NextGLab/ORANSight_Gemma_2_2B_Instruct

1---2base_model: unsloth/gemma-2-2b-it-bnb-4bit3tags:4- text-generation-inference5- transformers6- unsloth7- gemma28- trl9- sft10license: gemma11language:12- en13---14 15# Model Card for ORANSight Gemma-2B16 17This model belongs to the first release of the ORANSight family of models.18 19- **Developed by:** NextG lab@ NC State20- **License:** gemma21- **Context Window:** 8192 tokens  22- **Fine Tuning Framework:** Unsloth23  24### Generate with Transformers  25Below is a quick example of how to use the model with Hugging Face Transformers:  26 27```python28from transformers import pipeline29 30# Example query31messages = [32    {"role": "system", "content": "You are an O-RAN expert assistant."},33    {"role": "user", "content": "Explain the E2 interface."},34]35 36# Load the model37chatbot = pipeline("text-generation", model="NextGLab/ORANSight_Gemma_2_2B_Instruct")38result = chatbot(messages)39print(result)40```41 42### Coming Soon  43A detailed paper documenting the experiments and results achieved with this model will be available soon. Meanwhile, if you try this model, please cite the below mentioned paper to acknowledge the foundational work that enabled this fine-tuning.  44 45```bibtex46@article{gajjar2024oran,47  title={Oran-bench-13k: An open source benchmark for assessing llms in open radio access networks},48  author={Gajjar, Pranshav and Shah, Vijay K},49  journal={arXiv preprint arXiv:2407.06245},50  year={2024}51}52```  53---