metadata
language:
- en
- hi
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- gemma
- trl
base_model: unsloth/gemma-7b-bnb-4bit
datasets:
- fnnerd/Baatcheet_Hinglish_English_Translation_Corpus
- findnitai/english-to-hinglish
Model Summary
Based on the pre-quantized Gemma-7B model, this model has been fine-tuned on the Gemma-7B base model for Hinglish/English translations and completions using QLoRA. The training data includes two datasets: fnnerd/Baatcheet_Hinglish_English_Translation_Corpus and findnitai/english-to-hinglish.
This model, developed by L00ny Labs, has been open-sourced for research purposes. For commercial applications, a more accurate and finetuned model can be provided. For inquiries, please contact us (details below).
Uploaded
- Developed by: fnnerd
- License: apache-2.0
- Finetuned from model : gemma-7b
- Finetuned from model : L00ny Labs. Email: L00ny Labs [email protected]. LI: https://www.linkedin.com/in/sambodhi-khandelwal-42a18816/
Thanks to Unsloth and Huggingface's TRL library.
