

marathi-gpt-gemma-2b - AWQ

• Model creator: https://huggingface.co./l3cube-pune/
• Original model: https://huggingface.co./l3cube-pune/marathi-gpt-gemma-2b/

Original model description:

license: cc-by-4.0 language: mr widget: # - text: \n### Instruction:\n(9+0)+(10+5)? 3 चरणांमध्ये सोडवा\n\n### Input:\n\n\n### Response:\n - text: \n### Instruction:\nमहाराष्ट्राची राजधानी काय आहे?\n\n### Input:\n\n\n### Response:\n

MahaGemma-2B

MahaGemma-2B is a Marathi Gemma model. It is a Gemma 2B (google/gemma-2b) model LoRA fine-tuned on translated Marathi datasets. [dataset link] (https://github.com/l3cube-pune/MarathiNLP)

This is part of the MahaNLP initiative. More details coming soon.

Prompt format:

<bos>\n### Instruction:\nमहाराष्ट्राची राजधानी काय आहे?\n\n### Input:\n\n\n### Response:\nमहाराष्ट्राची राजधानी मुंबई आहे

Citing

@article{joshi2022l3cube,
  title={L3cube-mahanlp: Marathi natural language processing datasets, models, and library},
  author={Joshi, Raviraj},
  journal={arXiv preprint arXiv:2205.14728},
  year={2022}
}

Model Family:
MahaGemma-2B
MahaGemma-7B